diff --git a/2. Automatic Number Plate Detection.ipynb b/2. Automatic Number Plate Detection.ipynb new file mode 100644 index 000000000..c55e99c85 --- /dev/null +++ b/2. Automatic Number Plate Detection.ipynb @@ -0,0 +1,14078 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# GUI using Gradio" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Collecting gradio\n", + " Downloading gradio-3.35.2-py3-none-any.whl (19.7 MB)\n", + " 0.0/19.7 MB ? eta -:--:--\n", + " 0.1/19.7 MB 3.8 MB/s eta 0:00:06\n", + " 0.3/19.7 MB 3.7 MB/s eta 0:00:06\n", + " - 0.8/19.7 MB 7.7 MB/s eta 0:00:03\n", + " -- 1.4/19.7 MB 8.6 MB/s eta 0:00:03\n", + " --- 1.9/19.7 MB 9.3 MB/s eta 0:00:02\n", + " ----- 2.6/19.7 MB 10.3 MB/s eta 0:00:02\n", + " ------ 3.2/19.7 MB 10.7 MB/s eta 0:00:02\n", + " -------- 4.0/19.7 MB 11.5 MB/s eta 0:00:02\n", + " --------- 4.8/19.7 MB 12.2 MB/s eta 0:00:02\n", + " ----------- 5.6/19.7 MB 12.9 MB/s eta 0:00:02\n", + " ------------- 6.5/19.7 MB 13.3 MB/s eta 0:00:01\n", + " -------------- 7.4/19.7 MB 13.9 MB/s eta 0:00:01\n", + " ---------------- 8.3/19.7 MB 14.4 MB/s eta 0:00:01\n", + " ------------------- 9.5/19.7 MB 15.2 MB/s eta 0:00:01\n", + " -------------------- 10.5/19.7 MB 16.8 MB/s eta 0:00:01\n", + " ---------------------- 11.6/19.7 MB 18.2 MB/s eta 0:00:01\n", + " ------------------------ 12.4/19.7 MB 19.2 MB/s eta 0:00:01\n", + " -------------------------- 13.5/19.7 MB 19.8 MB/s eta 0:00:01\n", + " ----------------------------- 14.8/19.7 MB 21.1 MB/s eta 0:00:01\n", + " ------------------------------- 16.1/19.7 MB 23.4 MB/s eta 0:00:01\n", + " ---------------------------------- 17.5/19.7 MB 24.2 MB/s eta 0:00:01\n", + " ------------------------------------- 19.1/19.7 MB 26.2 MB/s eta 0:00:01\n", + " -------------------------------------- 19.7/19.7 MB 26.2 MB/s eta 0:00:01\n", + " -------------------------------------- 19.7/19.7 MB 26.2 MB/s eta 0:00:01\n", + " --------------------------------------- 19.7/19.7 MB 21.9 MB/s eta 0:00:00\n", + "Collecting aiofiles (from gradio)\n", + " Using cached aiofiles-23.1.0-py3-none-any.whl (14 kB)\n", + "Collecting aiohttp (from gradio)\n", + " Using cached aiohttp-3.8.4-cp39-cp39-win_amd64.whl (323 kB)\n", + "Collecting altair>=4.2.0 (from gradio)\n", + " Using cached altair-5.0.1-py3-none-any.whl (471 kB)\n", + "Collecting fastapi (from gradio)\n", + " Downloading fastapi-0.98.0-py3-none-any.whl (56 kB)\n", + " 0.0/57.0 kB ? eta -:--:--\n", + " ---------------------------------------- 57.0/57.0 kB ? eta 0:00:00\n", + "Collecting ffmpy (from gradio)\n", + " Using cached ffmpy-0.3.0-py3-none-any.whl\n", + "Collecting gradio-client>=0.2.7 (from gradio)\n", + " Downloading gradio_client-0.2.7-py3-none-any.whl (288 kB)\n", + " 0.0/288.4 kB ? eta -:--:--\n", + " ---------------------------------------- 288.4/288.4 kB ? eta 0:00:00\n", + "Collecting httpx (from gradio)\n", + " Using cached httpx-0.24.1-py3-none-any.whl (75 kB)\n", + "Collecting huggingface-hub>=0.14.0 (from gradio)\n", + " Using cached huggingface_hub-0.15.1-py3-none-any.whl (236 kB)\n", + "Requirement already satisfied: jinja2 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from gradio) (3.1.2)\n", + "Collecting markdown-it-py[linkify]>=2.0.0 (from gradio)\n", + " Using cached markdown_it_py-3.0.0-py3-none-any.whl (87 kB)\n", + "Requirement already satisfied: markupsafe in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from gradio) (2.1.2)\n", + "Requirement already satisfied: matplotlib in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from gradio) (3.7.1)\n", + "Collecting mdit-py-plugins<=0.3.3 (from gradio)\n", + " Using cached mdit_py_plugins-0.3.3-py3-none-any.whl (50 kB)\n", + "Requirement already satisfied: numpy in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from gradio) (1.23.5)\n", + "Collecting orjson (from gradio)\n", + " Downloading orjson-3.9.1-cp39-none-win_amd64.whl (191 kB)\n", + " 0.0/191.7 kB ? eta -:--:--\n", + " ------------------------------------- 191.7/191.7 kB 11.3 MB/s eta 0:00:00\n", + "Requirement already satisfied: pandas in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages\\pandas-2.0.0rc1-py3.9-win-amd64.egg (from gradio) (2.0.0rc1)\n", + "Requirement already satisfied: pillow in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from gradio) (9.4.0)\n", + "Collecting pydantic (from gradio)\n", + " Downloading pydantic-1.10.9-cp39-cp39-win_amd64.whl (2.2 MB)\n", + " 0.0/2.2 MB ? eta -:--:--\n", + " -------------------------------------- 2.1/2.2 MB 45.2 MB/s eta 0:00:01\n", + " ---------------------------------------- 2.2/2.2 MB 35.1 MB/s eta 0:00:00\n", + "Collecting pydub (from gradio)\n", + " Using cached pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n", + "Requirement already satisfied: pygments>=2.12.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from gradio) (2.14.0)\n", + "Collecting python-multipart (from gradio)\n", + " Using cached python_multipart-0.0.6-py3-none-any.whl (45 kB)\n", + "Requirement already satisfied: pyyaml in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from gradio) (5.1)\n", + "Requirement already satisfied: requests in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from gradio) (2.28.2)\n", + "Collecting semantic-version (from gradio)\n", + " Using cached semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n", + "Collecting uvicorn>=0.14.0 (from gradio)\n", + " Using cached uvicorn-0.22.0-py3-none-any.whl (58 kB)\n", + "Collecting websockets>=10.0 (from gradio)\n", + " Using cached websockets-11.0.3-cp39-cp39-win_amd64.whl (124 kB)\n", + "Collecting jsonschema>=3.0 (from altair>=4.2.0->gradio)\n", + " Downloading jsonschema-4.17.3-py3-none-any.whl (90 kB)\n", + " 0.0/90.4 kB ? eta -:--:--\n", + " ---------------------------------------- 90.4/90.4 kB ? eta 0:00:00\n", + "Collecting toolz (from altair>=4.2.0->gradio)\n", + " Downloading toolz-0.12.0-py3-none-any.whl (55 kB)\n", + " 0.0/55.8 kB ? eta -:--:--\n", + " ---------------------------------------- 55.8/55.8 kB ? eta 0:00:00\n", + "Requirement already satisfied: typing-extensions>=4.0.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from altair>=4.2.0->gradio) (4.5.0)\n", + "Collecting fsspec (from gradio-client>=0.2.7->gradio)\n", + " Downloading fsspec-2023.6.0-py3-none-any.whl (163 kB)\n", + " 0.0/163.8 kB ? eta -:--:--\n", + " ---------------------------------------- 163.8/163.8 kB ? eta 0:00:00\n", + "Requirement already satisfied: packaging in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from gradio-client>=0.2.7->gradio) (23.0)\n", + "Requirement already satisfied: filelock in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from huggingface-hub>=0.14.0->gradio) (3.9.0)\n", + "Collecting tqdm>=4.42.1 (from huggingface-hub>=0.14.0->gradio)\n", + " Downloading tqdm-4.65.0-py3-none-any.whl (77 kB)\n", + " 0.0/77.1 kB ? eta -:--:--\n", + " ---------------------------------------- 77.1/77.1 kB ? eta 0:00:00\n", + "Collecting mdurl~=0.1 (from markdown-it-py[linkify]>=2.0.0->gradio)\n", + " Using cached mdurl-0.1.2-py3-none-any.whl (10.0 kB)\n", + "Collecting linkify-it-py<3,>=1 (from markdown-it-py[linkify]>=2.0.0->gradio)\n", + " Using cached linkify_it_py-2.0.2-py3-none-any.whl (19 kB)\n", + "INFO: pip is looking at multiple versions of mdit-py-plugins to determine which version is compatible with other requirements. This could take a while.\n", + "Collecting mdit-py-plugins<=0.3.3 (from gradio)\n", + " Using cached mdit_py_plugins-0.3.2-py3-none-any.whl (50 kB)\n", + " Using cached mdit_py_plugins-0.3.1-py3-none-any.whl (46 kB)\n", + " Using cached mdit_py_plugins-0.3.0-py3-none-any.whl (43 kB)\n", + " Using cached mdit_py_plugins-0.2.8-py3-none-any.whl (41 kB)\n", + " Using cached mdit_py_plugins-0.2.7-py3-none-any.whl (41 kB)\n", + " Using cached mdit_py_plugins-0.2.6-py3-none-any.whl (39 kB)\n", + " Using cached mdit_py_plugins-0.2.5-py3-none-any.whl (39 kB)\n", + "INFO: pip is looking at multiple versions of mdit-py-plugins to determine which version is compatible with other requirements. This could take a while.\n", + " Using cached mdit_py_plugins-0.2.4-py3-none-any.whl (39 kB)\n", + " Using cached mdit_py_plugins-0.2.3-py3-none-any.whl (39 kB)\n", + " Using cached mdit_py_plugins-0.2.2-py3-none-any.whl (39 kB)\n", + " Using cached mdit_py_plugins-0.2.1-py3-none-any.whl (38 kB)\n", + " Using cached mdit_py_plugins-0.2.0-py3-none-any.whl (38 kB)\n", + "INFO: This is taking longer than usual. You might need to provide the dependency resolver with stricter constraints to reduce runtime. See https://pip.pypa.io/warnings/backtracking for guidance. If you want to abort this run, press Ctrl + C.\n", + " Using cached mdit_py_plugins-0.1.0-py3-none-any.whl (37 kB)\n", + "Collecting markdown-it-py[linkify]>=2.0.0 (from gradio)\n", + " Using cached markdown_it_py-2.2.0-py3-none-any.whl (84 kB)\n", + "Requirement already satisfied: python-dateutil>=2.8.2 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from pandas->gradio) (2.8.2)\n", + "Requirement already satisfied: pytz>=2020.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from pandas->gradio) (2023.3)\n", + "Collecting click>=7.0 (from uvicorn>=0.14.0->gradio)\n", + " Downloading click-8.1.3-py3-none-any.whl (96 kB)\n", + " 0.0/96.6 kB ? eta -:--:--\n", + " ---------------------------------------- 96.6/96.6 kB 5.8 MB/s eta 0:00:00\n", + "Collecting h11>=0.8 (from uvicorn>=0.14.0->gradio)\n", + " Using cached h11-0.14.0-py3-none-any.whl (58 kB)\n", + "Collecting attrs>=17.3.0 (from aiohttp->gradio)\n", + " Downloading attrs-23.1.0-py3-none-any.whl (61 kB)\n", + " 0.0/61.2 kB ? eta -:--:--\n", + " ---------------------------------------- 61.2/61.2 kB 3.2 MB/s eta 0:00:00\n", + "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from aiohttp->gradio) (3.1.0)\n", + "Collecting multidict<7.0,>=4.5 (from aiohttp->gradio)\n", + " Using cached multidict-6.0.4-cp39-cp39-win_amd64.whl (28 kB)\n", + "Collecting async-timeout<5.0,>=4.0.0a3 (from aiohttp->gradio)\n", + " Using cached async_timeout-4.0.2-py3-none-any.whl (5.8 kB)\n", + "Collecting yarl<2.0,>=1.0 (from aiohttp->gradio)\n", + " Using cached yarl-1.9.2-cp39-cp39-win_amd64.whl (61 kB)\n", + "Collecting frozenlist>=1.1.1 (from aiohttp->gradio)\n", + " Using cached frozenlist-1.3.3-cp39-cp39-win_amd64.whl (34 kB)\n", + "Collecting aiosignal>=1.1.2 (from aiohttp->gradio)\n", + " Using cached aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n", + "Collecting starlette<0.28.0,>=0.27.0 (from fastapi->gradio)\n", + " Using cached starlette-0.27.0-py3-none-any.whl (66 kB)\n", + "Requirement already satisfied: certifi in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from httpx->gradio) (2022.12.7)\n", + "Collecting httpcore<0.18.0,>=0.15.0 (from httpx->gradio)\n", + " Using cached httpcore-0.17.2-py3-none-any.whl (72 kB)\n", + "Requirement already satisfied: idna in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from httpx->gradio) (3.4)\n", + "Collecting sniffio (from httpx->gradio)\n", + " Downloading sniffio-1.3.0-py3-none-any.whl (10 kB)\n", + "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib->gradio) (1.0.7)\n", + "Requirement already satisfied: cycler>=0.10 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib->gradio) (0.11.0)\n", + "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib->gradio) (4.39.2)\n", + "Requirement already satisfied: kiwisolver>=1.0.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib->gradio) (1.4.4)\n", + "Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages\\pyparsing-2.4.7-py3.9.egg (from matplotlib->gradio) (2.4.7)\n", + "Requirement already satisfied: importlib-resources>=3.2.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib->gradio) (5.12.0)\n", + "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from requests->gradio) (1.26.15)\n", + "Requirement already satisfied: colorama in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from click>=7.0->uvicorn>=0.14.0->gradio) (0.4.6)\n", + "Collecting anyio<5.0,>=3.0 (from httpcore<0.18.0,>=0.15.0->httpx->gradio)\n", + " Downloading anyio-3.7.0-py3-none-any.whl (80 kB)\n", + " 0.0/80.9 kB ? eta -:--:--\n", + " ---------------------------------------- 80.9/80.9 kB 4.4 MB/s eta 0:00:00\n", + "Requirement already satisfied: zipp>=3.1.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from importlib-resources>=3.2.0->matplotlib->gradio) (3.15.0)\n", + "Collecting pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 (from jsonschema>=3.0->altair>=4.2.0->gradio)\n", + " Downloading pyrsistent-0.19.3-cp39-cp39-win_amd64.whl (62 kB)\n", + " 0.0/62.7 kB ? eta -:--:--\n", + " ---------------------------------------- 62.7/62.7 kB ? eta 0:00:00\n", + "Collecting uc-micro-py (from linkify-it-py<3,>=1->markdown-it-py[linkify]>=2.0.0->gradio)\n", + " Using cached uc_micro_py-1.0.2-py3-none-any.whl (6.2 kB)\n", + "Requirement already satisfied: six>=1.5 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from python-dateutil>=2.8.2->pandas->gradio) (1.16.0)\n", + "Collecting exceptiongroup (from anyio<5.0,>=3.0->httpcore<0.18.0,>=0.15.0->httpx->gradio)\n", + " Downloading exceptiongroup-1.1.1-py3-none-any.whl (14 kB)\n", + "Installing collected packages: pydub, ffmpy, websockets, uc-micro-py, tqdm, toolz, sniffio, semantic-version, python-multipart, pyrsistent, pydantic, orjson, multidict, mdurl, h11, fsspec, frozenlist, exceptiongroup, click, attrs, async-timeout, aiofiles, yarl, uvicorn, markdown-it-py, linkify-it-py, jsonschema, huggingface-hub, anyio, aiosignal, starlette, mdit-py-plugins, httpcore, altair, aiohttp, httpx, fastapi, gradio-client, gradio\n", + "Successfully installed aiofiles-23.1.0 aiohttp-3.8.4 aiosignal-1.3.1 altair-5.0.1 anyio-3.7.0 async-timeout-4.0.2 attrs-23.1.0 click-8.1.3 exceptiongroup-1.1.1 fastapi-0.98.0 ffmpy-0.3.0 frozenlist-1.3.3 fsspec-2023.6.0 gradio-3.35.2 gradio-client-0.2.7 h11-0.14.0 httpcore-0.17.2 httpx-0.24.1 huggingface-hub-0.15.1 jsonschema-4.17.3 linkify-it-py-2.0.2 markdown-it-py-2.2.0 mdit-py-plugins-0.3.3 mdurl-0.1.2 multidict-6.0.4 orjson-3.9.1 pydantic-1.10.9 pydub-0.25.1 pyrsistent-0.19.3 python-multipart-0.0.6 semantic-version-2.10.0 sniffio-1.3.0 starlette-0.27.0 toolz-0.12.0 tqdm-4.65.0 uc-micro-py-1.0.2 uvicorn-0.22.0 websockets-11.0.3 yarl-1.9.2\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", + "apache-beam 2.46.0 requires cloudpickle~=2.2.1, which is not installed.\n", + "apache-beam 2.46.0 requires crcmod<2.0,>=1.7, which is not installed.\n", + "apache-beam 2.46.0 requires dill<0.3.2,>=0.3.1.1, which is not installed.\n", + "apache-beam 2.46.0 requires fastavro<2,>=0.23.6, which is not installed.\n", + "apache-beam 2.46.0 requires fasteners<1.0,>=0.3, which is not installed.\n", + "apache-beam 2.46.0 requires hdfs<3.0.0,>=2.1.0, which is not installed.\n", + "apache-beam 2.46.0 requires httplib2<0.22.0,>=0.8, which is not installed.\n", + "apache-beam 2.46.0 requires objsize<0.7.0,>=0.6.1, which is not installed.\n", + "apache-beam 2.46.0 requires proto-plus<2,>=1.7.1, which is not installed.\n", + "apache-beam 2.46.0 requires pyarrow<10.0.0,>=3.0.0, which is not installed.\n", + "apache-beam 2.46.0 requires pydot<2,>=1.2.0, which is not installed.\n", + "apache-beam 2.46.0 requires pymongo<4.0.0,>=3.8.0, which is not installed.\n", + "apache-beam 2.46.0 requires zstandard<1,>=0.18.0, which is not installed.\n" + ] + } + ], + "source": [ + "!pip install gradio" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\gradio\\interface.py:326: UserWarning: The `allow_flagging` parameter in `Interface` nowtakes a string value ('auto', 'manual', or 'never'), not a boolean. Setting parameter to: 'never'.\n", + " warnings.warn(\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Running on local URL: http://127.0.0.1:7869\n", + "\n", + "To create a public link, set `share=True` in `launch()`.\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 59, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import gradio as gr\n", + "import tensorflow as tf\n", + "import numpy as np\n", + "import cv2\n", + "\n", + "\n", + "# Function to perform image recognition\n", + "def recognize_image(input_image):\n", + " # Load the TensorFlow model\n", + " model = tf.saved_model.load('PRETRAINED_MODEL_PATH') # Replace with the path to your saved model\n", + " \n", + " # Preprocess the image\n", + " image_rgb = cv2.cvtColor(input_image, cv2.COLOR_BGR2RGB)\n", + " image_resized = cv2.resize(image_rgb, (input_width, input_height))\n", + " input_tensor = np.expand_dims(image_resized, 0)\n", + " input_tensor = input_tensor.astype(np.uint8)\n", + " \n", + " # Perform object detection on the image\n", + " detections = model(input_tensor)\n", + " \n", + " # Process the detection results\n", + " # You can replace this with your own code to extract relevant information from detections\n", + " \n", + " # Draw bounding boxes on the image\n", + " image_with_boxes = draw_boxes(input_image, detections)\n", + " \n", + " return image_with_boxes\n", + "\n", + "# Function to draw bounding boxes on the image\n", + "def draw_boxes(image, detections):\n", + " image_with_boxes = np.copy(image)\n", + " image_height, image_width, _ = image.shape\n", + " \n", + " # Process the detection results and draw bounding boxes\n", + " for detection in detections:\n", + " # Extract the bounding box coordinates and class label\n", + " box = detection['box']\n", + " class_label = detection['class_label']\n", + " \n", + " # Scale the bounding box coordinates\n", + " start_x = int(box[1] * image_width)\n", + " start_y = int(box[0] * image_height)\n", + " end_x = int(box[3] * image_width)\n", + " end_y = int(box[2] * image_height)\n", + " \n", + " # Draw the bounding box rectangle on the image\n", + " cv2.rectangle(image_with_boxes, (start_x, start_y), (end_x, end_y), (0, 255, 0), 2)\n", + " \n", + " # Add the class label text\n", + " label_text = f'{class_label}'\n", + " label_size, _ = cv2.getTextSize(label_text, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)\n", + " text_width, text_height = label_size\n", + " cv2.rectangle(image_with_boxes, (start_x, start_y - text_height - 5),\n", + " (start_x + text_width + 5, start_y), (0, 255, 0), -1)\n", + " cv2.putText(image_with_boxes, label_text, (start_x + 2, start_y - 2),\n", + " cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1, cv2.LINE_AA)\n", + " \n", + " return image_with_boxes\n", + "\n", + "# Define input size for the model\n", + "input_width = 640\n", + "input_height = 480\n", + "\n", + "# Create the Gradio interface\n", + "iface = gr.Interface(\n", + " fn=recognize_image,\n", + " inputs=\"image\",\n", + " outputs=\"image\",\n", + " title=\"Object Detection\",\n", + " description=\"Detect objects in an image.\",\n", + " allow_flagging=False\n", + ")\n", + "\n", + "# Launch the interface\n", + "iface.launch()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "QUANWN3rpfC9" + }, + "source": [ + "# 0. Setup Paths" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "146BB11JpfDA" + }, + "outputs": [], + "source": [ + "import os" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "42hJEdo_pfDB" + }, + "outputs": [], + "source": [ + "CUSTOM_MODEL_NAME = 'my_ssd_mobnet' \n", + "PRETRAINED_MODEL_NAME = 'ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8'\n", + "PRETRAINED_MODEL_URL = 'http://download.tensorflow.org/models/object_detection/tf2/20200711/ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8.tar.gz'\n", + "TF_RECORD_SCRIPT_NAME = 'generate_tfrecord.py'\n", + "LABEL_MAP_NAME = 'label_map.pbtxt'" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": { + "id": "hbPhYVy_pfDB" + }, + "outputs": [], + "source": [ + "paths = {\n", + " 'WORKSPACE_PATH': os.path.join('Tensorflow', 'workspace'),\n", + " 'SCRIPTS_PATH': os.path.join('Tensorflow','scripts'),\n", + " 'APIMODEL_PATH': os.path.join('Tensorflow','models'),\n", + " 'ANNOTATION_PATH': os.path.join('Tensorflow', 'workspace','annotations'),\n", + " 'IMAGE_PATH': os.path.join('Tensorflow', 'workspace','images'),\n", + " 'MODEL_PATH': os.path.join('Tensorflow', 'workspace','models'),\n", + " 'PRETRAINED_MODEL_PATH': os.path.join('Tensorflow', 'workspace','pre-trained-models','ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8'),\n", + " 'CHECKPOINT_PATH': os.path.join('Tensorflow', 'workspace','models',CUSTOM_MODEL_NAME), \n", + " 'OUTPUT_PATH': os.path.join('Tensorflow', 'workspace','models',CUSTOM_MODEL_NAME, 'export'), \n", + " 'TFJS_PATH':os.path.join('Tensorflow', 'workspace','models',CUSTOM_MODEL_NAME, 'tfjsexport'), \n", + " 'TFLITE_PATH':os.path.join('Tensorflow', 'workspace','models',CUSTOM_MODEL_NAME, 'tfliteexport'), \n", + " 'PROTOC_PATH':os.path.join('Tensorflow','protoc')\n", + " }" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "id": "LwhWZMI0pfDC" + }, + "outputs": [], + "source": [ + "files = {\n", + " 'PIPELINE_CONFIG':os.path.join('Tensorflow', 'workspace','models', CUSTOM_MODEL_NAME, 'pipeline.config'),\n", + " 'TF_RECORD_SCRIPT': os.path.join(paths['SCRIPTS_PATH'], TF_RECORD_SCRIPT_NAME), \n", + " 'LABELMAP': os.path.join(paths['ANNOTATION_PATH'], LABEL_MAP_NAME)\n", + "}" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "id": "HR-TfDGrpfDC" + }, + "outputs": [], + "source": [ + "for path in paths.values():\n", + " if not os.path.exists(path):\n", + " if os.name == 'posix':\n", + " !mkdir -p {path}\n", + " if os.name == 'nt':\n", + " !mkdir {path}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "OLU-rs_ipfDE" + }, + "source": [ + "# 1. Download TF Models Pretrained Models from Tensorflow Model Zoo and Install TFOD" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "id": "K-Cmz2edpfDE", + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: wget in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (3.2)\n" + ] + } + ], + "source": [ + "if os.name=='nt':\n", + " !pip install wget\n", + " import wget" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "id": "iA1DIq5OpfDE" + }, + "outputs": [], + "source": [ + "if not os.path.exists(os.path.join(paths['APIMODEL_PATH'], 'research', 'object_detection')):\n", + " !git clone https://github.com/tensorflow/models {paths['APIMODEL_PATH']}" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "collapsed": true, + "id": "rJjMHbnDs3Tv" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "100% [..........................................................................] 1468733 / 1468733 1 file(s) moved.\n", + " 1 file(s) copied.\n", + "running build\n", + "running build_py\n", + "copying object_detection\\protos\\anchor_generator_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\argmax_matcher_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\bipartite_matcher_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\box_coder_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\box_predictor_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\calibration_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\center_net_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\eval_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\faster_rcnn_box_coder_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\faster_rcnn_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\flexible_grid_anchor_generator_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\fpn_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\graph_rewriter_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\grid_anchor_generator_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\hyperparams_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\image_resizer_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\input_reader_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\keypoint_box_coder_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\losses_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\matcher_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\mean_stddev_box_coder_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\model_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\multiscale_anchor_generator_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\optimizer_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\pipeline_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\post_processing_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\preprocessor_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\region_similarity_calculator_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\square_box_coder_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\ssd_anchor_generator_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\ssd_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\string_int_label_map_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\target_assigner_pb2.py -> build\\lib\\object_detection\\protos\n", + "copying object_detection\\protos\\train_pb2.py -> build\\lib\\object_detection\\protos\n", + "running egg_info\n", + "writing object_detection.egg-info\\PKG-INFO\n", + "writing dependency_links to object_detection.egg-info\\dependency_links.txt\n", + "writing requirements to object_detection.egg-info\\requires.txt\n", + "writing top-level names to object_detection.egg-info\\top_level.txt\n", + "reading manifest file 'object_detection.egg-info\\SOURCES.txt'\n", + "writing manifest file 'object_detection.egg-info\\SOURCES.txt'\n", + "running install\n", + "running bdist_egg\n", + "running egg_info\n", + "writing object_detection.egg-info\\PKG-INFO\n", + "writing dependency_links to object_detection.egg-info\\dependency_links.txt\n", + "writing requirements to object_detection.egg-info\\requires.txt\n", + "writing top-level names to object_detection.egg-info\\top_level.txt\n", + "reading manifest file 'object_detection.egg-info\\SOURCES.txt'\n", + "writing manifest file 'object_detection.egg-info\\SOURCES.txt'\n", + "installing library code to build\\bdist.win-amd64\\egg\n", + "running install_lib\n", + "running build_py\n", + "creating build\\bdist.win-amd64\\egg\n", + "creating build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\build_imagenet_data.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\cifar10.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\dataset_factory.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\dataset_utils.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\download_and_convert_cifar10.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\download_and_convert_flowers.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\download_and_convert_mnist.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\download_and_convert_visualwakewords.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\download_and_convert_visualwakewords_lib.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\flowers.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\imagenet.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\mnist.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\preprocess_imagenet_validation_data.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\process_bounding_boxes.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\visualwakewords.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "copying build\\lib\\datasets\\__init__.py -> build\\bdist.win-amd64\\egg\\datasets\n", + "creating build\\bdist.win-amd64\\egg\\deployment\n", + "copying build\\lib\\deployment\\model_deploy.py -> build\\bdist.win-amd64\\egg\\deployment\n", + "copying build\\lib\\deployment\\model_deploy_test.py -> build\\bdist.win-amd64\\egg\\deployment\n", + "copying build\\lib\\deployment\\__init__.py -> build\\bdist.win-amd64\\egg\\deployment\n", + "creating build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\alexnet.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\alexnet_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\cifarnet.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\cyclegan.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\cyclegan_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\dcgan.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\dcgan_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\i3d.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\i3d_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\i3d_utils.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception_resnet_v2.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception_resnet_v2_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception_utils.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception_v1.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception_v1_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception_v2.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception_v2_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception_v3.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception_v3_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception_v4.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\inception_v4_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\lenet.py -> build\\bdist.win-amd64\\egg\\nets\n", + "creating build\\bdist.win-amd64\\egg\\nets\\mobilenet\n", + "copying build\\lib\\nets\\mobilenet\\conv_blocks.py -> build\\bdist.win-amd64\\egg\\nets\\mobilenet\n", + "copying build\\lib\\nets\\mobilenet\\mobilenet.py -> build\\bdist.win-amd64\\egg\\nets\\mobilenet\n", + "copying build\\lib\\nets\\mobilenet\\mobilenet_v2.py -> build\\bdist.win-amd64\\egg\\nets\\mobilenet\n", + "copying build\\lib\\nets\\mobilenet\\mobilenet_v2_test.py -> build\\bdist.win-amd64\\egg\\nets\\mobilenet\n", + "copying build\\lib\\nets\\mobilenet\\mobilenet_v3.py -> build\\bdist.win-amd64\\egg\\nets\\mobilenet\n", + "copying build\\lib\\nets\\mobilenet\\mobilenet_v3_test.py -> build\\bdist.win-amd64\\egg\\nets\\mobilenet\n", + "copying build\\lib\\nets\\mobilenet\\__init__.py -> build\\bdist.win-amd64\\egg\\nets\\mobilenet\n", + "copying build\\lib\\nets\\mobilenet_v1.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\mobilenet_v1_eval.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\mobilenet_v1_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\mobilenet_v1_train.py -> build\\bdist.win-amd64\\egg\\nets\n", + "creating build\\bdist.win-amd64\\egg\\nets\\nasnet\n", + "copying build\\lib\\nets\\nasnet\\nasnet.py -> build\\bdist.win-amd64\\egg\\nets\\nasnet\n", + "copying build\\lib\\nets\\nasnet\\nasnet_test.py -> build\\bdist.win-amd64\\egg\\nets\\nasnet\n", + "copying build\\lib\\nets\\nasnet\\nasnet_utils.py -> build\\bdist.win-amd64\\egg\\nets\\nasnet\n", + "copying build\\lib\\nets\\nasnet\\nasnet_utils_test.py -> build\\bdist.win-amd64\\egg\\nets\\nasnet\n", + "copying build\\lib\\nets\\nasnet\\pnasnet.py -> build\\bdist.win-amd64\\egg\\nets\\nasnet\n", + "copying build\\lib\\nets\\nasnet\\pnasnet_test.py -> build\\bdist.win-amd64\\egg\\nets\\nasnet\n", + "copying build\\lib\\nets\\nasnet\\__init__.py -> build\\bdist.win-amd64\\egg\\nets\\nasnet\n", + "copying build\\lib\\nets\\nets_factory.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\nets_factory_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\overfeat.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\overfeat_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\pix2pix.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\pix2pix_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\post_training_quantization.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\resnet_utils.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\resnet_v1.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\resnet_v1_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\resnet_v2.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\resnet_v2_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\s3dg.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\s3dg_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\vgg.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\vgg_test.py -> build\\bdist.win-amd64\\egg\\nets\n", + "copying build\\lib\\nets\\__init__.py -> build\\bdist.win-amd64\\egg\\nets\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\n", + "copying build\\lib\\object_detection\\anchor_generators\\flexible_grid_anchor_generator.py -> build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\n", + "copying build\\lib\\object_detection\\anchor_generators\\flexible_grid_anchor_generator_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\n", + "copying build\\lib\\object_detection\\anchor_generators\\grid_anchor_generator.py -> build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\n", + "copying build\\lib\\object_detection\\anchor_generators\\grid_anchor_generator_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\n", + "copying build\\lib\\object_detection\\anchor_generators\\multiple_grid_anchor_generator.py -> build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\n", + "copying build\\lib\\object_detection\\anchor_generators\\multiple_grid_anchor_generator_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\n", + "copying build\\lib\\object_detection\\anchor_generators\\multiscale_grid_anchor_generator.py -> build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\n", + "copying build\\lib\\object_detection\\anchor_generators\\multiscale_grid_anchor_generator_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\n", + "copying build\\lib\\object_detection\\anchor_generators\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\box_coders\n", + "copying build\\lib\\object_detection\\box_coders\\faster_rcnn_box_coder.py -> build\\bdist.win-amd64\\egg\\object_detection\\box_coders\n", + "copying build\\lib\\object_detection\\box_coders\\faster_rcnn_box_coder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\box_coders\n", + "copying build\\lib\\object_detection\\box_coders\\keypoint_box_coder.py -> build\\bdist.win-amd64\\egg\\object_detection\\box_coders\n", + "copying build\\lib\\object_detection\\box_coders\\keypoint_box_coder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\box_coders\n", + "copying build\\lib\\object_detection\\box_coders\\mean_stddev_box_coder.py -> build\\bdist.win-amd64\\egg\\object_detection\\box_coders\n", + "copying build\\lib\\object_detection\\box_coders\\mean_stddev_box_coder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\box_coders\n", + "copying build\\lib\\object_detection\\box_coders\\square_box_coder.py -> build\\bdist.win-amd64\\egg\\object_detection\\box_coders\n", + "copying build\\lib\\object_detection\\box_coders\\square_box_coder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\box_coders\n", + "copying build\\lib\\object_detection\\box_coders\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\box_coders\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\anchor_generator_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\anchor_generator_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\box_coder_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\box_coder_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\box_predictor_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\box_predictor_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\calibration_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\calibration_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\dataset_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\dataset_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\decoder_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\decoder_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\graph_rewriter_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\graph_rewriter_builder_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\hyperparams_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\hyperparams_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\image_resizer_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\image_resizer_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\input_reader_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\input_reader_builder_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\losses_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\losses_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\matcher_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\matcher_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\model_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\model_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\model_builder_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\model_builder_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\optimizer_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\optimizer_builder_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\optimizer_builder_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\post_processing_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\post_processing_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\preprocessor_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\preprocessor_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\region_similarity_calculator_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\region_similarity_calculator_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\target_assigner_builder.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\target_assigner_builder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "copying build\\lib\\object_detection\\builders\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\builders\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\anchor_generator.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\balanced_positive_negative_sampler.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\balanced_positive_negative_sampler_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\batcher.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\batcher_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\batch_multiclass_nms_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\box_coder.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\box_coder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\box_list.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\box_list_ops.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\box_list_ops_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\box_list_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\box_predictor.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\class_agnostic_nms_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\data_decoder.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\data_parser.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\densepose_ops.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\densepose_ops_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\freezable_batch_norm.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\freezable_batch_norm_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\freezable_sync_batch_norm.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\keypoint_ops.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\keypoint_ops_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\losses.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\losses_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\matcher.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\matcher_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\minibatch_sampler.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\minibatch_sampler_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\model.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\model_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\multiclass_nms_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\post_processing.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\prefetcher.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\prefetcher_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\preprocessor.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\preprocessor_cache.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\preprocessor_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\region_similarity_calculator.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\region_similarity_calculator_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\standard_fields.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\target_assigner.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\target_assigner_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "copying build\\lib\\object_detection\\core\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\core\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\n", + "copying build\\lib\\object_detection\\dataset_tools\\context_rcnn\\add_context_to_examples.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\n", + "copying build\\lib\\object_detection\\dataset_tools\\context_rcnn\\add_context_to_examples_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\n", + "copying build\\lib\\object_detection\\dataset_tools\\context_rcnn\\create_cococameratraps_tfexample_main.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\n", + "copying build\\lib\\object_detection\\dataset_tools\\context_rcnn\\create_cococameratraps_tfexample_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\n", + "copying build\\lib\\object_detection\\dataset_tools\\context_rcnn\\generate_detection_data.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\n", + "copying build\\lib\\object_detection\\dataset_tools\\context_rcnn\\generate_detection_data_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\n", + "copying build\\lib\\object_detection\\dataset_tools\\context_rcnn\\generate_embedding_data.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\n", + "copying build\\lib\\object_detection\\dataset_tools\\context_rcnn\\generate_embedding_data_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\n", + "copying build\\lib\\object_detection\\dataset_tools\\context_rcnn\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\n", + "copying build\\lib\\object_detection\\dataset_tools\\create_ava_actions_tf_record.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\create_coco_tf_record.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\create_coco_tf_record_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\create_kitti_tf_record.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\create_kitti_tf_record_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\create_oid_tf_record.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\create_pascal_tf_record.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\create_pascal_tf_record_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\create_pet_tf_record.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\oid_hierarchical_labels_expansion.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\oid_hierarchical_labels_expansion_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\oid_tfrecord_creation.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\oid_tfrecord_creation_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\seq_example_util.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\seq_example_util_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\tf_record_creation_util.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\tf_record_creation_util_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "copying build\\lib\\object_detection\\dataset_tools\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\data_decoders\n", + "copying build\\lib\\object_detection\\data_decoders\\tf_example_decoder.py -> build\\bdist.win-amd64\\egg\\object_detection\\data_decoders\n", + "copying build\\lib\\object_detection\\data_decoders\\tf_example_decoder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\data_decoders\n", + "copying build\\lib\\object_detection\\data_decoders\\tf_sequence_example_decoder.py -> build\\bdist.win-amd64\\egg\\object_detection\\data_decoders\n", + "copying build\\lib\\object_detection\\data_decoders\\tf_sequence_example_decoder_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\data_decoders\n", + "copying build\\lib\\object_detection\\data_decoders\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\data_decoders\n", + "copying build\\lib\\object_detection\\eval_util.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\eval_util_test.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\exporter.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\exporter_lib_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\exporter_lib_v2.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\exporter_main_v2.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\exporter_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\export_inference_graph.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\export_tflite_graph_lib_tf2.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\export_tflite_graph_lib_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\export_tflite_graph_tf2.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\export_tflite_ssd_graph.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\export_tflite_ssd_graph_lib.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\export_tflite_ssd_graph_lib_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\inference\n", + "copying build\\lib\\object_detection\\inference\\detection_inference.py -> build\\bdist.win-amd64\\egg\\object_detection\\inference\n", + "copying build\\lib\\object_detection\\inference\\detection_inference_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\inference\n", + "copying build\\lib\\object_detection\\inference\\infer_detections.py -> build\\bdist.win-amd64\\egg\\object_detection\\inference\n", + "copying build\\lib\\object_detection\\inference\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\inference\n", + "copying build\\lib\\object_detection\\inputs.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\inputs_test.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\legacy\n", + "copying build\\lib\\object_detection\\legacy\\eval.py -> build\\bdist.win-amd64\\egg\\object_detection\\legacy\n", + "copying build\\lib\\object_detection\\legacy\\evaluator.py -> build\\bdist.win-amd64\\egg\\object_detection\\legacy\n", + "copying build\\lib\\object_detection\\legacy\\train.py -> build\\bdist.win-amd64\\egg\\object_detection\\legacy\n", + "copying build\\lib\\object_detection\\legacy\\trainer.py -> build\\bdist.win-amd64\\egg\\object_detection\\legacy\n", + "copying build\\lib\\object_detection\\legacy\\trainer_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\legacy\n", + "copying build\\lib\\object_detection\\legacy\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\legacy\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\matchers\n", + "copying build\\lib\\object_detection\\matchers\\argmax_matcher.py -> build\\bdist.win-amd64\\egg\\object_detection\\matchers\n", + "copying build\\lib\\object_detection\\matchers\\argmax_matcher_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\matchers\n", + "copying build\\lib\\object_detection\\matchers\\bipartite_matcher.py -> build\\bdist.win-amd64\\egg\\object_detection\\matchers\n", + "copying build\\lib\\object_detection\\matchers\\bipartite_matcher_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\matchers\n", + "copying build\\lib\\object_detection\\matchers\\hungarian_matcher.py -> build\\bdist.win-amd64\\egg\\object_detection\\matchers\n", + "copying build\\lib\\object_detection\\matchers\\hungarian_matcher_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\matchers\n", + "copying build\\lib\\object_detection\\matchers\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\matchers\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\center_net_meta_arch.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\center_net_meta_arch_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\context_rcnn_lib.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\context_rcnn_lib_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\context_rcnn_lib_tf2.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\context_rcnn_lib_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\context_rcnn_meta_arch.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\context_rcnn_meta_arch_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\deepmac_meta_arch.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\deepmac_meta_arch_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\faster_rcnn_meta_arch.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\faster_rcnn_meta_arch_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\faster_rcnn_meta_arch_test_lib.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\rfcn_meta_arch.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\rfcn_meta_arch_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\ssd_meta_arch.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\ssd_meta_arch_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\ssd_meta_arch_test_lib.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "copying build\\lib\\object_detection\\meta_architectures\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\calibration_evaluation.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\calibration_evaluation_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\calibration_metrics.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\calibration_metrics_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\coco_evaluation.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\coco_evaluation_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\coco_tools.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\coco_tools_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\io_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\lvis_evaluation.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\lvis_evaluation_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\lvis_tools.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\lvis_tools_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\offline_eval_map_corloc.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\offline_eval_map_corloc_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\oid_challenge_evaluation.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\oid_challenge_evaluation_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\oid_challenge_evaluation_utils_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\oid_vrd_challenge_evaluation.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\oid_vrd_challenge_evaluation_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\oid_vrd_challenge_evaluation_utils_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\tf_example_parser.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\tf_example_parser_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "copying build\\lib\\object_detection\\metrics\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\metrics\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\bidirectional_feature_pyramid_generators.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\bidirectional_feature_pyramid_generators_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\center_net_hourglass_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\center_net_hourglass_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\center_net_mobilenet_v2_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\center_net_mobilenet_v2_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\center_net_mobilenet_v2_fpn_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\center_net_mobilenet_v2_fpn_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\center_net_resnet_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\center_net_resnet_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\center_net_resnet_v1_fpn_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\center_net_resnet_v1_fpn_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\embedded_ssd_mobilenet_v1_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\embedded_ssd_mobilenet_v1_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_inception_resnet_v2_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_inception_resnet_v2_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_inception_resnet_v2_keras_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_inception_resnet_v2_keras_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_inception_v2_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_inception_v2_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_mobilenet_v1_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_mobilenet_v1_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_nas_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_nas_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_pnas_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_pnas_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_resnet_keras_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_resnet_keras_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_resnet_v1_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_resnet_v1_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_resnet_v1_fpn_keras_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\faster_rcnn_resnet_v1_fpn_keras_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\feature_map_generators.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\feature_map_generators_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\convert_keras_models.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\hourglass_network.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\hourglass_network_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\inception_resnet_v2.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\inception_resnet_v2_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\mobilenet_v1.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\mobilenet_v1_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\mobilenet_v2.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\mobilenet_v2_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\model_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\nonlocal_block.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\nonlocal_block_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\resnet_v1.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\resnet_v1_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\test_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\keras_models\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\n", + "copying build\\lib\\object_detection\\models\\ssd_efficientnet_bifpn_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_efficientnet_bifpn_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_feature_extractor_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_inception_v2_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_inception_v2_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_inception_v3_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_inception_v3_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobiledet_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobiledet_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_edgetpu_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_edgetpu_feature_extractor_testbase.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_edgetpu_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v1_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v1_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v1_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v1_fpn_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v1_fpn_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v1_fpn_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v1_fpn_keras_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v1_keras_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v1_ppn_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v1_ppn_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v2_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v2_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v2_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v2_fpn_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v2_fpn_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v2_fpn_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v2_fpn_keras_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v2_keras_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v2_mnasfpn_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v2_mnasfpn_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v3_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v3_feature_extractor_testbase.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_mobilenet_v3_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_pnasnet_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_pnasnet_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_resnet_v1_fpn_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_resnet_v1_fpn_feature_extractor_testbase.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_resnet_v1_fpn_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_resnet_v1_fpn_feature_extractor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_resnet_v1_fpn_keras_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_resnet_v1_ppn_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_resnet_v1_ppn_feature_extractor_testbase.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_resnet_v1_ppn_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_spaghettinet_feature_extractor.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\ssd_spaghettinet_feature_extractor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\models\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\models\n", + "copying build\\lib\\object_detection\\model_hparams.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\model_lib.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\model_lib_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\model_lib_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\model_lib_v2.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\model_main.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\model_main_tf2.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "copying build\\lib\\object_detection\\model_tpu_main.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\convolutional_box_predictor.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\convolutional_box_predictor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\convolutional_keras_box_predictor.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\convolutional_keras_box_predictor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\box_head.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\box_head_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\class_head.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\class_head_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\head.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\keras_box_head.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\keras_box_head_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\keras_class_head.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\keras_class_head_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\keras_mask_head.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\keras_mask_head_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\keypoint_head.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\keypoint_head_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\mask_head.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\mask_head_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\heads\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\n", + "copying build\\lib\\object_detection\\predictors\\mask_rcnn_box_predictor.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\mask_rcnn_box_predictor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\mask_rcnn_keras_box_predictor.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\mask_rcnn_keras_box_predictor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\rfcn_box_predictor.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\rfcn_box_predictor_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\rfcn_keras_box_predictor.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\rfcn_keras_box_predictor_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "copying build\\lib\\object_detection\\predictors\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\predictors\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\anchor_generator_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\argmax_matcher_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\bipartite_matcher_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\box_coder_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\box_predictor_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\calibration_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\center_net_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\eval_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\faster_rcnn_box_coder_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\faster_rcnn_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\flexible_grid_anchor_generator_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\fpn_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\graph_rewriter_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\grid_anchor_generator_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\hyperparams_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\image_resizer_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\input_reader_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\keypoint_box_coder_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\losses_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\matcher_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\mean_stddev_box_coder_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\model_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\multiscale_anchor_generator_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\optimizer_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\pipeline_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\post_processing_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\preprocessor_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\region_similarity_calculator_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\square_box_coder_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\ssd_anchor_generator_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\ssd_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\string_int_label_map_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\target_assigner_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\train_pb2.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "copying build\\lib\\object_detection\\protos\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\protos\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\n", + "copying build\\lib\\object_detection\\tpu_exporters\\export_saved_model_tpu.py -> build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\n", + "copying build\\lib\\object_detection\\tpu_exporters\\export_saved_model_tpu_lib.py -> build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\n", + "copying build\\lib\\object_detection\\tpu_exporters\\export_saved_model_tpu_lib_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\n", + "copying build\\lib\\object_detection\\tpu_exporters\\faster_rcnn.py -> build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\n", + "copying build\\lib\\object_detection\\tpu_exporters\\ssd.py -> build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\\testdata\n", + "copying build\\lib\\object_detection\\tpu_exporters\\testdata\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\\testdata\n", + "copying build\\lib\\object_detection\\tpu_exporters\\utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\n", + "copying build\\lib\\object_detection\\tpu_exporters\\utils_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\n", + "copying build\\lib\\object_detection\\tpu_exporters\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\n", + "creating build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\autoaugment_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\bifpn_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\category_util.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\category_util_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\colab_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\config_util.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\config_util_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\context_manager.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\context_manager_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\dataset_util.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\dataset_util_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\json_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\json_utils_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\label_map_util.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\label_map_util_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\learning_schedules.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\learning_schedules_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\metrics.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\metrics_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\model_util.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\model_util_tf2_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_box_list.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_box_list_ops.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_box_list_ops_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_box_list_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_box_mask_list.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_box_mask_list_ops.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_box_mask_list_ops_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_box_mask_list_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_box_ops.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_box_ops_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_mask_ops.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\np_mask_ops_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\object_detection_evaluation.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\object_detection_evaluation_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\ops.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\ops_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\patch_ops.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\patch_ops_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\per_image_evaluation.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\per_image_evaluation_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\per_image_vrd_evaluation.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\per_image_vrd_evaluation_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\shape_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\shape_utils_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\spatial_transform_ops.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\spatial_transform_ops_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\static_shape.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\static_shape_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\target_assigner_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\target_assigner_utils_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\test_case.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\test_case_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\test_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\test_utils_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\tf_version.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\variables_helper.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\variables_helper_tf1_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\visualization_utils.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\visualization_utils_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\vrd_evaluation.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\vrd_evaluation_test.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\utils\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\\utils\n", + "copying build\\lib\\object_detection\\__init__.py -> build\\bdist.win-amd64\\egg\\object_detection\n", + "creating build\\bdist.win-amd64\\egg\\preprocessing\n", + "copying build\\lib\\preprocessing\\cifarnet_preprocessing.py -> build\\bdist.win-amd64\\egg\\preprocessing\n", + "copying build\\lib\\preprocessing\\inception_preprocessing.py -> build\\bdist.win-amd64\\egg\\preprocessing\n", + "copying build\\lib\\preprocessing\\lenet_preprocessing.py -> build\\bdist.win-amd64\\egg\\preprocessing\n", + "copying build\\lib\\preprocessing\\preprocessing_factory.py -> build\\bdist.win-amd64\\egg\\preprocessing\n", + "copying build\\lib\\preprocessing\\vgg_preprocessing.py -> build\\bdist.win-amd64\\egg\\preprocessing\n", + "copying build\\lib\\preprocessing\\__init__.py -> build\\bdist.win-amd64\\egg\\preprocessing\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\build_imagenet_data.py to build_imagenet_data.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\cifar10.py to cifar10.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\dataset_factory.py to dataset_factory.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\dataset_utils.py to dataset_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\download_and_convert_cifar10.py to download_and_convert_cifar10.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\download_and_convert_flowers.py to download_and_convert_flowers.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\download_and_convert_mnist.py to download_and_convert_mnist.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\download_and_convert_visualwakewords.py to download_and_convert_visualwakewords.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\download_and_convert_visualwakewords_lib.py to download_and_convert_visualwakewords_lib.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\flowers.py to flowers.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\imagenet.py to imagenet.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\mnist.py to mnist.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\preprocess_imagenet_validation_data.py to preprocess_imagenet_validation_data.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\process_bounding_boxes.py to process_bounding_boxes.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\visualwakewords.py to visualwakewords.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\datasets\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\deployment\\model_deploy.py to model_deploy.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\deployment\\model_deploy_test.py to model_deploy_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\deployment\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\alexnet.py to alexnet.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\alexnet_test.py to alexnet_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\cifarnet.py to cifarnet.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\cyclegan.py to cyclegan.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\cyclegan_test.py to cyclegan_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\dcgan.py to dcgan.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\dcgan_test.py to dcgan_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\i3d.py to i3d.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\i3d_test.py to i3d_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\i3d_utils.py to i3d_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception.py to inception.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception_resnet_v2.py to inception_resnet_v2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception_resnet_v2_test.py to inception_resnet_v2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception_utils.py to inception_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception_v1.py to inception_v1.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception_v1_test.py to inception_v1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception_v2.py to inception_v2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception_v2_test.py to inception_v2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception_v3.py to inception_v3.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception_v3_test.py to inception_v3_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception_v4.py to inception_v4.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\inception_v4_test.py to inception_v4_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\lenet.py to lenet.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\mobilenet\\conv_blocks.py to conv_blocks.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\mobilenet\\mobilenet.py to mobilenet.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\mobilenet\\mobilenet_v2.py to mobilenet_v2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\mobilenet\\mobilenet_v2_test.py to mobilenet_v2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\mobilenet\\mobilenet_v3.py to mobilenet_v3.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\mobilenet\\mobilenet_v3_test.py to mobilenet_v3_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\mobilenet\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\mobilenet_v1.py to mobilenet_v1.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\mobilenet_v1_eval.py to mobilenet_v1_eval.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\mobilenet_v1_test.py to mobilenet_v1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\mobilenet_v1_train.py to mobilenet_v1_train.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\nasnet\\nasnet.py to nasnet.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\nasnet\\nasnet_test.py to nasnet_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\nasnet\\nasnet_utils.py to nasnet_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\nasnet\\nasnet_utils_test.py to nasnet_utils_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\nasnet\\pnasnet.py to pnasnet.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\nasnet\\pnasnet_test.py to pnasnet_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\nasnet\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\nets_factory.py to nets_factory.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\nets_factory_test.py to nets_factory_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\overfeat.py to overfeat.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\overfeat_test.py to overfeat_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\pix2pix.py to pix2pix.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\pix2pix_test.py to pix2pix_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\post_training_quantization.py to post_training_quantization.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\resnet_utils.py to resnet_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\resnet_v1.py to resnet_v1.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\resnet_v1_test.py to resnet_v1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\resnet_v2.py to resnet_v2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\resnet_v2_test.py to resnet_v2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\s3dg.py to s3dg.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\s3dg_test.py to s3dg_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\vgg.py to vgg.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\vgg_test.py to vgg_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\nets\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\\flexible_grid_anchor_generator.py to flexible_grid_anchor_generator.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\\flexible_grid_anchor_generator_test.py to flexible_grid_anchor_generator_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\\grid_anchor_generator.py to grid_anchor_generator.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\\grid_anchor_generator_test.py to grid_anchor_generator_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\\multiple_grid_anchor_generator.py to multiple_grid_anchor_generator.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\\multiple_grid_anchor_generator_test.py to multiple_grid_anchor_generator_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\\multiscale_grid_anchor_generator.py to multiscale_grid_anchor_generator.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\\multiscale_grid_anchor_generator_test.py to multiscale_grid_anchor_generator_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\anchor_generators\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\box_coders\\faster_rcnn_box_coder.py to faster_rcnn_box_coder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\box_coders\\faster_rcnn_box_coder_test.py to faster_rcnn_box_coder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\box_coders\\keypoint_box_coder.py to keypoint_box_coder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\box_coders\\keypoint_box_coder_test.py to keypoint_box_coder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\box_coders\\mean_stddev_box_coder.py to mean_stddev_box_coder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\box_coders\\mean_stddev_box_coder_test.py to mean_stddev_box_coder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\box_coders\\square_box_coder.py to square_box_coder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\box_coders\\square_box_coder_test.py to square_box_coder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\box_coders\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\anchor_generator_builder.py to anchor_generator_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\anchor_generator_builder_test.py to anchor_generator_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\box_coder_builder.py to box_coder_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\box_coder_builder_test.py to box_coder_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\box_predictor_builder.py to box_predictor_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\box_predictor_builder_test.py to box_predictor_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\calibration_builder.py to calibration_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\calibration_builder_test.py to calibration_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\dataset_builder.py to dataset_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\dataset_builder_test.py to dataset_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\decoder_builder.py to decoder_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\decoder_builder_test.py to decoder_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\graph_rewriter_builder.py to graph_rewriter_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\graph_rewriter_builder_tf1_test.py to graph_rewriter_builder_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\hyperparams_builder.py to hyperparams_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\hyperparams_builder_test.py to hyperparams_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\image_resizer_builder.py to image_resizer_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\image_resizer_builder_test.py to image_resizer_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\input_reader_builder.py to input_reader_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\input_reader_builder_tf1_test.py to input_reader_builder_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\losses_builder.py to losses_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\losses_builder_test.py to losses_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\matcher_builder.py to matcher_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\matcher_builder_test.py to matcher_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\model_builder.py to model_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\model_builder_test.py to model_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\model_builder_tf1_test.py to model_builder_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\model_builder_tf2_test.py to model_builder_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\optimizer_builder.py to optimizer_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\optimizer_builder_tf1_test.py to optimizer_builder_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\optimizer_builder_tf2_test.py to optimizer_builder_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\post_processing_builder.py to post_processing_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\post_processing_builder_test.py to post_processing_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\preprocessor_builder.py to preprocessor_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\preprocessor_builder_test.py to preprocessor_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\region_similarity_calculator_builder.py to region_similarity_calculator_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\region_similarity_calculator_builder_test.py to region_similarity_calculator_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\target_assigner_builder.py to target_assigner_builder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\target_assigner_builder_test.py to target_assigner_builder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\builders\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\anchor_generator.py to anchor_generator.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\balanced_positive_negative_sampler.py to balanced_positive_negative_sampler.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\balanced_positive_negative_sampler_test.py to balanced_positive_negative_sampler_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\batcher.py to batcher.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\batcher_tf1_test.py to batcher_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\batch_multiclass_nms_test.py to batch_multiclass_nms_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\box_coder.py to box_coder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\box_coder_test.py to box_coder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\box_list.py to box_list.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\box_list_ops.py to box_list_ops.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\box_list_ops_test.py to box_list_ops_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\box_list_test.py to box_list_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\box_predictor.py to box_predictor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\class_agnostic_nms_test.py to class_agnostic_nms_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\data_decoder.py to data_decoder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\data_parser.py to data_parser.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\densepose_ops.py to densepose_ops.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\densepose_ops_test.py to densepose_ops_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\freezable_batch_norm.py to freezable_batch_norm.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\freezable_batch_norm_tf2_test.py to freezable_batch_norm_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\freezable_sync_batch_norm.py to freezable_sync_batch_norm.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\keypoint_ops.py to keypoint_ops.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\keypoint_ops_test.py to keypoint_ops_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\losses.py to losses.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\losses_test.py to losses_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\matcher.py to matcher.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\matcher_test.py to matcher_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\minibatch_sampler.py to minibatch_sampler.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\minibatch_sampler_test.py to minibatch_sampler_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\model.py to model.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\model_test.py to model_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\multiclass_nms_test.py to multiclass_nms_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\post_processing.py to post_processing.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\prefetcher.py to prefetcher.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\prefetcher_tf1_test.py to prefetcher_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\preprocessor.py to preprocessor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\preprocessor_cache.py to preprocessor_cache.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\preprocessor_test.py to preprocessor_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\region_similarity_calculator.py to region_similarity_calculator.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\region_similarity_calculator_test.py to region_similarity_calculator_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\standard_fields.py to standard_fields.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\target_assigner.py to target_assigner.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\target_assigner_test.py to target_assigner_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\core\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\\add_context_to_examples.py to add_context_to_examples.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\\add_context_to_examples_tf2_test.py to add_context_to_examples_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\\create_cococameratraps_tfexample_main.py to create_cococameratraps_tfexample_main.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\\create_cococameratraps_tfexample_tf2_test.py to create_cococameratraps_tfexample_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\\generate_detection_data.py to generate_detection_data.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\\generate_detection_data_tf2_test.py to generate_detection_data_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\\generate_embedding_data.py to generate_embedding_data.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\\generate_embedding_data_tf2_test.py to generate_embedding_data_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\context_rcnn\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\create_ava_actions_tf_record.py to create_ava_actions_tf_record.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\create_coco_tf_record.py to create_coco_tf_record.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\create_coco_tf_record_test.py to create_coco_tf_record_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\create_kitti_tf_record.py to create_kitti_tf_record.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\create_kitti_tf_record_test.py to create_kitti_tf_record_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\create_oid_tf_record.py to create_oid_tf_record.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\create_pascal_tf_record.py to create_pascal_tf_record.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\create_pascal_tf_record_test.py to create_pascal_tf_record_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\create_pet_tf_record.py to create_pet_tf_record.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\oid_hierarchical_labels_expansion.py to oid_hierarchical_labels_expansion.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\oid_hierarchical_labels_expansion_test.py to oid_hierarchical_labels_expansion_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\oid_tfrecord_creation.py to oid_tfrecord_creation.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\oid_tfrecord_creation_test.py to oid_tfrecord_creation_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\seq_example_util.py to seq_example_util.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\seq_example_util_test.py to seq_example_util_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\tf_record_creation_util.py to tf_record_creation_util.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\tf_record_creation_util_test.py to tf_record_creation_util_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\dataset_tools\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\data_decoders\\tf_example_decoder.py to tf_example_decoder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\data_decoders\\tf_example_decoder_test.py to tf_example_decoder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\data_decoders\\tf_sequence_example_decoder.py to tf_sequence_example_decoder.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\data_decoders\\tf_sequence_example_decoder_test.py to tf_sequence_example_decoder_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\data_decoders\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\eval_util.py to eval_util.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\eval_util_test.py to eval_util_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\exporter.py to exporter.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\exporter_lib_tf2_test.py to exporter_lib_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\exporter_lib_v2.py to exporter_lib_v2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\exporter_main_v2.py to exporter_main_v2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\exporter_tf1_test.py to exporter_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\export_inference_graph.py to export_inference_graph.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\export_tflite_graph_lib_tf2.py to export_tflite_graph_lib_tf2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\export_tflite_graph_lib_tf2_test.py to export_tflite_graph_lib_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\export_tflite_graph_tf2.py to export_tflite_graph_tf2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\export_tflite_ssd_graph.py to export_tflite_ssd_graph.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\export_tflite_ssd_graph_lib.py to export_tflite_ssd_graph_lib.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\export_tflite_ssd_graph_lib_tf1_test.py to export_tflite_ssd_graph_lib_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\inference\\detection_inference.py to detection_inference.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\inference\\detection_inference_tf1_test.py to detection_inference_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\inference\\infer_detections.py to infer_detections.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\inference\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\inputs.py to inputs.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\inputs_test.py to inputs_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\legacy\\eval.py to eval.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\legacy\\evaluator.py to evaluator.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\legacy\\train.py to train.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\legacy\\trainer.py to trainer.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\legacy\\trainer_tf1_test.py to trainer_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\legacy\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\matchers\\argmax_matcher.py to argmax_matcher.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\matchers\\argmax_matcher_test.py to argmax_matcher_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\matchers\\bipartite_matcher.py to bipartite_matcher.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\matchers\\bipartite_matcher_tf1_test.py to bipartite_matcher_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\matchers\\hungarian_matcher.py to hungarian_matcher.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\matchers\\hungarian_matcher_tf2_test.py to hungarian_matcher_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\matchers\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\center_net_meta_arch.py to center_net_meta_arch.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\center_net_meta_arch_tf2_test.py to center_net_meta_arch_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\context_rcnn_lib.py to context_rcnn_lib.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\context_rcnn_lib_tf1_test.py to context_rcnn_lib_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\context_rcnn_lib_tf2.py to context_rcnn_lib_tf2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\context_rcnn_lib_tf2_test.py to context_rcnn_lib_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\context_rcnn_meta_arch.py to context_rcnn_meta_arch.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\context_rcnn_meta_arch_test.py to context_rcnn_meta_arch_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\deepmac_meta_arch.py to deepmac_meta_arch.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\deepmac_meta_arch_test.py to deepmac_meta_arch_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\faster_rcnn_meta_arch.py to faster_rcnn_meta_arch.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\faster_rcnn_meta_arch_test.py to faster_rcnn_meta_arch_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\faster_rcnn_meta_arch_test_lib.py to faster_rcnn_meta_arch_test_lib.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\rfcn_meta_arch.py to rfcn_meta_arch.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\rfcn_meta_arch_test.py to rfcn_meta_arch_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\ssd_meta_arch.py to ssd_meta_arch.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\ssd_meta_arch_test.py to ssd_meta_arch_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\ssd_meta_arch_test_lib.py to ssd_meta_arch_test_lib.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\meta_architectures\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\calibration_evaluation.py to calibration_evaluation.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\calibration_evaluation_tf1_test.py to calibration_evaluation_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\calibration_metrics.py to calibration_metrics.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\calibration_metrics_tf1_test.py to calibration_metrics_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\coco_evaluation.py to coco_evaluation.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\coco_evaluation_test.py to coco_evaluation_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\coco_tools.py to coco_tools.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\coco_tools_test.py to coco_tools_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\io_utils.py to io_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\lvis_evaluation.py to lvis_evaluation.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\lvis_evaluation_test.py to lvis_evaluation_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\lvis_tools.py to lvis_tools.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\lvis_tools_test.py to lvis_tools_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\offline_eval_map_corloc.py to offline_eval_map_corloc.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\offline_eval_map_corloc_test.py to offline_eval_map_corloc_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\oid_challenge_evaluation.py to oid_challenge_evaluation.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\oid_challenge_evaluation_utils.py to oid_challenge_evaluation_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\oid_challenge_evaluation_utils_test.py to oid_challenge_evaluation_utils_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\oid_vrd_challenge_evaluation.py to oid_vrd_challenge_evaluation.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\oid_vrd_challenge_evaluation_utils.py to oid_vrd_challenge_evaluation_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\oid_vrd_challenge_evaluation_utils_test.py to oid_vrd_challenge_evaluation_utils_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\tf_example_parser.py to tf_example_parser.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\tf_example_parser_test.py to tf_example_parser_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\metrics\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\bidirectional_feature_pyramid_generators.py to bidirectional_feature_pyramid_generators.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\bidirectional_feature_pyramid_generators_tf2_test.py to bidirectional_feature_pyramid_generators_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\center_net_hourglass_feature_extractor.py to center_net_hourglass_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\center_net_hourglass_feature_extractor_tf2_test.py to center_net_hourglass_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\center_net_mobilenet_v2_feature_extractor.py to center_net_mobilenet_v2_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\center_net_mobilenet_v2_feature_extractor_tf2_test.py to center_net_mobilenet_v2_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\center_net_mobilenet_v2_fpn_feature_extractor.py to center_net_mobilenet_v2_fpn_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\center_net_mobilenet_v2_fpn_feature_extractor_tf2_test.py to center_net_mobilenet_v2_fpn_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\center_net_resnet_feature_extractor.py to center_net_resnet_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\center_net_resnet_feature_extractor_tf2_test.py to center_net_resnet_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\center_net_resnet_v1_fpn_feature_extractor.py to center_net_resnet_v1_fpn_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\center_net_resnet_v1_fpn_feature_extractor_tf2_test.py to center_net_resnet_v1_fpn_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\embedded_ssd_mobilenet_v1_feature_extractor.py to embedded_ssd_mobilenet_v1_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\embedded_ssd_mobilenet_v1_feature_extractor_tf1_test.py to embedded_ssd_mobilenet_v1_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_inception_resnet_v2_feature_extractor.py to faster_rcnn_inception_resnet_v2_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_inception_resnet_v2_feature_extractor_tf1_test.py to faster_rcnn_inception_resnet_v2_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_inception_resnet_v2_keras_feature_extractor.py to faster_rcnn_inception_resnet_v2_keras_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_inception_resnet_v2_keras_feature_extractor_tf2_test.py to faster_rcnn_inception_resnet_v2_keras_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_inception_v2_feature_extractor.py to faster_rcnn_inception_v2_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_inception_v2_feature_extractor_tf1_test.py to faster_rcnn_inception_v2_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_mobilenet_v1_feature_extractor.py to faster_rcnn_mobilenet_v1_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_mobilenet_v1_feature_extractor_tf1_test.py to faster_rcnn_mobilenet_v1_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_nas_feature_extractor.py to faster_rcnn_nas_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_nas_feature_extractor_tf1_test.py to faster_rcnn_nas_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_pnas_feature_extractor.py to faster_rcnn_pnas_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_pnas_feature_extractor_tf1_test.py to faster_rcnn_pnas_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_resnet_keras_feature_extractor.py to faster_rcnn_resnet_keras_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_resnet_keras_feature_extractor_tf2_test.py to faster_rcnn_resnet_keras_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_resnet_v1_feature_extractor.py to faster_rcnn_resnet_v1_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_resnet_v1_feature_extractor_tf1_test.py to faster_rcnn_resnet_v1_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_resnet_v1_fpn_keras_feature_extractor.py to faster_rcnn_resnet_v1_fpn_keras_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\faster_rcnn_resnet_v1_fpn_keras_feature_extractor_tf2_test.py to faster_rcnn_resnet_v1_fpn_keras_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\feature_map_generators.py to feature_map_generators.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\feature_map_generators_test.py to feature_map_generators_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\convert_keras_models.py to convert_keras_models.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\hourglass_network.py to hourglass_network.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\hourglass_network_tf2_test.py to hourglass_network_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\inception_resnet_v2.py to inception_resnet_v2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\inception_resnet_v2_tf2_test.py to inception_resnet_v2_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\mobilenet_v1.py to mobilenet_v1.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\mobilenet_v1_tf2_test.py to mobilenet_v1_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\mobilenet_v2.py to mobilenet_v2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\mobilenet_v2_tf2_test.py to mobilenet_v2_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\model_utils.py to model_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\nonlocal_block.py to nonlocal_block.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\nonlocal_block_tf2_test.py to nonlocal_block_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\resnet_v1.py to resnet_v1.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\resnet_v1_tf2_test.py to resnet_v1_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\test_utils.py to test_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\keras_models\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_efficientnet_bifpn_feature_extractor.py to ssd_efficientnet_bifpn_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_efficientnet_bifpn_feature_extractor_tf2_test.py to ssd_efficientnet_bifpn_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_feature_extractor_test.py to ssd_feature_extractor_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_inception_v2_feature_extractor.py to ssd_inception_v2_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_inception_v2_feature_extractor_tf1_test.py to ssd_inception_v2_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_inception_v3_feature_extractor.py to ssd_inception_v3_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_inception_v3_feature_extractor_tf1_test.py to ssd_inception_v3_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobiledet_feature_extractor.py to ssd_mobiledet_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobiledet_feature_extractor_tf1_test.py to ssd_mobiledet_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_edgetpu_feature_extractor.py to ssd_mobilenet_edgetpu_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_edgetpu_feature_extractor_testbase.py to ssd_mobilenet_edgetpu_feature_extractor_testbase.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_edgetpu_feature_extractor_tf1_test.py to ssd_mobilenet_edgetpu_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v1_feature_extractor.py to ssd_mobilenet_v1_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v1_feature_extractor_tf1_test.py to ssd_mobilenet_v1_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v1_feature_extractor_tf2_test.py to ssd_mobilenet_v1_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v1_fpn_feature_extractor.py to ssd_mobilenet_v1_fpn_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v1_fpn_feature_extractor_tf1_test.py to ssd_mobilenet_v1_fpn_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v1_fpn_feature_extractor_tf2_test.py to ssd_mobilenet_v1_fpn_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v1_fpn_keras_feature_extractor.py to ssd_mobilenet_v1_fpn_keras_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v1_keras_feature_extractor.py to ssd_mobilenet_v1_keras_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v1_ppn_feature_extractor.py to ssd_mobilenet_v1_ppn_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v1_ppn_feature_extractor_tf1_test.py to ssd_mobilenet_v1_ppn_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v2_feature_extractor.py to ssd_mobilenet_v2_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v2_feature_extractor_tf1_test.py to ssd_mobilenet_v2_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v2_feature_extractor_tf2_test.py to ssd_mobilenet_v2_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v2_fpn_feature_extractor.py to ssd_mobilenet_v2_fpn_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v2_fpn_feature_extractor_tf1_test.py to ssd_mobilenet_v2_fpn_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v2_fpn_feature_extractor_tf2_test.py to ssd_mobilenet_v2_fpn_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v2_fpn_keras_feature_extractor.py to ssd_mobilenet_v2_fpn_keras_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v2_keras_feature_extractor.py to ssd_mobilenet_v2_keras_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v2_mnasfpn_feature_extractor.py to ssd_mobilenet_v2_mnasfpn_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v2_mnasfpn_feature_extractor_tf1_test.py to ssd_mobilenet_v2_mnasfpn_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v3_feature_extractor.py to ssd_mobilenet_v3_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v3_feature_extractor_testbase.py to ssd_mobilenet_v3_feature_extractor_testbase.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_mobilenet_v3_feature_extractor_tf1_test.py to ssd_mobilenet_v3_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_pnasnet_feature_extractor.py to ssd_pnasnet_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_pnasnet_feature_extractor_tf1_test.py to ssd_pnasnet_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_resnet_v1_fpn_feature_extractor.py to ssd_resnet_v1_fpn_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_resnet_v1_fpn_feature_extractor_testbase.py to ssd_resnet_v1_fpn_feature_extractor_testbase.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_resnet_v1_fpn_feature_extractor_tf1_test.py to ssd_resnet_v1_fpn_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_resnet_v1_fpn_feature_extractor_tf2_test.py to ssd_resnet_v1_fpn_feature_extractor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_resnet_v1_fpn_keras_feature_extractor.py to ssd_resnet_v1_fpn_keras_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_resnet_v1_ppn_feature_extractor.py to ssd_resnet_v1_ppn_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_resnet_v1_ppn_feature_extractor_testbase.py to ssd_resnet_v1_ppn_feature_extractor_testbase.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_resnet_v1_ppn_feature_extractor_tf1_test.py to ssd_resnet_v1_ppn_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_spaghettinet_feature_extractor.py to ssd_spaghettinet_feature_extractor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\ssd_spaghettinet_feature_extractor_tf1_test.py to ssd_spaghettinet_feature_extractor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\models\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\model_hparams.py to model_hparams.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\model_lib.py to model_lib.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\model_lib_tf1_test.py to model_lib_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\model_lib_tf2_test.py to model_lib_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\model_lib_v2.py to model_lib_v2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\model_main.py to model_main.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\model_main_tf2.py to model_main_tf2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\model_tpu_main.py to model_tpu_main.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\convolutional_box_predictor.py to convolutional_box_predictor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\convolutional_box_predictor_tf1_test.py to convolutional_box_predictor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\convolutional_keras_box_predictor.py to convolutional_keras_box_predictor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\convolutional_keras_box_predictor_tf2_test.py to convolutional_keras_box_predictor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\box_head.py to box_head.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\box_head_tf1_test.py to box_head_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\class_head.py to class_head.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\class_head_tf1_test.py to class_head_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\head.py to head.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\keras_box_head.py to keras_box_head.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\keras_box_head_tf2_test.py to keras_box_head_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\keras_class_head.py to keras_class_head.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\keras_class_head_tf2_test.py to keras_class_head_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\keras_mask_head.py to keras_mask_head.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\keras_mask_head_tf2_test.py to keras_mask_head_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\keypoint_head.py to keypoint_head.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\keypoint_head_tf1_test.py to keypoint_head_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\mask_head.py to mask_head.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\mask_head_tf1_test.py to mask_head_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\heads\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\mask_rcnn_box_predictor.py to mask_rcnn_box_predictor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\mask_rcnn_box_predictor_tf1_test.py to mask_rcnn_box_predictor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\mask_rcnn_keras_box_predictor.py to mask_rcnn_keras_box_predictor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\mask_rcnn_keras_box_predictor_tf2_test.py to mask_rcnn_keras_box_predictor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\rfcn_box_predictor.py to rfcn_box_predictor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\rfcn_box_predictor_tf1_test.py to rfcn_box_predictor_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\rfcn_keras_box_predictor.py to rfcn_keras_box_predictor.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\rfcn_keras_box_predictor_tf2_test.py to rfcn_keras_box_predictor_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\predictors\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\anchor_generator_pb2.py to anchor_generator_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\argmax_matcher_pb2.py to argmax_matcher_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\bipartite_matcher_pb2.py to bipartite_matcher_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\box_coder_pb2.py to box_coder_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\box_predictor_pb2.py to box_predictor_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\calibration_pb2.py to calibration_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\center_net_pb2.py to center_net_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\eval_pb2.py to eval_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\faster_rcnn_box_coder_pb2.py to faster_rcnn_box_coder_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\faster_rcnn_pb2.py to faster_rcnn_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\flexible_grid_anchor_generator_pb2.py to flexible_grid_anchor_generator_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\fpn_pb2.py to fpn_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\graph_rewriter_pb2.py to graph_rewriter_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\grid_anchor_generator_pb2.py to grid_anchor_generator_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\hyperparams_pb2.py to hyperparams_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\image_resizer_pb2.py to image_resizer_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\input_reader_pb2.py to input_reader_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\keypoint_box_coder_pb2.py to keypoint_box_coder_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\losses_pb2.py to losses_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\matcher_pb2.py to matcher_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\mean_stddev_box_coder_pb2.py to mean_stddev_box_coder_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\model_pb2.py to model_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\multiscale_anchor_generator_pb2.py to multiscale_anchor_generator_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\optimizer_pb2.py to optimizer_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\pipeline_pb2.py to pipeline_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\post_processing_pb2.py to post_processing_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\preprocessor_pb2.py to preprocessor_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\region_similarity_calculator_pb2.py to region_similarity_calculator_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\square_box_coder_pb2.py to square_box_coder_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\ssd_anchor_generator_pb2.py to ssd_anchor_generator_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\ssd_pb2.py to ssd_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\string_int_label_map_pb2.py to string_int_label_map_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\target_assigner_pb2.py to target_assigner_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\train_pb2.py to train_pb2.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\protos\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\\export_saved_model_tpu.py to export_saved_model_tpu.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\\export_saved_model_tpu_lib.py to export_saved_model_tpu_lib.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\\export_saved_model_tpu_lib_tf1_test.py to export_saved_model_tpu_lib_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\\faster_rcnn.py to faster_rcnn.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\\ssd.py to ssd.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\\testdata\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\\utils.py to utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\\utils_test.py to utils_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\tpu_exporters\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\autoaugment_utils.py to autoaugment_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\bifpn_utils.py to bifpn_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\category_util.py to category_util.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\category_util_test.py to category_util_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\colab_utils.py to colab_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\config_util.py to config_util.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\config_util_test.py to config_util_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\context_manager.py to context_manager.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\context_manager_test.py to context_manager_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\dataset_util.py to dataset_util.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\dataset_util_test.py to dataset_util_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\json_utils.py to json_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\json_utils_test.py to json_utils_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\label_map_util.py to label_map_util.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\label_map_util_test.py to label_map_util_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\learning_schedules.py to learning_schedules.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\learning_schedules_test.py to learning_schedules_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\metrics.py to metrics.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\metrics_test.py to metrics_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\model_util.py to model_util.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\model_util_tf2_test.py to model_util_tf2_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_box_list.py to np_box_list.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_box_list_ops.py to np_box_list_ops.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_box_list_ops_test.py to np_box_list_ops_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_box_list_test.py to np_box_list_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_box_mask_list.py to np_box_mask_list.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_box_mask_list_ops.py to np_box_mask_list_ops.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_box_mask_list_ops_test.py to np_box_mask_list_ops_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_box_mask_list_test.py to np_box_mask_list_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_box_ops.py to np_box_ops.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_box_ops_test.py to np_box_ops_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_mask_ops.py to np_mask_ops.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\np_mask_ops_test.py to np_mask_ops_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\object_detection_evaluation.py to object_detection_evaluation.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\object_detection_evaluation_test.py to object_detection_evaluation_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\ops.py to ops.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\ops_test.py to ops_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\patch_ops.py to patch_ops.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\patch_ops_test.py to patch_ops_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\per_image_evaluation.py to per_image_evaluation.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\per_image_evaluation_test.py to per_image_evaluation_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\per_image_vrd_evaluation.py to per_image_vrd_evaluation.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\per_image_vrd_evaluation_test.py to per_image_vrd_evaluation_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\shape_utils.py to shape_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\shape_utils_test.py to shape_utils_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\spatial_transform_ops.py to spatial_transform_ops.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\spatial_transform_ops_test.py to spatial_transform_ops_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\static_shape.py to static_shape.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\static_shape_test.py to static_shape_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\target_assigner_utils.py to target_assigner_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\target_assigner_utils_test.py to target_assigner_utils_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\test_case.py to test_case.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\test_case_test.py to test_case_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\test_utils.py to test_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\test_utils_test.py to test_utils_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\tf_version.py to tf_version.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\variables_helper.py to variables_helper.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\variables_helper_tf1_test.py to variables_helper_tf1_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\visualization_utils.py to visualization_utils.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\visualization_utils_test.py to visualization_utils_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\vrd_evaluation.py to vrd_evaluation.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\vrd_evaluation_test.py to vrd_evaluation_test.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\utils\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\object_detection\\__init__.py to __init__.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\preprocessing\\cifarnet_preprocessing.py to cifarnet_preprocessing.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\preprocessing\\inception_preprocessing.py to inception_preprocessing.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\preprocessing\\lenet_preprocessing.py to lenet_preprocessing.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\preprocessing\\preprocessing_factory.py to preprocessing_factory.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\preprocessing\\vgg_preprocessing.py to vgg_preprocessing.cpython-39.pyc\n", + "byte-compiling build\\bdist.win-amd64\\egg\\preprocessing\\__init__.py to __init__.cpython-39.pyc\n", + "creating build\\bdist.win-amd64\\egg\\EGG-INFO\n", + "copying object_detection.egg-info\\PKG-INFO -> build\\bdist.win-amd64\\egg\\EGG-INFO\n", + "copying object_detection.egg-info\\SOURCES.txt -> build\\bdist.win-amd64\\egg\\EGG-INFO\n", + "copying object_detection.egg-info\\dependency_links.txt -> build\\bdist.win-amd64\\egg\\EGG-INFO\n", + "copying object_detection.egg-info\\requires.txt -> build\\bdist.win-amd64\\egg\\EGG-INFO\n", + "copying object_detection.egg-info\\top_level.txt -> build\\bdist.win-amd64\\egg\\EGG-INFO\n", + "creating 'dist\\object_detection-0.1-py3.9.egg' and adding 'build\\bdist.win-amd64\\egg' to it\n", + "removing 'build\\bdist.win-amd64\\egg' (and everything under it)\n", + "Processing object_detection-0.1-py3.9.egg\n", + "removing 'c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg' (and everything under it)\n", + "creating c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\n", + "Extracting object_detection-0.1-py3.9.egg to c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages\n", + "object-detection 0.1 is already the active version in easy-install.pth\n", + "\n", + "Installed c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\n", + "Processing dependencies for object-detection==0.1\n", + "Searching for tensorflow-text~=2.11.0\n", + "Reading https://pypi.org/simple/tensorflow-text/\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "zip_safe flag not set; analyzing archive contents...\n", + "object_detection.core.__pycache__.densepose_ops.cpython-39: module references __file__\n", + "object_detection.core.__pycache__.preprocessor.cpython-39: module MAY be using inspect.stack\n", + "object_detection.utils.__pycache__.autoaugment_utils.cpython-39: module MAY be using inspect.stack\n", + "No local packages or working download links found for tensorflow-text~=2.11.0\n", + "error: Could not find suitable distribution for Requirement.parse('tensorflow-text~=2.11.0')\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Obtaining file:///C:/Users/SAURAV/TFODCourse/Tensorflow/models/research/slim\n", + " Preparing metadata (setup.py): started\n", + " Preparing metadata (setup.py): finished with status 'done'\n", + "Requirement already satisfied: six in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from slim==0.1) (1.16.0)\n", + "Requirement already satisfied: tf-slim>=1.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from slim==0.1) (1.1.0)\n", + "Requirement already satisfied: absl-py>=0.2.2 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tf-slim>=1.1->slim==0.1) (1.4.0)\n", + "Installing collected packages: slim\n", + " Attempting uninstall: slim\n", + " Found existing installation: slim 0.1\n", + " Uninstalling slim-0.1:\n", + " Successfully uninstalled slim-0.1\n", + " Running setup.py develop for slim\n", + "Successfully installed slim-0.1\n" + ] + } + ], + "source": [ + "# Install Tensorflow Object Detection \n", + "if os.name=='posix': \n", + " !apt-get install protobuf-compiler\n", + " !cd Tensorflow/models/research && protoc object_detection/protos/*.proto --python_out=. && cp object_detection/packages/tf2/setup.py . && python -m pip install . \n", + " \n", + "if os.name=='nt':\n", + " url=\"https://github.com/protocolbuffers/protobuf/releases/download/v3.15.6/protoc-3.15.6-win64.zip\"\n", + " wget.download(url)\n", + " !move protoc-3.15.6-win64.zip {paths['PROTOC_PATH']}\n", + " !cd {paths['PROTOC_PATH']} && tar -xf protoc-3.15.6-win64.zip\n", + " os.environ['PATH'] += os.pathsep + os.path.abspath(os.path.join(paths['PROTOC_PATH'], 'bin')) \n", + " !cd Tensorflow/models/research && protoc object_detection/protos/*.proto --python_out=. && copy object_detection\\\\packages\\\\tf2\\\\setup.py setup.py && python setup.py build && python setup.py install\n", + " !cd Tensorflow/models/research/slim && pip install -e . " + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Package Version Editable project location\n", + "---------------------------- ------------ ----------------------------------------------------------\n", + "absl-py 1.4.0\n", + "apache-beam 2.46.0\n", + "asttokens 2.2.1\n", + "astunparse 1.6.3\n", + "avro-python3 1.10.2\n", + "backcall 0.2.0\n", + "cachetools 5.3.0\n", + "certifi 2022.12.7\n", + "charset-normalizer 3.1.0\n", + "colorama 0.4.6\n", + "comm 0.1.2\n", + "contextlib2 21.6.0\n", + "contourpy 1.0.7\n", + "cycler 0.11.0\n", + "Cython 3.0.0b2\n", + "debugpy 1.6.6\n", + "decorator 5.1.1\n", + "easyocr 1.6.2\n", + "executing 1.2.0\n", + "filelock 3.9.0\n", + "flatbuffers 23.3.3\n", + "fonttools 4.39.2\n", + "gast 0.4.0\n", + "gin-config 0.5.0\n", + "google-auth 2.16.2\n", + "google-auth-oauthlib 1.0.0\n", + "google-pasta 0.2.0\n", + "grpcio 1.51.3\n", + "h5py 3.8.0\n", + "idna 3.4\n", + "imageio 2.27.0\n", + "importlib-metadata 6.0.0\n", + "importlib-resources 5.12.0\n", + "ipykernel 6.21.3\n", + "ipython 8.11.0\n", + "jax 0.4.8\n", + "jedi 0.18.2\n", + "Jinja2 3.1.2\n", + "jupyter_client 8.0.3\n", + "jupyter_core 5.3.0\n", + "keras 2.12.0\n", + "kiwisolver 1.4.4\n", + "lazy_loader 0.2\n", + "libclang 15.0.6.1\n", + "lvis 0.5.3\n", + "lxml 4.9.2\n", + "Markdown 3.4.1\n", + "MarkupSafe 2.1.2\n", + "matplotlib 3.7.1\n", + "matplotlib-inline 0.1.6\n", + "ml-dtypes 0.0.4\n", + "mpmath 1.3.0\n", + "nest-asyncio 1.5.6\n", + "networkx 3.0\n", + "ninja 1.11.1\n", + "numpy 1.23.5\n", + "oauthlib 3.2.2\n", + "object-detection 0.1\n", + "opencv-contrib-python 4.7.0.72\n", + "opencv-python 4.7.0.72\n", + "opencv-python-headless 4.5.4.60\n", + "opt-einsum 3.3.0\n", + "packaging 23.0\n", + "pandas 2.0.0rc1\n", + "parso 0.8.3\n", + "pickleshare 0.7.5\n", + "Pillow 9.4.0\n", + "pip 23.1.2\n", + "platformdirs 3.1.1\n", + "portalocker 2.7.0\n", + "prompt-toolkit 3.0.38\n", + "protobuf 3.20.1\n", + "psutil 5.9.4\n", + "pure-eval 0.2.2\n", + "pyasn1 0.4.8\n", + "pyasn1-modules 0.2.8\n", + "pyclipper 1.3.0.post4\n", + "pycocotools 2.0.6\n", + "Pygments 2.14.0\n", + "pyparsing 2.4.7\n", + "PyQt5 5.15.9\n", + "PyQt5-Qt5 5.15.2\n", + "PyQt5-sip 12.11.1\n", + "python-bidi 0.4.2\n", + "python-dateutil 2.8.2\n", + "pytz 2023.3\n", + "PyWavelets 1.4.1\n", + "pywin32 305\n", + "PyYAML 5.1\n", + "pyzmq 25.0.1\n", + "regex 2023.3.23\n", + "requests 2.28.2\n", + "requests-oauthlib 1.3.1\n", + "rsa 4.9\n", + "sacrebleu 2.2.0\n", + "scikit-image 0.20.0\n", + "scipy 1.9.1\n", + "setuptools 58.1.0\n", + "shapely 2.0.1\n", + "six 1.16.0\n", + "slim 0.1 c:\\users\\saurav\\tfodcourse\\tensorflow\\models\\research\\slim\n", + "stack-data 0.6.2\n", + "sympy 1.11.1\n", + "tabulate 0.9.0\n", + "tensorboard 2.12.1\n", + "tensorboard-data-server 0.7.0\n", + "tensorboard-plugin-wit 1.8.1\n", + "tensorflow 2.12.0\n", + "tensorflow-addons 0.16.1\n", + "tensorflow-estimator 2.12.0\n", + "tensorflow-intel 2.12.0\n", + "tensorflow-io 0.31.0\n", + "tensorflow-io-gcs-filesystem 0.31.0\n", + "termcolor 2.2.0\n", + "tf-models-official 2.11.3\n", + "tf-slim 1.1.0\n", + "tifffile 2023.4.12\n", + "torch 2.0.0+cu117\n", + "torchaudio 2.0.1+cu117\n", + "torchvision 0.15.1+cu117\n", + "tornado 6.2\n", + "traitlets 5.9.0\n", + "typeguard 3.0.2\n", + "typing_extensions 4.5.0\n", + "urllib3 1.26.15\n", + "wcwidth 0.2.6\n", + "Werkzeug 2.2.3\n", + "wget 3.2\n", + "wheel 0.40.0\n", + "wrapt 1.14.1\n", + "zipp 3.15.0\n" + ] + } + ], + "source": [ + "!pip list" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\tensorflow_addons\\utils\\ensure_tf_install.py:53: UserWarning: Tensorflow Addons supports using Python ops for all Tensorflow versions above or equal to 2.6.0 and strictly below 2.9.0 (nightly versions are not supported). \n", + " The versions of TensorFlow you are currently using is 2.12.0 and is not supported. \n", + "Some things might work, some things might not.\n", + "If you were to encounter a bug, do not file an issue.\n", + "If you want to make sure you're using a tested and supported configuration, either change the TensorFlow version or the TensorFlow Addons's version. \n", + "You can find the compatibility matrix in TensorFlow Addon's readme:\n", + "https://github.com/tensorflow/addons\n", + " warnings.warn(\n", + "Running tests under Python 3.9.13: C:\\Users\\SAURAV\\TFODCourse\\tfod\\Scripts\\python.exe\n", + "[ RUN ] ModelBuilderTF2Test.test_create_center_net_deepmac\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.899064 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.899064 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.914711 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.914711 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.914711 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.914711 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.914711 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.930336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.930336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.930336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.930336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.930336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.930336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.945961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.945961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.945961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.945961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.945961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.945961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.961586 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.961586 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.961586 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.961586 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.961586 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.961586 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.977211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.977211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.977211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.977211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.977211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.977211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.992836 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.992836 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.992836 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.992836 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.992836 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.992836 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:40.992836 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.008461 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.008461 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.008461 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.008461 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.008461 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.008461 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.024087 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.024087 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.024087 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.024087 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.024087 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.024087 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.039711 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.039711 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.039711 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.039711 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.039711 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.039711 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.055336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.055336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.055336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.055336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.055336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.055336 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.070961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.070961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.070961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.070961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.070961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.070961 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.086587 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.086587 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.086587 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.086587 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.086587 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.086587 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.102211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.102211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.102211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.102211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.102211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.102211 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\builders\\model_builder.py:1112: DeprecationWarning: The 'warn' function is deprecated, use 'warning' instead\n", + " logging.warn(('Building experimental DeepMAC meta-arch.'\n", + "W0628 17:45:41.133848 7520 model_builder.py:1112] Building experimental DeepMAC meta-arch. Some features may be omitted.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.165148 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.180773 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.180773 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.180773 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.180773 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.180773 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.180773 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.196398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.196398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.196398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.196398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.196398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.196398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.212022 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.212022 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.212022 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.212022 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.212022 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.212022 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.212022 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.227648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.227648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.227648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.227648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.227648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.227648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.243273 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.243273 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.243273 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.243273 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.243273 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.243273 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.258898 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.258898 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.258898 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.258898 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.258898 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.258898 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.274522 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.274522 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.274522 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.274522 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.274522 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.274522 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.290148 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.290148 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.290148 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.290148 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.290148 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.290148 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.290148 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.305775 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.305775 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.305775 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.305775 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.305775 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.305775 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.321398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.321398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.321398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.321398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.321398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.321398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.321398 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.337062 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.337062 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.337062 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.337062 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.337062 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.337062 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.352648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.352648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.352648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.352648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.352648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.352648 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.368272 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.368272 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.368272 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:41.462023 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_deepmac): 0.71s\n", + "I0628 17:45:41.486618 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_center_net_deepmac): 0.71s\n", + "[ OK ] ModelBuilderTF2Test.test_create_center_net_deepmac\n", + "[ RUN ] ModelBuilderTF2Test.test_create_center_net_model0 (customize_head_params=True)\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.947539 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.947539 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.963159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.963159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.963159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.963159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.963159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.963159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.978783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.978783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.978783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.978783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.978783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.978783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.978783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.994407 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.994407 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.994407 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.994407 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.994407 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:42.994407 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.010032 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.010032 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.010032 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.010032 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.010032 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.010032 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.025658 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.025658 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.025658 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.025658 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.025658 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.025658 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.041283 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.041283 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.041283 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.041283 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.041283 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.041283 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.056908 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.056908 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.056908 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.056908 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.056908 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.056908 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.072533 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.072533 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.072533 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.072533 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.072533 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.072533 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.072533 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.088157 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.088157 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.088157 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.088157 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.088157 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.088157 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.103783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.103783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.103783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.103783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.103783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.103783 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.119408 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.119408 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.119408 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.119408 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.119408 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.119408 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.135033 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.135033 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.135033 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.135033 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.135033 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.135033 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.135033 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.150658 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.150658 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.150658 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model0 (customize_head_params=True)): 1.73s\n", + "I0628 17:45:43.213798 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_center_net_model0 (customize_head_params=True)): 1.73s\n", + "[ OK ] ModelBuilderTF2Test.test_create_center_net_model0 (customize_head_params=True)\n", + "[ RUN ] ModelBuilderTF2Test.test_create_center_net_model1 (customize_head_params=False)\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.229423 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.229423 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.229423 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.229423 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.245159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.245159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.245159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.245159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.245159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.245159 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.260673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.260673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.260673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.260673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.260673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.260673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.276298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.276298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.276298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.276298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.276298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.276298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.291923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.291923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.291923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.291923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.291923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.291923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.291923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.307548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.307548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.307548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.307548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.307548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.307548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.323173 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.323173 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.323173 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.323173 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.323173 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.323173 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.323173 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.338909 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.338909 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.338909 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.338909 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.338909 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.338909 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.354565 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.354565 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.354565 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.354565 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.354565 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.354565 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.370048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.370048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.370048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.370048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.370048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.370048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.385673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.385673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.385673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.385673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.385673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.385673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.401298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.401298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.401298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.401298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.401298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.401298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.401298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.416923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.416923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.416923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.416923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.416923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.416923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.432548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model1 (customize_head_params=False)): 0.27s\n", + "I0628 17:45:43.479423 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_center_net_model1 (customize_head_params=False)): 0.27s\n", + "[ OK ] ModelBuilderTF2Test.test_create_center_net_model1 (customize_head_params=False)\n", + "[ RUN ] ModelBuilderTF2Test.test_create_center_net_model_from_keypoints\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.479423 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.495058 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.495058 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.495058 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.495058 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.495058 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.495058 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.510673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.510673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.510673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.510673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.510673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.510673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.526298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.526298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.526298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.526298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.526298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.526298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.526298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.541923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.541923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.541923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.541923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.541923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.541923 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.557548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.557548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.557548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.557548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.557548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.557548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.557548 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.573174 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.573174 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.573174 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.573174 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.573174 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.573174 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.588798 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.588798 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.588798 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.588798 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.588798 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.588798 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.588798 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.604554 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.604554 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.604554 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.604554 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.604554 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.604554 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.620048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.620048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.620048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.620048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.620048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.620048 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.635673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.635673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.635673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.635673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.635673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.635673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.635673 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.651298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.651298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.651298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.651298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.651298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.651298 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.666995 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.666995 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.666995 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.666995 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.666995 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.682931 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.682931 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.682931 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "WARNING:tensorflow:`tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "W0628 17:45:43.682931 7520 batch_normalization.py:1426] `tf.keras.layers.experimental.SyncBatchNormalization` endpoint is deprecated and will be removed in a future release. Please use `tf.keras.layers.BatchNormalization` with parameter `synchronized` set to True.\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model_from_keypoints): 0.23s\n", + "I0628 17:45:43.713980 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_center_net_model_from_keypoints): 0.23s\n", + "[ OK ] ModelBuilderTF2Test.test_create_center_net_model_from_keypoints\n", + "[ RUN ] ModelBuilderTF2Test.test_create_center_net_model_mobilenet\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model_mobilenet): 2.13s\n", + "I0628 17:45:45.841116 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_center_net_model_mobilenet): 2.13s\n", + "[ OK ] ModelBuilderTF2Test.test_create_center_net_model_mobilenet\n", + "[ RUN ] ModelBuilderTF2Test.test_create_experimental_model\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_experimental_model): 0.0s\n", + "I0628 17:45:45.858606 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_experimental_model): 0.0s\n", + "[ OK ] ModelBuilderTF2Test.test_create_experimental_model\n", + "[ RUN ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)): 0.01s\n", + "I0628 17:45:45.872148 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)): 0.01s\n", + "[ OK ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)\n", + "[ RUN ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)): 0.02s\n", + "I0628 17:45:45.887821 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)): 0.02s\n", + "[ OK ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)\n", + "[ RUN ] ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner): 0.02s\n", + "I0628 17:45:45.903446 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner): 0.02s\n", + "[ OK ] ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner\n", + "[ RUN ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul): 0.09s\n", + "I0628 17:45:45.997196 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul): 0.09s\n", + "[ OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul\n", + "[ RUN ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul): 0.09s\n", + "I0628 17:45:46.091490 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul): 0.09s\n", + "[ OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul\n", + "[ RUN ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul): 0.08s\n", + "I0628 17:45:46.169612 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul): 0.08s\n", + "[ OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul\n", + "[ RUN ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul): 0.09s\n", + "I0628 17:45:46.263338 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul): 0.09s\n", + "[ OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul\n", + "[ RUN ] ModelBuilderTF2Test.test_create_rfcn_model_from_config\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_rfcn_model_from_config): 0.08s\n", + "I0628 17:45:46.341490 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_rfcn_model_from_config): 0.08s\n", + "[ OK ] ModelBuilderTF2Test.test_create_rfcn_model_from_config\n", + "[ RUN ] ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config): 0.03s\n", + "I0628 17:45:46.372739 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config): 0.03s\n", + "[ OK ] ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config\n", + "[ RUN ] ModelBuilderTF2Test.test_create_ssd_models_from_config\n", + "I0628 17:45:46.528972 7520 ssd_efficientnet_bifpn_feature_extractor.py:150] EfficientDet EfficientNet backbone version: efficientnet-b0\n", + "I0628 17:45:46.528972 7520 ssd_efficientnet_bifpn_feature_extractor.py:152] EfficientDet BiFPN num filters: 64\n", + "I0628 17:45:46.528972 7520 ssd_efficientnet_bifpn_feature_extractor.py:153] EfficientDet BiFPN num iterations: 3\n", + "I0628 17:45:46.528972 7520 efficientnet_model.py:143] round_filter input=32 output=32\n", + "I0628 17:45:46.560223 7520 efficientnet_model.py:143] round_filter input=32 output=32\n", + "I0628 17:45:46.560223 7520 efficientnet_model.py:143] round_filter input=16 output=16\n", + "I0628 17:45:46.638776 7520 efficientnet_model.py:143] round_filter input=16 output=16\n", + "I0628 17:45:46.638776 7520 efficientnet_model.py:143] round_filter input=24 output=24\n", + "I0628 17:45:46.826300 7520 efficientnet_model.py:143] round_filter input=24 output=24\n", + "I0628 17:45:46.826300 7520 efficientnet_model.py:143] round_filter input=40 output=40\n", + "I0628 17:45:46.998175 7520 efficientnet_model.py:143] round_filter input=40 output=40\n", + "I0628 17:45:46.998175 7520 efficientnet_model.py:143] round_filter input=80 output=80\n", + "I0628 17:45:47.263800 7520 efficientnet_model.py:143] round_filter input=80 output=80\n", + "I0628 17:45:47.263800 7520 efficientnet_model.py:143] round_filter input=112 output=112\n", + "I0628 17:45:47.529863 7520 efficientnet_model.py:143] round_filter input=112 output=112\n", + "I0628 17:45:47.529863 7520 efficientnet_model.py:143] round_filter input=192 output=192\n", + "I0628 17:45:47.889409 7520 efficientnet_model.py:143] round_filter input=192 output=192\n", + "I0628 17:45:47.889409 7520 efficientnet_model.py:143] round_filter input=320 output=320\n", + "I0628 17:45:47.983149 7520 efficientnet_model.py:143] round_filter input=1280 output=1280\n", + "I0628 17:45:48.029856 7520 efficientnet_model.py:453] Building model efficientnet with params ModelConfig(width_coefficient=1.0, depth_coefficient=1.0, resolution=224, dropout_rate=0.2, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')\n", + "I0628 17:45:48.076739 7520 ssd_efficientnet_bifpn_feature_extractor.py:150] EfficientDet EfficientNet backbone version: efficientnet-b1\n", + "I0628 17:45:48.076739 7520 ssd_efficientnet_bifpn_feature_extractor.py:152] EfficientDet BiFPN num filters: 88\n", + "I0628 17:45:48.076739 7520 ssd_efficientnet_bifpn_feature_extractor.py:153] EfficientDet BiFPN num iterations: 4\n", + "I0628 17:45:48.076739 7520 efficientnet_model.py:143] round_filter input=32 output=32\n", + "I0628 17:45:48.092364 7520 efficientnet_model.py:143] round_filter input=32 output=32\n", + "I0628 17:45:48.092364 7520 efficientnet_model.py:143] round_filter input=16 output=16\n", + "I0628 17:45:48.217364 7520 efficientnet_model.py:143] round_filter input=16 output=16\n", + "I0628 17:45:48.217364 7520 efficientnet_model.py:143] round_filter input=24 output=24\n", + "I0628 17:45:48.451738 7520 efficientnet_model.py:143] round_filter input=24 output=24\n", + "I0628 17:45:48.451738 7520 efficientnet_model.py:143] round_filter input=40 output=40\n", + "I0628 17:45:48.701564 7520 efficientnet_model.py:143] round_filter input=40 output=40\n", + "I0628 17:45:48.701564 7520 efficientnet_model.py:143] round_filter input=80 output=80\n", + "I0628 17:45:49.014064 7520 efficientnet_model.py:143] round_filter input=80 output=80\n", + "I0628 17:45:49.014064 7520 efficientnet_model.py:143] round_filter input=112 output=112\n", + "I0628 17:45:49.342189 7520 efficientnet_model.py:143] round_filter input=112 output=112\n", + "I0628 17:45:49.342189 7520 efficientnet_model.py:143] round_filter input=192 output=192\n", + "I0628 17:45:49.889064 7520 efficientnet_model.py:143] round_filter input=192 output=192\n", + "I0628 17:45:49.889064 7520 efficientnet_model.py:143] round_filter input=320 output=320\n", + "I0628 17:45:50.076565 7520 efficientnet_model.py:143] round_filter input=1280 output=1280\n", + "I0628 17:45:50.123417 7520 efficientnet_model.py:453] Building model efficientnet with params ModelConfig(width_coefficient=1.0, depth_coefficient=1.1, resolution=240, dropout_rate=0.2, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')\n", + "I0628 17:45:50.170852 7520 ssd_efficientnet_bifpn_feature_extractor.py:150] EfficientDet EfficientNet backbone version: efficientnet-b2\n", + "I0628 17:45:50.170852 7520 ssd_efficientnet_bifpn_feature_extractor.py:152] EfficientDet BiFPN num filters: 112\n", + "I0628 17:45:50.170852 7520 ssd_efficientnet_bifpn_feature_extractor.py:153] EfficientDet BiFPN num iterations: 5\n", + "I0628 17:45:50.170852 7520 efficientnet_model.py:143] round_filter input=32 output=32\n", + "I0628 17:45:50.186476 7520 efficientnet_model.py:143] round_filter input=32 output=32\n", + "I0628 17:45:50.186476 7520 efficientnet_model.py:143] round_filter input=16 output=16\n", + "I0628 17:45:50.311480 7520 efficientnet_model.py:143] round_filter input=16 output=16\n", + "I0628 17:45:50.311480 7520 efficientnet_model.py:143] round_filter input=24 output=24\n", + "I0628 17:45:50.546012 7520 efficientnet_model.py:143] round_filter input=24 output=24\n", + "I0628 17:45:50.546012 7520 efficientnet_model.py:143] round_filter input=40 output=48\n", + "I0628 17:45:50.795851 7520 efficientnet_model.py:143] round_filter input=40 output=48\n", + "I0628 17:45:50.795851 7520 efficientnet_model.py:143] round_filter input=80 output=88\n", + "I0628 17:45:51.139601 7520 efficientnet_model.py:143] round_filter input=80 output=88\n", + "I0628 17:45:51.139601 7520 efficientnet_model.py:143] round_filter input=112 output=120\n", + "I0628 17:45:51.498981 7520 efficientnet_model.py:143] round_filter input=112 output=120\n", + "I0628 17:45:51.498981 7520 efficientnet_model.py:143] round_filter input=192 output=208\n", + "I0628 17:45:51.936606 7520 efficientnet_model.py:143] round_filter input=192 output=208\n", + "I0628 17:45:51.936606 7520 efficientnet_model.py:143] round_filter input=320 output=352\n", + "I0628 17:45:52.139733 7520 efficientnet_model.py:143] round_filter input=1280 output=1408\n", + "I0628 17:45:52.186571 7520 efficientnet_model.py:453] Building model efficientnet with params ModelConfig(width_coefficient=1.1, depth_coefficient=1.2, resolution=260, dropout_rate=0.3, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')\n", + "I0628 17:45:52.249106 7520 ssd_efficientnet_bifpn_feature_extractor.py:150] EfficientDet EfficientNet backbone version: efficientnet-b3\n", + "I0628 17:45:52.249106 7520 ssd_efficientnet_bifpn_feature_extractor.py:152] EfficientDet BiFPN num filters: 160\n", + "I0628 17:45:52.249106 7520 ssd_efficientnet_bifpn_feature_extractor.py:153] EfficientDet BiFPN num iterations: 6\n", + "I0628 17:45:52.249106 7520 efficientnet_model.py:143] round_filter input=32 output=40\n", + "I0628 17:45:52.264731 7520 efficientnet_model.py:143] round_filter input=32 output=40\n", + "I0628 17:45:52.264731 7520 efficientnet_model.py:143] round_filter input=16 output=24\n", + "I0628 17:45:52.405356 7520 efficientnet_model.py:143] round_filter input=16 output=24\n", + "I0628 17:45:52.405356 7520 efficientnet_model.py:143] round_filter input=24 output=32\n", + "I0628 17:45:52.639731 7520 efficientnet_model.py:143] round_filter input=24 output=32\n", + "I0628 17:45:52.639731 7520 efficientnet_model.py:143] round_filter input=40 output=48\n", + "I0628 17:45:52.890392 7520 efficientnet_model.py:143] round_filter input=40 output=48\n", + "I0628 17:45:52.890392 7520 efficientnet_model.py:143] round_filter input=80 output=96\n", + "I0628 17:45:53.327939 7520 efficientnet_model.py:143] round_filter input=80 output=96\n", + "I0628 17:45:53.327939 7520 efficientnet_model.py:143] round_filter input=112 output=136\n", + "I0628 17:45:53.781044 7520 efficientnet_model.py:143] round_filter input=112 output=136\n", + "I0628 17:45:53.781044 7520 efficientnet_model.py:143] round_filter input=192 output=232\n", + "I0628 17:45:54.328121 7520 efficientnet_model.py:143] round_filter input=192 output=232\n", + "I0628 17:45:54.328121 7520 efficientnet_model.py:143] round_filter input=320 output=384\n", + "I0628 17:45:54.546860 7520 efficientnet_model.py:143] round_filter input=1280 output=1536\n", + "I0628 17:45:54.609592 7520 efficientnet_model.py:453] Building model efficientnet with params ModelConfig(width_coefficient=1.2, depth_coefficient=1.4, resolution=300, dropout_rate=0.3, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')\n", + "I0628 17:45:54.656256 7520 ssd_efficientnet_bifpn_feature_extractor.py:150] EfficientDet EfficientNet backbone version: efficientnet-b4\n", + "I0628 17:45:54.656256 7520 ssd_efficientnet_bifpn_feature_extractor.py:152] EfficientDet BiFPN num filters: 224\n", + "I0628 17:45:54.656256 7520 ssd_efficientnet_bifpn_feature_extractor.py:153] EfficientDet BiFPN num iterations: 7\n", + "I0628 17:45:54.671881 7520 efficientnet_model.py:143] round_filter input=32 output=48\n", + "I0628 17:45:54.687506 7520 efficientnet_model.py:143] round_filter input=32 output=48\n", + "I0628 17:45:54.687506 7520 efficientnet_model.py:143] round_filter input=16 output=24\n", + "I0628 17:45:54.812866 7520 efficientnet_model.py:143] round_filter input=16 output=24\n", + "I0628 17:45:54.812866 7520 efficientnet_model.py:143] round_filter input=24 output=32\n", + "I0628 17:45:55.125357 7520 efficientnet_model.py:143] round_filter input=24 output=32\n", + "I0628 17:45:55.125357 7520 efficientnet_model.py:143] round_filter input=40 output=56\n", + "I0628 17:45:55.656897 7520 efficientnet_model.py:143] round_filter input=40 output=56\n", + "I0628 17:45:55.656897 7520 efficientnet_model.py:143] round_filter input=80 output=112\n", + "I0628 17:45:56.172587 7520 efficientnet_model.py:143] round_filter input=80 output=112\n", + "I0628 17:45:56.172587 7520 efficientnet_model.py:143] round_filter input=112 output=160\n", + "I0628 17:45:56.735082 7520 efficientnet_model.py:143] round_filter input=112 output=160\n", + "I0628 17:45:56.735082 7520 efficientnet_model.py:143] round_filter input=192 output=272\n", + "I0628 17:45:57.501971 7520 efficientnet_model.py:143] round_filter input=192 output=272\n", + "I0628 17:45:57.501971 7520 efficientnet_model.py:143] round_filter input=320 output=448\n", + "I0628 17:45:57.720884 7520 efficientnet_model.py:143] round_filter input=1280 output=1792\n", + "I0628 17:45:57.783392 7520 efficientnet_model.py:453] Building model efficientnet with params ModelConfig(width_coefficient=1.4, depth_coefficient=1.8, resolution=380, dropout_rate=0.4, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')\n", + "I0628 17:45:57.845720 7520 ssd_efficientnet_bifpn_feature_extractor.py:150] EfficientDet EfficientNet backbone version: efficientnet-b5\n", + "I0628 17:45:57.845720 7520 ssd_efficientnet_bifpn_feature_extractor.py:152] EfficientDet BiFPN num filters: 288\n", + "I0628 17:45:57.845720 7520 ssd_efficientnet_bifpn_feature_extractor.py:153] EfficientDet BiFPN num iterations: 7\n", + "I0628 17:45:57.845720 7520 efficientnet_model.py:143] round_filter input=32 output=48\n", + "I0628 17:45:57.861345 7520 efficientnet_model.py:143] round_filter input=32 output=48\n", + "I0628 17:45:57.861345 7520 efficientnet_model.py:143] round_filter input=16 output=24\n", + "I0628 17:45:58.080081 7520 efficientnet_model.py:143] round_filter input=16 output=24\n", + "I0628 17:45:58.080081 7520 efficientnet_model.py:143] round_filter input=24 output=40\n", + "I0628 17:45:58.502404 7520 efficientnet_model.py:143] round_filter input=24 output=40\n", + "I0628 17:45:58.502404 7520 efficientnet_model.py:143] round_filter input=40 output=64\n", + "I0628 17:45:58.940068 7520 efficientnet_model.py:143] round_filter input=40 output=64\n", + "I0628 17:45:58.940068 7520 efficientnet_model.py:143] round_filter input=80 output=128\n", + "I0628 17:45:59.564740 7520 efficientnet_model.py:143] round_filter input=80 output=128\n", + "I0628 17:45:59.564740 7520 efficientnet_model.py:143] round_filter input=112 output=176\n", + "I0628 17:46:00.190022 7520 efficientnet_model.py:143] round_filter input=112 output=176\n", + "I0628 17:46:00.190022 7520 efficientnet_model.py:143] round_filter input=192 output=304\n", + "I0628 17:46:01.065716 7520 efficientnet_model.py:143] round_filter input=192 output=304\n", + "I0628 17:46:01.065716 7520 efficientnet_model.py:143] round_filter input=320 output=512\n", + "I0628 17:46:01.409744 7520 efficientnet_model.py:143] round_filter input=1280 output=2048\n", + "I0628 17:46:01.471994 7520 efficientnet_model.py:453] Building model efficientnet with params ModelConfig(width_coefficient=1.6, depth_coefficient=2.2, resolution=456, dropout_rate=0.4, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')\n", + "I0628 17:46:01.718199 7520 ssd_efficientnet_bifpn_feature_extractor.py:150] EfficientDet EfficientNet backbone version: efficientnet-b6\n", + "I0628 17:46:01.718199 7520 ssd_efficientnet_bifpn_feature_extractor.py:152] EfficientDet BiFPN num filters: 384\n", + "I0628 17:46:01.718199 7520 ssd_efficientnet_bifpn_feature_extractor.py:153] EfficientDet BiFPN num iterations: 8\n", + "I0628 17:46:01.718199 7520 efficientnet_model.py:143] round_filter input=32 output=56\n", + "I0628 17:46:01.742348 7520 efficientnet_model.py:143] round_filter input=32 output=56\n", + "I0628 17:46:01.742348 7520 efficientnet_model.py:143] round_filter input=16 output=32\n", + "I0628 17:46:01.962648 7520 efficientnet_model.py:143] round_filter input=16 output=32\n", + "I0628 17:46:01.962648 7520 efficientnet_model.py:143] round_filter input=24 output=40\n", + "I0628 17:46:02.462798 7520 efficientnet_model.py:143] round_filter input=24 output=40\n", + "I0628 17:46:02.462798 7520 efficientnet_model.py:143] round_filter input=40 output=72\n", + "I0628 17:46:02.962807 7520 efficientnet_model.py:143] round_filter input=40 output=72\n", + "I0628 17:46:02.962807 7520 efficientnet_model.py:143] round_filter input=80 output=144\n", + "I0628 17:46:03.665931 7520 efficientnet_model.py:143] round_filter input=80 output=144\n", + "I0628 17:46:03.665931 7520 efficientnet_model.py:143] round_filter input=112 output=200\n", + "I0628 17:46:04.385004 7520 efficientnet_model.py:143] round_filter input=112 output=200\n", + "I0628 17:46:04.385004 7520 efficientnet_model.py:143] round_filter input=192 output=344\n", + "I0628 17:46:05.510359 7520 efficientnet_model.py:143] round_filter input=192 output=344\n", + "I0628 17:46:05.510359 7520 efficientnet_model.py:143] round_filter input=320 output=576\n", + "I0628 17:46:05.870255 7520 efficientnet_model.py:143] round_filter input=1280 output=2304\n", + "I0628 17:46:05.935183 7520 efficientnet_model.py:453] Building model efficientnet with params ModelConfig(width_coefficient=1.8, depth_coefficient=2.6, resolution=528, dropout_rate=0.5, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')\n", + "I0628 17:46:06.011531 7520 ssd_efficientnet_bifpn_feature_extractor.py:150] EfficientDet EfficientNet backbone version: efficientnet-b7\n", + "I0628 17:46:06.011531 7520 ssd_efficientnet_bifpn_feature_extractor.py:152] EfficientDet BiFPN num filters: 384\n", + "I0628 17:46:06.011531 7520 ssd_efficientnet_bifpn_feature_extractor.py:153] EfficientDet BiFPN num iterations: 8\n", + "I0628 17:46:06.026990 7520 efficientnet_model.py:143] round_filter input=32 output=64\n", + "I0628 17:46:06.042630 7520 efficientnet_model.py:143] round_filter input=32 output=64\n", + "I0628 17:46:06.042630 7520 efficientnet_model.py:143] round_filter input=16 output=32\n", + "I0628 17:46:06.292613 7520 efficientnet_model.py:143] round_filter input=16 output=32\n", + "I0628 17:46:06.292613 7520 efficientnet_model.py:143] round_filter input=24 output=48\n", + "I0628 17:46:06.887233 7520 efficientnet_model.py:143] round_filter input=24 output=48\n", + "I0628 17:46:06.887233 7520 efficientnet_model.py:143] round_filter input=40 output=80\n", + "I0628 17:46:07.480738 7520 efficientnet_model.py:143] round_filter input=40 output=80\n", + "I0628 17:46:07.480738 7520 efficientnet_model.py:143] round_filter input=80 output=160\n", + "I0628 17:46:08.622036 7520 efficientnet_model.py:143] round_filter input=80 output=160\n", + "I0628 17:46:08.622036 7520 efficientnet_model.py:143] round_filter input=112 output=224\n", + "I0628 17:46:09.591575 7520 efficientnet_model.py:143] round_filter input=112 output=224\n", + "I0628 17:46:09.591575 7520 efficientnet_model.py:143] round_filter input=192 output=384\n", + "I0628 17:46:10.919902 7520 efficientnet_model.py:143] round_filter input=192 output=384\n", + "I0628 17:46:10.919902 7520 efficientnet_model.py:143] round_filter input=320 output=640\n", + "I0628 17:46:11.450883 7520 efficientnet_model.py:143] round_filter input=1280 output=2560\n", + "I0628 17:46:11.513387 7520 efficientnet_model.py:453] Building model efficientnet with params ModelConfig(width_coefficient=2.0, depth_coefficient=3.1, resolution=600, dropout_rate=0.5, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_ssd_models_from_config): 25.23s\n", + "I0628 17:46:11.607133 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_create_ssd_models_from_config): 25.23s\n", + "[ OK ] ModelBuilderTF2Test.test_create_ssd_models_from_config\n", + "[ RUN ] ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update): 0.0s\n", + "I0628 17:46:11.638383 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update): 0.0s\n", + "[ OK ] ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update\n", + "[ RUN ] ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold): 0.0s\n", + "I0628 17:46:11.638383 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold): 0.0s\n", + "[ OK ] ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold\n", + "[ RUN ] ModelBuilderTF2Test.test_invalid_model_config_proto\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_model_config_proto): 0.0s\n", + "I0628 17:46:11.638383 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_invalid_model_config_proto): 0.0s\n", + "[ OK ] ModelBuilderTF2Test.test_invalid_model_config_proto\n", + "[ RUN ] ModelBuilderTF2Test.test_invalid_second_stage_batch_size\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_second_stage_batch_size): 0.0s\n", + "I0628 17:46:11.638383 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_invalid_second_stage_batch_size): 0.0s\n", + "[ OK ] ModelBuilderTF2Test.test_invalid_second_stage_batch_size\n", + "[ RUN ] ModelBuilderTF2Test.test_session\n", + "[ SKIPPED ] ModelBuilderTF2Test.test_session\n", + "[ RUN ] ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor): 0.0s\n", + "I0628 17:46:11.638383 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor): 0.0s\n", + "[ OK ] ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor\n", + "[ RUN ] ModelBuilderTF2Test.test_unknown_meta_architecture\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_meta_architecture): 0.0s\n", + "I0628 17:46:11.638383 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_unknown_meta_architecture): 0.0s\n", + "[ OK ] ModelBuilderTF2Test.test_unknown_meta_architecture\n", + "[ RUN ] ModelBuilderTF2Test.test_unknown_ssd_feature_extractor\n", + "INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_ssd_feature_extractor): 0.0s\n", + "I0628 17:46:11.638383 7520 test_util.py:2467] time(__main__.ModelBuilderTF2Test.test_unknown_ssd_feature_extractor): 0.0s\n", + "[ OK ] ModelBuilderTF2Test.test_unknown_ssd_feature_extractor\n", + "----------------------------------------------------------------------\n", + "Ran 24 tests in 30.860s\n", + "\n", + "OK (skipped=1)\n" + ] + } + ], + "source": [ + "VERIFICATION_SCRIPT = os.path.join(paths['APIMODEL_PATH'], 'research', 'object_detection', 'builders', 'model_builder_tf2_test.py')\n", + "# Verify Installation\n", + "!python {VERIFICATION_SCRIPT}" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Collecting tensorflow-addons==0.20.0\n", + " Downloading tensorflow_addons-0.20.0-cp39-cp39-win_amd64.whl (746 kB)\n", + " 0.0/746.7 kB ? eta -:--:--\n", + " ------ 122.9/746.7 kB 3.6 MB/s eta 0:00:01\n", + " -------------------------- 512.0/746.7 kB 6.4 MB/s eta 0:00:01\n", + " -------------------------------------- 746.7/746.7 kB 5.9 MB/s eta 0:00:00\n", + "Collecting typeguard<3.0.0,>=2.7 (from tensorflow-addons==0.20.0)\n", + " Downloading typeguard-2.13.3-py3-none-any.whl (17 kB)\n", + "Requirement already satisfied: packaging in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-addons==0.20.0) (23.0)\n", + "Installing collected packages: typeguard, tensorflow-addons\n", + " Attempting uninstall: typeguard\n", + " Found existing installation: typeguard 3.0.2\n", + " Uninstalling typeguard-3.0.2:\n", + " Successfully uninstalled typeguard-3.0.2\n", + " Attempting uninstall: tensorflow-addons\n", + " Found existing installation: tensorflow-addons 0.16.1\n", + " Uninstalling tensorflow-addons-0.16.1:\n", + " Successfully uninstalled tensorflow-addons-0.16.1\n", + "Successfully installed tensorflow-addons-0.20.0 typeguard-2.13.3\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", + "tf-models-official 2.11.3 requires google-api-python-client>=1.6.7, which is not installed.\n", + "tf-models-official 2.11.3 requires immutabledict, which is not installed.\n", + "tf-models-official 2.11.3 requires kaggle>=1.3.9, which is not installed.\n", + "tf-models-official 2.11.3 requires oauth2client, which is not installed.\n", + "tf-models-official 2.11.3 requires py-cpuinfo>=3.3.0, which is not installed.\n", + "tf-models-official 2.11.3 requires sentencepiece, which is not installed.\n", + "tf-models-official 2.11.3 requires seqeval, which is not installed.\n", + "tf-models-official 2.11.3 requires tensorflow-datasets, which is not installed.\n", + "tf-models-official 2.11.3 requires tensorflow-hub>=0.6.0, which is not installed.\n", + "tf-models-official 2.11.3 requires tensorflow-model-optimization>=0.4.1, which is not installed.\n", + "tf-models-official 2.11.3 requires tensorflow-text~=2.11.0, which is not installed.\n", + "tf-models-official 2.11.3 requires tensorflow~=2.11.0, but you have tensorflow 2.12.0 which is incompatible.\n" + ] + } + ], + "source": [ + "!pip install tensorflow-addons==0.20.0\n", + "import tensorflow_addons as tfa" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: gin-config in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (0.5.0)\n" + ] + } + ], + "source": [ + "!pip install gin-config" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Collecting protobuf==3.20.1\n", + " Using cached protobuf-3.20.1-cp39-cp39-win_amd64.whl (904 kB)\n", + "Installing collected packages: protobuf\n", + " Attempting uninstall: protobuf\n", + " Found existing installation: protobuf 4.23.3\n", + " Uninstalling protobuf-4.23.3:\n", + " Successfully uninstalled protobuf-4.23.3\n", + "Successfully installed protobuf-3.20.1\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "WARNING: Ignoring invalid distribution -rotobuf (c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages)\n", + "WARNING: Ignoring invalid distribution -rotobuf (c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages)\n", + "ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", + "apache-beam 2.46.0 requires cloudpickle~=2.2.1, which is not installed.\n", + "apache-beam 2.46.0 requires crcmod<2.0,>=1.7, which is not installed.\n", + "apache-beam 2.46.0 requires dill<0.3.2,>=0.3.1.1, which is not installed.\n", + "apache-beam 2.46.0 requires fastavro<2,>=0.23.6, which is not installed.\n", + "apache-beam 2.46.0 requires fasteners<1.0,>=0.3, which is not installed.\n", + "apache-beam 2.46.0 requires hdfs<3.0.0,>=2.1.0, which is not installed.\n", + "apache-beam 2.46.0 requires httplib2<0.22.0,>=0.8, which is not installed.\n", + "apache-beam 2.46.0 requires objsize<0.7.0,>=0.6.1, which is not installed.\n", + "apache-beam 2.46.0 requires orjson<4.0, which is not installed.\n", + "apache-beam 2.46.0 requires proto-plus<2,>=1.7.1, which is not installed.\n", + "apache-beam 2.46.0 requires pyarrow<10.0.0,>=3.0.0, which is not installed.\n", + "apache-beam 2.46.0 requires pydot<2,>=1.2.0, which is not installed.\n", + "apache-beam 2.46.0 requires pymongo<4.0.0,>=3.8.0, which is not installed.\n", + "apache-beam 2.46.0 requires zstandard<1,>=0.18.0, which is not installed.\n", + "tensorflow-intel 2.12.0 requires protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3, but you have protobuf 3.20.1 which is incompatible.\n" + ] + } + ], + "source": [ + "!pip install protobuf==3.20.1" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: tensorflow in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (2.12.0)\n", + "Requirement already satisfied: tensorflow-intel==2.12.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow) (2.12.0)\n", + "Requirement already satisfied: absl-py>=1.0.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (1.4.0)\n", + "Requirement already satisfied: astunparse>=1.6.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (1.6.3)\n", + "Requirement already satisfied: flatbuffers>=2.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (23.3.3)\n", + "Requirement already satisfied: gast<=0.4.0,>=0.2.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (0.4.0)\n", + "Requirement already satisfied: google-pasta>=0.1.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (0.2.0)\n", + "Requirement already satisfied: h5py>=2.9.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (3.8.0)\n", + "Requirement already satisfied: jax>=0.3.15 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (0.4.8)\n", + "Requirement already satisfied: libclang>=13.0.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (15.0.6.1)\n", + "Requirement already satisfied: numpy<1.24,>=1.22 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (1.23.5)\n", + "Requirement already satisfied: opt-einsum>=2.3.2 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (3.3.0)\n", + "Requirement already satisfied: packaging in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (23.0)\n", + "Collecting protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 (from tensorflow-intel==2.12.0->tensorflow)\n", + " Downloading protobuf-4.23.3-cp39-cp39-win_amd64.whl (422 kB)\n", + " 0.0/422.5 kB ? eta -:--:--\n", + " ------------ 143.4/422.5 kB 4.3 MB/s eta 0:00:01\n", + " -------------------------------------- 422.5/422.5 kB 5.3 MB/s eta 0:00:00\n", + "Requirement already satisfied: setuptools in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (58.1.0)\n", + "Requirement already satisfied: six>=1.12.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (1.16.0)\n", + "Requirement already satisfied: termcolor>=1.1.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (2.2.0)\n", + "Requirement already satisfied: typing-extensions>=3.6.6 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (4.5.0)\n", + "Requirement already satisfied: wrapt<1.15,>=1.11.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (1.14.1)\n", + "Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (1.51.3)\n", + "Requirement already satisfied: tensorboard<2.13,>=2.12 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (2.12.1)\n", + "Requirement already satisfied: tensorflow-estimator<2.13,>=2.12.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (2.12.0)\n", + "Requirement already satisfied: keras<2.13,>=2.12.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (2.12.0)\n", + "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorflow-intel==2.12.0->tensorflow) (0.31.0)\n", + "Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from astunparse>=1.6.0->tensorflow-intel==2.12.0->tensorflow) (0.40.0)\n", + "Requirement already satisfied: ml-dtypes>=0.0.3 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from jax>=0.3.15->tensorflow-intel==2.12.0->tensorflow) (0.0.4)\n", + "Requirement already satisfied: scipy>=1.7 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from jax>=0.3.15->tensorflow-intel==2.12.0->tensorflow) (1.9.1)\n", + "Requirement already satisfied: google-auth<3,>=1.6.3 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (2.16.2)\n", + "Requirement already satisfied: google-auth-oauthlib<1.1,>=0.5 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (1.0.0)\n", + "Requirement already satisfied: markdown>=2.6.8 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (3.4.1)\n", + "Requirement already satisfied: requests<3,>=2.21.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (2.28.2)\n", + "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (0.7.0)\n", + "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (1.8.1)\n", + "Requirement already satisfied: werkzeug>=1.0.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (2.2.3)\n", + "Requirement already satisfied: cachetools<6.0,>=2.0.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (5.3.0)\n", + "Requirement already satisfied: pyasn1-modules>=0.2.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (0.2.8)\n", + "Requirement already satisfied: rsa<5,>=3.1.4 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (4.9)\n", + "Requirement already satisfied: requests-oauthlib>=0.7.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from google-auth-oauthlib<1.1,>=0.5->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (1.3.1)\n", + "Requirement already satisfied: importlib-metadata>=4.4 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from markdown>=2.6.8->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (6.0.0)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (3.1.0)\n", + "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (3.4)\n", + "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (1.26.15)\n", + "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (2022.12.7)\n", + "Requirement already satisfied: MarkupSafe>=2.1.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from werkzeug>=1.0.1->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (2.1.2)\n", + "Requirement already satisfied: zipp>=0.5 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (3.15.0)\n", + "Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (0.4.8)\n", + "Requirement already satisfied: oauthlib>=3.0.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<1.1,>=0.5->tensorboard<2.13,>=2.12->tensorflow-intel==2.12.0->tensorflow) (3.2.2)\n", + "Installing collected packages: protobuf\n", + " Attempting uninstall: protobuf\n", + " Found existing installation: protobuf 3.20.1\n", + " Uninstalling protobuf-3.20.1:\n", + " Successfully uninstalled protobuf-3.20.1\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "ERROR: Could not install packages due to an OSError: [WinError 5] Access is denied: 'C:\\\\Users\\\\SAURAV\\\\TFODCourse\\\\tfod\\\\Lib\\\\site-packages\\\\google\\\\~.otobuf\\\\internal\\\\_api_implementation.cp39-win_amd64.pyd'\n", + "Check the permissions.\n", + "\n" + ] + } + ], + "source": [ + "!pip install tensorflow --upgrade" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: matplotlib in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (3.7.1)\n", + "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib) (1.0.7)\n", + "Requirement already satisfied: cycler>=0.10 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib) (0.11.0)\n", + "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib) (4.39.2)\n", + "Requirement already satisfied: kiwisolver>=1.0.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib) (1.4.4)\n", + "Requirement already satisfied: numpy>=1.20 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib) (1.23.5)\n", + "Requirement already satisfied: packaging>=20.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib) (23.0)\n", + "Requirement already satisfied: pillow>=6.2.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib) (9.4.0)\n", + "Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages\\pyparsing-2.4.7-py3.9.egg (from matplotlib) (2.4.7)\n", + "Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib) (2.8.2)\n", + "Requirement already satisfied: importlib-resources>=3.2.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from matplotlib) (5.12.0)\n", + "Requirement already satisfied: zipp>=3.1.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from importlib-resources>=3.2.0->matplotlib) (3.15.0)\n", + "Requirement already satisfied: six>=1.5 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "WARNING: Ignoring invalid distribution -rotobuf (c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages)\n", + "WARNING: Ignoring invalid distribution -rotobuf (c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages)\n" + ] + } + ], + "source": [ + "!pip install matplotlib" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: Pillow in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (9.4.0)\n" + ] + } + ], + "source": [ + "!pip install Pillow" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: pyyaml in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (5.1)\n" + ] + } + ], + "source": [ + "!pip install pyyaml" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [], + "source": [ + "import object_detection" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "collapsed": true, + "id": "csofht2npfDE", + "outputId": "ff5471b2-bed2-43f2-959c-327a706527b6" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " 0% [ ] 0 / 20515344\r", + " 0% [ ] 8192 / 20515344\r", + " 0% [ ] 16384 / 20515344\r", + " 0% [ ] 24576 / 20515344\r", + " 0% [ ] 32768 / 20515344\r", + " 0% [ ] 40960 / 20515344\r", + " 0% [ ] 49152 / 20515344\r", + " 0% [ ] 57344 / 20515344\r", + " 0% [ ] 65536 / 20515344\r", + " 0% [ ] 73728 / 20515344\r", + " 0% [ ] 81920 / 20515344\r", + " 0% [ ] 90112 / 20515344\r", + " 0% [ ] 98304 / 20515344\r", + " 0% [ ] 106496 / 20515344\r", + " 0% [ ] 114688 / 20515344\r", + " 0% [ ] 122880 / 20515344\r", + " 0% [ ] 131072 / 20515344\r", + " 0% [ ] 139264 / 20515344\r", + " 0% [ ] 147456 / 20515344\r", + " 0% [ ] 155648 / 20515344\r", + " 0% [ ] 163840 / 20515344\r", + " 0% [ ] 172032 / 20515344\r", + " 0% [ ] 180224 / 20515344\r", + " 0% [ ] 188416 / 20515344\r", + " 0% [ ] 196608 / 20515344\r", + " 0% [ ] 204800 / 20515344\r", + " 1% [ ] 212992 / 20515344\r", + " 1% [ ] 221184 / 20515344\r", + " 1% [ ] 229376 / 20515344\r", + " 1% [ ] 237568 / 20515344\r", + " 1% [ ] 245760 / 20515344\r", + " 1% [ ] 253952 / 20515344\r", + " 1% [ ] 262144 / 20515344\r", + " 1% [ ] 270336 / 20515344\r", + " 1% [ ] 278528 / 20515344\r", + " 1% [. ] 286720 / 20515344\r", + " 1% [. ] 294912 / 20515344\r", + " 1% [. ] 303104 / 20515344\r", + " 1% [. ] 311296 / 20515344\r", + " 1% [. ] 319488 / 20515344\r", + " 1% [. ] 327680 / 20515344\r", + " 1% [. ] 335872 / 20515344\r", + " 1% [. ] 344064 / 20515344\r", + " 1% [. ] 352256 / 20515344\r", + " 1% [. ] 360448 / 20515344\r", + " 1% [. ] 368640 / 20515344\r", + " 1% [. ] 376832 / 20515344\r", + " 1% [. ] 385024 / 20515344\r", + " 1% [. ] 393216 / 20515344\r", + " 1% [. ] 401408 / 20515344\r", + " 1% [. ] 409600 / 20515344\r", + " 2% [. ] 417792 / 20515344\r", + " 2% [. ] 425984 / 20515344\r", + " 2% [. ] 434176 / 20515344\r", + " 2% [. ] 442368 / 20515344\r", + " 2% [. ] 450560 / 20515344\r", + " 2% [. ] 458752 / 20515344\r", + " 2% [. ] 466944 / 20515344\r", + " 2% [. ] 475136 / 20515344\r", + " 2% [. ] 483328 / 20515344\r", + " 2% [. ] 491520 / 20515344\r", + " 2% [. ] 499712 / 20515344\r", + " 2% [. ] 507904 / 20515344\r", + " 2% [. ] 516096 / 20515344\r", + " 2% [. ] 524288 / 20515344\r", + " 2% [. ] 532480 / 20515344\r", + " 2% [. ] 540672 / 20515344\r", + " 2% [. ] 548864 / 20515344\r", + " 2% [. ] 557056 / 20515344\r", + " 2% [. ] 565248 / 20515344\r", + " 2% [.. ] 573440 / 20515344\r", + " 2% [.. ] 581632 / 20515344\r", + " 2% [.. ] 589824 / 20515344\r", + " 2% [.. ] 598016 / 20515344\r", + " 2% [.. ] 606208 / 20515344\r", + " 2% [.. ] 614400 / 20515344\r", + " 3% [.. ] 622592 / 20515344\r", + " 3% [.. ] 630784 / 20515344\r", + " 3% [.. ] 638976 / 20515344\r", + " 3% [.. ] 647168 / 20515344\r", + " 3% [.. ] 655360 / 20515344\r", + " 3% [.. ] 663552 / 20515344\r", + " 3% [.. ] 671744 / 20515344\r", + " 3% [.. ] 679936 / 20515344\r", + " 3% [.. ] 688128 / 20515344\r", + " 3% [.. ] 696320 / 20515344\r", + " 3% [.. ] 704512 / 20515344\r", + " 3% [.. ] 712704 / 20515344\r", + " 3% [.. ] 720896 / 20515344\r", + " 3% [.. ] 729088 / 20515344\r", + " 3% [.. ] 737280 / 20515344\r", + " 3% [.. ] 745472 / 20515344\r", + " 3% [.. ] 753664 / 20515344\r", + " 3% [.. ] 761856 / 20515344\r", + " 3% [.. ] 770048 / 20515344\r", + " 3% [.. ] 778240 / 20515344\r", + " 3% [.. ] 786432 / 20515344\r", + " 3% [.. ] 794624 / 20515344\r", + " 3% [.. ] 802816 / 20515344\r", + " 3% [.. ] 811008 / 20515344\r", + " 3% [.. ] 819200 / 20515344\r", + " 4% [.. ] 827392 / 20515344\r", + " 4% [.. ] 835584 / 20515344\r", + " 4% [.. ] 843776 / 20515344\r", + " 4% [.. ] 851968 / 20515344\r", + " 4% [... ] 860160 / 20515344\r", + " 4% [... ] 868352 / 20515344\r", + " 4% [... ] 876544 / 20515344\r", + " 4% [... ] 884736 / 20515344\r", + " 4% [... ] 892928 / 20515344\r", + " 4% [... ] 901120 / 20515344\r", + " 4% [... ] 909312 / 20515344\r", + " 4% [... ] 917504 / 20515344\r", + " 4% [... ] 925696 / 20515344\r", + " 4% [... ] 933888 / 20515344\r", + " 4% [... ] 942080 / 20515344\r", + " 4% [... ] 950272 / 20515344\r", + " 4% [... ] 958464 / 20515344\r", + " 4% [... ] 966656 / 20515344\r", + " 4% [... ] 974848 / 20515344\r", + " 4% [... ] 983040 / 20515344\r", + " 4% [... ] 991232 / 20515344\r", + " 4% [... ] 999424 / 20515344\r", + " 4% [... ] 1007616 / 20515344\r", + " 4% [... ] 1015808 / 20515344\r", + " 4% [... ] 1024000 / 20515344\r", + " 5% [... ] 1032192 / 20515344\r", + " 5% [... ] 1040384 / 20515344\r", + " 5% [... ] 1048576 / 20515344\r", + " 5% [... ] 1056768 / 20515344\r", + " 5% [... ] 1064960 / 20515344\r", + " 5% [... ] 1073152 / 20515344\r", + " 5% [... ] 1081344 / 20515344\r", + " 5% [... ] 1089536 / 20515344\r", + " 5% [... ] 1097728 / 20515344\r", + " 5% [... ] 1105920 / 20515344\r", + " 5% [... ] 1114112 / 20515344\r", + " 5% [... ] 1122304 / 20515344\r", + " 5% [... ] 1130496 / 20515344\r", + " 5% [... ] 1138688 / 20515344\r", + " 5% [.... ] 1146880 / 20515344\r", + " 5% [.... ] 1155072 / 20515344\r", + " 5% [.... ] 1163264 / 20515344\r", + " 5% [.... ] 1171456 / 20515344\r", + " 5% [.... ] 1179648 / 20515344\r", + " 5% [.... ] 1187840 / 20515344\r", + " 5% [.... ] 1196032 / 20515344\r", + " 5% [.... ] 1204224 / 20515344\r", + " 5% [.... ] 1212416 / 20515344\r", + " 5% [.... ] 1220608 / 20515344\r", + " 5% [.... ] 1228800 / 20515344\r", + " 6% [.... ] 1236992 / 20515344\r", + " 6% [.... ] 1245184 / 20515344\r", + " 6% [.... ] 1253376 / 20515344\r", + " 6% [.... ] 1261568 / 20515344\r", + " 6% [.... ] 1269760 / 20515344\r", + " 6% [.... ] 1277952 / 20515344\r", + " 6% [.... ] 1286144 / 20515344\r", + " 6% [.... ] 1294336 / 20515344\r", + " 6% [.... ] 1302528 / 20515344\r", + " 6% [.... ] 1310720 / 20515344\r", + " 6% [.... ] 1318912 / 20515344\r", + " 6% [.... ] 1327104 / 20515344\r", + " 6% [.... ] 1335296 / 20515344\r", + " 6% [.... ] 1343488 / 20515344\r", + " 6% [.... ] 1351680 / 20515344\r", + " 6% [.... ] 1359872 / 20515344\r", + " 6% [.... ] 1368064 / 20515344\r", + " 6% [.... ] 1376256 / 20515344\r", + " 6% [.... ] 1384448 / 20515344\r", + " 6% [.... ] 1392640 / 20515344\r", + " 6% [.... ] 1400832 / 20515344\r", + " 6% [.... ] 1409024 / 20515344\r", + " 6% [.... ] 1417216 / 20515344\r", + " 6% [..... ] 1425408 / 20515344\r", + " 6% [..... ] 1433600 / 20515344\r", + " 7% [..... ] 1441792 / 20515344\r", + " 7% [..... ] 1449984 / 20515344\r", + " 7% [..... ] 1458176 / 20515344\r", + " 7% [..... ] 1466368 / 20515344\r", + " 7% [..... ] 1474560 / 20515344\r", + " 7% [..... ] 1482752 / 20515344\r", + " 7% [..... ] 1490944 / 20515344\r", + " 7% [..... ] 1499136 / 20515344\r", + " 7% [..... ] 1507328 / 20515344\r", + " 7% [..... ] 1515520 / 20515344\r", + " 7% [..... ] 1523712 / 20515344\r", + " 7% [..... ] 1531904 / 20515344\r", + " 7% [..... ] 1540096 / 20515344\r", + " 7% [..... ] 1548288 / 20515344\r", + " 7% [..... ] 1556480 / 20515344\r", + " 7% [..... ] 1564672 / 20515344\r", + " 7% [..... ] 1572864 / 20515344\r", + " 7% [..... ] 1581056 / 20515344\r", + " 7% [..... ] 1589248 / 20515344\r", + " 7% [..... ] 1597440 / 20515344\r", + " 7% [..... ] 1605632 / 20515344\r", + " 7% [..... ] 1613824 / 20515344\r", + " 7% [..... ] 1622016 / 20515344\r", + " 7% [..... ] 1630208 / 20515344\r", + " 7% [..... ] 1638400 / 20515344\r", + " 8% [..... ] 1646592 / 20515344\r", + " 8% [..... ] 1654784 / 20515344\r", + " 8% [..... ] 1662976 / 20515344\r", + " 8% [..... ] 1671168 / 20515344\r", + " 8% [..... ] 1679360 / 20515344\r", + " 8% [..... ] 1687552 / 20515344\r", + " 8% [..... ] 1695744 / 20515344\r", + " 8% [..... ] 1703936 / 20515344\r", + " 8% [...... ] 1712128 / 20515344\r", + " 8% [...... ] 1720320 / 20515344\r", + " 8% [...... ] 1728512 / 20515344\r", + " 8% [...... ] 1736704 / 20515344\r", + " 8% [...... ] 1744896 / 20515344\r", + " 8% [...... ] 1753088 / 20515344\r", + " 8% [...... ] 1761280 / 20515344\r", + " 8% [...... ] 1769472 / 20515344\r", + " 8% [...... ] 1777664 / 20515344\r", + " 8% [...... ] 1785856 / 20515344\r", + " 8% [...... ] 1794048 / 20515344" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " 8% [...... ] 1802240 / 20515344\r", + " 8% [...... ] 1810432 / 20515344\r", + " 8% [...... ] 1818624 / 20515344\r", + " 8% [...... ] 1826816 / 20515344\r", + " 8% [...... ] 1835008 / 20515344\r", + " 8% [...... ] 1843200 / 20515344\r", + " 9% [...... ] 1851392 / 20515344\r", + " 9% [...... ] 1859584 / 20515344\r", + " 9% [...... ] 1867776 / 20515344\r", + " 9% [...... ] 1875968 / 20515344\r", + " 9% [...... ] 1884160 / 20515344\r", + " 9% [...... ] 1892352 / 20515344\r", + " 9% [...... ] 1900544 / 20515344\r", + " 9% [...... ] 1908736 / 20515344\r", + " 9% [...... ] 1916928 / 20515344\r", + " 9% [...... ] 1925120 / 20515344\r", + " 9% [...... ] 1933312 / 20515344\r", + " 9% [...... ] 1941504 / 20515344\r", + " 9% [...... ] 1949696 / 20515344\r", + " 9% [...... ] 1957888 / 20515344\r", + " 9% [...... ] 1966080 / 20515344\r", + " 9% [...... ] 1974272 / 20515344\r", + " 9% [...... ] 1982464 / 20515344\r", + " 9% [...... ] 1990656 / 20515344\r", + " 9% [....... ] 1998848 / 20515344\r", + " 9% [....... ] 2007040 / 20515344\r", + " 9% [....... ] 2015232 / 20515344\r", + " 9% [....... ] 2023424 / 20515344\r", + " 9% [....... ] 2031616 / 20515344\r", + " 9% [....... ] 2039808 / 20515344\r", + " 9% [....... ] 2048000 / 20515344\r", + " 10% [....... ] 2056192 / 20515344\r", + " 10% [....... ] 2064384 / 20515344\r", + " 10% [....... ] 2072576 / 20515344\r", + " 10% [....... ] 2080768 / 20515344\r", + " 10% [....... ] 2088960 / 20515344\r", + " 10% [....... ] 2097152 / 20515344\r", + " 10% [....... ] 2105344 / 20515344\r", + " 10% [....... ] 2113536 / 20515344\r", + " 10% [....... ] 2121728 / 20515344\r", + " 10% [....... ] 2129920 / 20515344\r", + " 10% [....... ] 2138112 / 20515344\r", + " 10% [....... ] 2146304 / 20515344\r", + " 10% [....... ] 2154496 / 20515344\r", + " 10% [....... ] 2162688 / 20515344\r", + " 10% [....... ] 2170880 / 20515344\r", + " 10% [....... ] 2179072 / 20515344\r", + " 10% [....... ] 2187264 / 20515344\r", + " 10% [....... ] 2195456 / 20515344\r", + " 10% [....... ] 2203648 / 20515344\r", + " 10% [....... ] 2211840 / 20515344\r", + " 10% [....... ] 2220032 / 20515344\r", + " 10% [....... ] 2228224 / 20515344\r", + " 10% [....... ] 2236416 / 20515344\r", + " 10% [....... ] 2244608 / 20515344\r", + " 10% [....... ] 2252800 / 20515344\r", + " 11% [....... ] 2260992 / 20515344\r", + " 11% [....... ] 2269184 / 20515344\r", + " 11% [....... ] 2277376 / 20515344\r", + " 11% [........ ] 2285568 / 20515344\r", + " 11% [........ ] 2293760 / 20515344\r", + " 11% [........ ] 2301952 / 20515344\r", + " 11% [........ ] 2310144 / 20515344\r", + " 11% [........ ] 2318336 / 20515344\r", + " 11% [........ ] 2326528 / 20515344\r", + " 11% [........ ] 2334720 / 20515344\r", + " 11% [........ ] 2342912 / 20515344\r", + " 11% [........ ] 2351104 / 20515344\r", + " 11% [........ ] 2359296 / 20515344\r", + " 11% [........ ] 2367488 / 20515344\r", + " 11% [........ ] 2375680 / 20515344\r", + " 11% [........ ] 2383872 / 20515344\r", + " 11% [........ ] 2392064 / 20515344\r", + " 11% [........ ] 2400256 / 20515344\r", + " 11% [........ ] 2408448 / 20515344\r", + " 11% [........ ] 2416640 / 20515344\r", + " 11% [........ ] 2424832 / 20515344\r", + " 11% [........ ] 2433024 / 20515344\r", + " 11% [........ ] 2441216 / 20515344\r", + " 11% [........ ] 2449408 / 20515344\r", + " 11% [........ ] 2457600 / 20515344\r", + " 12% [........ ] 2465792 / 20515344\r", + " 12% [........ ] 2473984 / 20515344\r", + " 12% [........ ] 2482176 / 20515344\r", + " 12% [........ ] 2490368 / 20515344\r", + " 12% [........ ] 2498560 / 20515344\r", + " 12% [........ ] 2506752 / 20515344\r", + " 12% [........ ] 2514944 / 20515344\r", + " 12% [........ ] 2523136 / 20515344\r", + " 12% [........ ] 2531328 / 20515344\r", + " 12% [........ ] 2539520 / 20515344\r", + " 12% [........ ] 2547712 / 20515344\r", + " 12% [........ ] 2555904 / 20515344\r", + " 12% [........ ] 2564096 / 20515344\r", + " 12% [......... ] 2572288 / 20515344\r", + " 12% [......... ] 2580480 / 20515344\r", + " 12% [......... ] 2588672 / 20515344\r", + " 12% [......... ] 2596864 / 20515344\r", + " 12% [......... ] 2605056 / 20515344\r", + " 12% [......... ] 2613248 / 20515344\r", + " 12% [......... ] 2621440 / 20515344\r", + " 12% [......... ] 2629632 / 20515344\r", + " 12% [......... ] 2637824 / 20515344\r", + " 12% [......... ] 2646016 / 20515344\r", + " 12% [......... ] 2654208 / 20515344\r", + " 12% [......... ] 2662400 / 20515344\r", + " 13% [......... ] 2670592 / 20515344\r", + " 13% [......... ] 2678784 / 20515344\r", + " 13% [......... ] 2686976 / 20515344\r", + " 13% [......... ] 2695168 / 20515344\r", + " 13% [......... ] 2703360 / 20515344\r", + " 13% [......... ] 2711552 / 20515344\r", + " 13% [......... ] 2719744 / 20515344\r", + " 13% [......... ] 2727936 / 20515344\r", + " 13% [......... ] 2736128 / 20515344\r", + " 13% [......... ] 2744320 / 20515344\r", + " 13% [......... ] 2752512 / 20515344\r", + " 13% [......... ] 2760704 / 20515344\r", + " 13% [......... ] 2768896 / 20515344\r", + " 13% [......... ] 2777088 / 20515344\r", + " 13% [......... ] 2785280 / 20515344\r", + " 13% [......... ] 2793472 / 20515344\r", + " 13% [......... ] 2801664 / 20515344\r", + " 13% [......... ] 2809856 / 20515344\r", + " 13% [......... ] 2818048 / 20515344\r", + " 13% [......... ] 2826240 / 20515344\r", + " 13% [......... ] 2834432 / 20515344\r", + " 13% [......... ] 2842624 / 20515344\r", + " 13% [.......... ] 2850816 / 20515344\r", + " 13% [.......... ] 2859008 / 20515344\r", + " 13% [.......... ] 2867200 / 20515344\r", + " 14% [.......... ] 2875392 / 20515344\r", + " 14% [.......... ] 2883584 / 20515344\r", + " 14% [.......... ] 2891776 / 20515344\r", + " 14% [.......... ] 2899968 / 20515344\r", + " 14% [.......... ] 2908160 / 20515344\r", + " 14% [.......... ] 2916352 / 20515344\r", + " 14% [.......... ] 2924544 / 20515344\r", + " 14% [.......... ] 2932736 / 20515344\r", + " 14% [.......... ] 2940928 / 20515344\r", + " 14% [.......... ] 2949120 / 20515344\r", + " 14% [.......... ] 2957312 / 20515344\r", + " 14% [.......... ] 2965504 / 20515344\r", + " 14% [.......... ] 2973696 / 20515344\r", + " 14% [.......... ] 2981888 / 20515344\r", + " 14% [.......... ] 2990080 / 20515344\r", + " 14% [.......... ] 2998272 / 20515344\r", + " 14% [.......... ] 3006464 / 20515344\r", + " 14% [.......... ] 3014656 / 20515344\r", + " 14% [.......... ] 3022848 / 20515344\r", + " 14% [.......... ] 3031040 / 20515344\r", + " 14% [.......... ] 3039232 / 20515344\r", + " 14% [.......... ] 3047424 / 20515344\r", + " 14% [.......... ] 3055616 / 20515344\r", + " 14% [.......... ] 3063808 / 20515344\r", + " 14% [.......... ] 3072000 / 20515344\r", + " 15% [.......... ] 3080192 / 20515344\r", + " 15% [.......... ] 3088384 / 20515344\r", + " 15% [.......... ] 3096576 / 20515344\r", + " 15% [.......... ] 3104768 / 20515344\r", + " 15% [.......... ] 3112960 / 20515344\r", + " 15% [.......... ] 3121152 / 20515344\r", + " 15% [.......... ] 3129344 / 20515344\r", + " 15% [........... ] 3137536 / 20515344\r", + " 15% [........... ] 3145728 / 20515344\r", + " 15% [........... ] 3153920 / 20515344\r", + " 15% [........... ] 3162112 / 20515344\r", + " 15% [........... ] 3170304 / 20515344\r", + " 15% [........... ] 3178496 / 20515344\r", + " 15% [........... ] 3186688 / 20515344\r", + " 15% [........... ] 3194880 / 20515344\r", + " 15% [........... ] 3203072 / 20515344\r", + " 15% [........... ] 3211264 / 20515344\r", + " 15% [........... ] 3219456 / 20515344\r", + " 15% [........... ] 3227648 / 20515344\r", + " 15% [........... ] 3235840 / 20515344\r", + " 15% [........... ] 3244032 / 20515344\r", + " 15% [........... ] 3252224 / 20515344\r", + " 15% [........... ] 3260416 / 20515344\r", + " 15% [........... ] 3268608 / 20515344\r", + " 15% [........... ] 3276800 / 20515344\r", + " 16% [........... ] 3284992 / 20515344\r", + " 16% [........... ] 3293184 / 20515344\r", + " 16% [........... ] 3301376 / 20515344\r", + " 16% [........... ] 3309568 / 20515344\r", + " 16% [........... ] 3317760 / 20515344\r", + " 16% [........... ] 3325952 / 20515344\r", + " 16% [........... ] 3334144 / 20515344\r", + " 16% [........... ] 3342336 / 20515344\r", + " 16% [........... ] 3350528 / 20515344\r", + " 16% [........... ] 3358720 / 20515344\r", + " 16% [........... ] 3366912 / 20515344\r", + " 16% [........... ] 3375104 / 20515344\r", + " 16% [........... ] 3383296 / 20515344\r", + " 16% [........... ] 3391488 / 20515344\r", + " 16% [........... ] 3399680 / 20515344\r", + " 16% [........... ] 3407872 / 20515344\r", + " 16% [........... ] 3416064 / 20515344\r", + " 16% [............ ] 3424256 / 20515344\r", + " 16% [............ ] 3432448 / 20515344\r", + " 16% [............ ] 3440640 / 20515344\r", + " 16% [............ ] 3448832 / 20515344\r", + " 16% [............ ] 3457024 / 20515344\r", + " 16% [............ ] 3465216 / 20515344\r", + " 16% [............ ] 3473408 / 20515344\r", + " 16% [............ ] 3481600 / 20515344\r", + " 17% [............ ] 3489792 / 20515344\r", + " 17% [............ ] 3497984 / 20515344\r", + " 17% [............ ] 3506176 / 20515344\r", + " 17% [............ ] 3514368 / 20515344\r", + " 17% [............ ] 3522560 / 20515344\r", + " 17% [............ ] 3530752 / 20515344\r", + " 17% [............ ] 3538944 / 20515344\r", + " 17% [............ ] 3547136 / 20515344\r", + " 17% [............ ] 3555328 / 20515344\r", + " 17% [............ ] 3563520 / 20515344\r", + " 17% [............ ] 3571712 / 20515344\r", + " 17% [............ ] 3579904 / 20515344\r", + " 17% [............ ] 3588096 / 20515344\r", + " 17% [............ ] 3596288 / 20515344\r", + " 17% [............ ] 3604480 / 20515344\r", + " 17% [............ ] 3612672 / 20515344\r", + " 17% [............ ] 3620864 / 20515344\r", + " 17% [............ ] 3629056 / 20515344\r", + " 17% [............ ] 3637248 / 20515344\r", + " 17% [............ ] 3645440 / 20515344\r", + " 17% [............ ] 3653632 / 20515344\r", + " 17% [............ ] 3661824 / 20515344\r", + " 17% [............ ] 3670016 / 20515344\r", + " 17% [............ ] 3678208 / 20515344\r", + " 17% [............ ] 3686400 / 20515344\r", + " 18% [............ ] 3694592 / 20515344\r", + " 18% [............ ] 3702784 / 20515344\r", + " 18% [............. ] 3710976 / 20515344\r", + " 18% [............. ] 3719168 / 20515344\r", + " 18% [............. ] 3727360 / 20515344\r", + " 18% [............. ] 3735552 / 20515344\r", + " 18% [............. ] 3743744 / 20515344\r", + " 18% [............. ] 3751936 / 20515344\r", + " 18% [............. ] 3760128 / 20515344\r", + " 18% [............. ] 3768320 / 20515344\r", + " 18% [............. ] 3776512 / 20515344\r", + " 18% [............. ] 3784704 / 20515344\r", + " 18% [............. ] 3792896 / 20515344\r", + " 18% [............. ] 3801088 / 20515344\r", + " 18% [............. ] 3809280 / 20515344\r", + " 18% [............. ] 3817472 / 20515344\r", + " 18% [............. ] 3825664 / 20515344\r", + " 18% [............. ] 3833856 / 20515344\r", + " 18% [............. ] 3842048 / 20515344\r", + " 18% [............. ] 3850240 / 20515344\r", + " 18% [............. ] 3858432 / 20515344\r", + " 18% [............. ] 3866624 / 20515344\r", + " 18% [............. ] 3874816 / 20515344\r", + " 18% [............. ] 3883008 / 20515344\r", + " 18% [............. ] 3891200 / 20515344\r", + " 19% [............. ] 3899392 / 20515344\r", + " 19% [............. ] 3907584 / 20515344\r", + " 19% [............. ] 3915776 / 20515344\r", + " 19% [............. ] 3923968 / 20515344\r", + " 19% [............. ] 3932160 / 20515344\r", + " 19% [............. ] 3940352 / 20515344\r", + " 19% [............. ] 3948544 / 20515344\r", + " 19% [............. ] 3956736 / 20515344\r", + " 19% [............. ] 3964928 / 20515344\r", + " 19% [............. ] 3973120 / 20515344\r", + " 19% [............. ] 3981312 / 20515344\r", + " 19% [.............. ] 3989504 / 20515344\r", + " 19% [.............. ] 3997696 / 20515344\r", + " 19% [.............. ] 4005888 / 20515344\r", + " 19% [.............. ] 4014080 / 20515344\r", + " 19% [.............. ] 4022272 / 20515344\r", + " 19% [.............. ] 4030464 / 20515344\r", + " 19% [.............. ] 4038656 / 20515344\r", + " 19% [.............. ] 4046848 / 20515344\r", + " 19% [.............. ] 4055040 / 20515344\r", + " 19% [.............. ] 4063232 / 20515344\r", + " 19% [.............. ] 4071424 / 20515344\r", + " 19% [.............. ] 4079616 / 20515344\r", + " 19% [.............. ] 4087808 / 20515344\r", + " 19% [.............. ] 4096000 / 20515344\r", + " 20% [.............. ] 4104192 / 20515344\r", + " 20% [.............. ] 4112384 / 20515344\r", + " 20% [.............. ] 4120576 / 20515344\r", + " 20% [.............. ] 4128768 / 20515344\r", + " 20% [.............. ] 4136960 / 20515344\r", + " 20% [.............. ] 4145152 / 20515344\r", + " 20% [.............. ] 4153344 / 20515344\r", + " 20% [.............. ] 4161536 / 20515344\r", + " 20% [.............. ] 4169728 / 20515344\r", + " 20% [.............. ] 4177920 / 20515344\r", + " 20% [.............. ] 4186112 / 20515344\r", + " 20% [.............. ] 4194304 / 20515344\r", + " 20% [.............. ] 4202496 / 20515344\r", + " 20% [.............. ] 4210688 / 20515344\r", + " 20% [.............. ] 4218880 / 20515344\r", + " 20% [.............. ] 4227072 / 20515344\r", + " 20% [.............. ] 4235264 / 20515344\r", + " 20% [.............. ] 4243456 / 20515344\r", + " 20% [.............. ] 4251648 / 20515344\r", + " 20% [.............. ] 4259840 / 20515344\r", + " 20% [.............. ] 4268032 / 20515344\r", + " 20% [............... ] 4276224 / 20515344\r", + " 20% [............... ] 4284416 / 20515344\r", + " 20% [............... ] 4292608 / 20515344\r", + " 20% [............... ] 4300800 / 20515344\r", + " 21% [............... ] 4308992 / 20515344\r", + " 21% [............... ] 4317184 / 20515344\r", + " 21% [............... ] 4325376 / 20515344\r", + " 21% [............... ] 4333568 / 20515344\r", + " 21% [............... ] 4341760 / 20515344\r", + " 21% [............... ] 4349952 / 20515344\r", + " 21% [............... ] 4358144 / 20515344\r", + " 21% [............... ] 4366336 / 20515344\r", + " 21% [............... ] 4374528 / 20515344\r", + " 21% [............... ] 4382720 / 20515344\r", + " 21% [............... ] 4390912 / 20515344\r", + " 21% [............... ] 4399104 / 20515344\r", + " 21% [............... ] 4407296 / 20515344\r", + " 21% [............... ] 4415488 / 20515344\r", + " 21% [............... ] 4423680 / 20515344\r", + " 21% [............... ] 4431872 / 20515344\r", + " 21% [............... ] 4440064 / 20515344\r", + " 21% [............... ] 4448256 / 20515344\r", + " 21% [............... ] 4456448 / 20515344\r", + " 21% [............... ] 4464640 / 20515344\r", + " 21% [............... ] 4472832 / 20515344\r", + " 21% [............... ] 4481024 / 20515344\r", + " 21% [............... ] 4489216 / 20515344\r", + " 21% [............... ] 4497408 / 20515344\r", + " 21% [............... ] 4505600 / 20515344\r", + " 22% [............... ] 4513792 / 20515344\r", + " 22% [............... ] 4521984 / 20515344\r", + " 22% [............... ] 4530176 / 20515344\r", + " 22% [............... ] 4538368 / 20515344\r", + " 22% [............... ] 4546560 / 20515344\r", + " 22% [............... ] 4554752 / 20515344\r", + " 22% [................ ] 4562944 / 20515344\r", + " 22% [................ ] 4571136 / 20515344\r", + " 22% [................ ] 4579328 / 20515344\r", + " 22% [................ ] 4587520 / 20515344\r", + " 22% [................ ] 4595712 / 20515344\r", + " 22% [................ ] 4603904 / 20515344\r", + " 22% [................ ] 4612096 / 20515344\r", + " 22% [................ ] 4620288 / 20515344\r", + " 22% [................ ] 4628480 / 20515344\r", + " 22% [................ ] 4636672 / 20515344\r", + " 22% [................ ] 4644864 / 20515344\r", + " 22% [................ ] 4653056 / 20515344\r", + " 22% [................ ] 4661248 / 20515344\r", + " 22% [................ ] 4669440 / 20515344\r", + " 22% [................ ] 4677632 / 20515344\r", + " 22% [................ ] 4685824 / 20515344\r", + " 22% [................ ] 4694016 / 20515344\r", + " 22% [................ ] 4702208 / 20515344\r", + " 22% [................ ] 4710400 / 20515344\r", + " 23% [................ ] 4718592 / 20515344\r", + " 23% [................ ] 4726784 / 20515344\r", + " 23% [................ ] 4734976 / 20515344\r", + " 23% [................ ] 4743168 / 20515344\r", + " 23% [................ ] 4751360 / 20515344\r", + " 23% [................ ] 4759552 / 20515344\r", + " 23% [................ ] 4767744 / 20515344\r", + " 23% [................ ] 4775936 / 20515344\r", + " 23% [................ ] 4784128 / 20515344\r", + " 23% [................ ] 4792320 / 20515344\r", + " 23% [................ ] 4800512 / 20515344\r", + " 23% [................ ] 4808704 / 20515344\r", + " 23% [................ ] 4816896 / 20515344\r", + " 23% [................ ] 4825088 / 20515344\r", + " 23% [................ ] 4833280 / 20515344\r", + " 23% [................ ] 4841472 / 20515344\r", + " 23% [................. ] 4849664 / 20515344\r", + " 23% [................. ] 4857856 / 20515344\r", + " 23% [................. ] 4866048 / 20515344\r", + " 23% [................. ] 4874240 / 20515344\r", + " 23% [................. ] 4882432 / 20515344\r", + " 23% [................. ] 4890624 / 20515344\r", + " 23% [................. ] 4898816 / 20515344\r", + " 23% [................. ] 4907008 / 20515344\r", + " 23% [................. ] 4915200 / 20515344\r", + " 23% [................. ] 4923392 / 20515344\r", + " 24% [................. ] 4931584 / 20515344\r", + " 24% [................. ] 4939776 / 20515344\r", + " 24% [................. ] 4947968 / 20515344\r", + " 24% [................. ] 4956160 / 20515344\r", + " 24% [................. ] 4964352 / 20515344\r", + " 24% [................. ] 4972544 / 20515344\r", + " 24% [................. ] 4980736 / 20515344\r", + " 24% [................. ] 4988928 / 20515344\r", + " 24% [................. ] 4997120 / 20515344\r", + " 24% [................. ] 5005312 / 20515344\r", + " 24% [................. ] 5013504 / 20515344\r", + " 24% [................. ] 5021696 / 20515344\r", + " 24% [................. ] 5029888 / 20515344\r", + " 24% [................. ] 5038080 / 20515344\r", + " 24% [................. ] 5046272 / 20515344\r", + " 24% [................. ] 5054464 / 20515344\r", + " 24% [................. ] 5062656 / 20515344\r", + " 24% [................. ] 5070848 / 20515344\r", + " 24% [................. ] 5079040 / 20515344\r", + " 24% [................. ] 5087232 / 20515344\r", + " 24% [................. ] 5095424 / 20515344\r", + " 24% [................. ] 5103616 / 20515344\r", + " 24% [................. ] 5111808 / 20515344\r", + " 24% [................. ] 5120000 / 20515344\r", + " 24% [................. ] 5128192 / 20515344\r", + " 25% [.................. ] 5136384 / 20515344\r", + " 25% [.................. ] 5144576 / 20515344\r", + " 25% [.................. ] 5152768 / 20515344\r", + " 25% [.................. ] 5160960 / 20515344\r", + " 25% [.................. ] 5169152 / 20515344\r", + " 25% [.................. ] 5177344 / 20515344\r", + " 25% [.................. ] 5185536 / 20515344\r", + " 25% [.................. ] 5193728 / 20515344\r", + " 25% [.................. ] 5201920 / 20515344\r", + " 25% [.................. ] 5210112 / 20515344\r", + " 25% [.................. ] 5218304 / 20515344\r", + " 25% [.................. ] 5226496 / 20515344\r", + " 25% [.................. ] 5234688 / 20515344\r", + " 25% [.................. ] 5242880 / 20515344\r", + " 25% [.................. ] 5251072 / 20515344\r", + " 25% [.................. ] 5259264 / 20515344\r", + " 25% [.................. ] 5267456 / 20515344\r", + " 25% [.................. ] 5275648 / 20515344\r", + " 25% [.................. ] 5283840 / 20515344\r", + " 25% [.................. ] 5292032 / 20515344\r", + " 25% [.................. ] 5300224 / 20515344\r", + " 25% [.................. ] 5308416 / 20515344\r", + " 25% [.................. ] 5316608 / 20515344\r", + " 25% [.................. ] 5324800 / 20515344\r", + " 25% [.................. ] 5332992 / 20515344\r", + " 26% [.................. ] 5341184 / 20515344\r", + " 26% [.................. ] 5349376 / 20515344\r", + " 26% [.................. ] 5357568 / 20515344\r", + " 26% [.................. ] 5365760 / 20515344\r", + " 26% [.................. ] 5373952 / 20515344\r", + " 26% [.................. ] 5382144 / 20515344\r", + " 26% [.................. ] 5390336 / 20515344\r", + " 26% [.................. ] 5398528 / 20515344\r", + " 26% [.................. ] 5406720 / 20515344\r", + " 26% [................... ] 5414912 / 20515344\r", + " 26% [................... ] 5423104 / 20515344\r", + " 26% [................... ] 5431296 / 20515344\r", + " 26% [................... ] 5439488 / 20515344\r", + " 26% [................... ] 5447680 / 20515344\r", + " 26% [................... ] 5455872 / 20515344\r", + " 26% [................... ] 5464064 / 20515344\r", + " 26% [................... ] 5472256 / 20515344\r", + " 26% [................... ] 5480448 / 20515344\r", + " 26% [................... ] 5488640 / 20515344\r", + " 26% [................... ] 5496832 / 20515344\r", + " 26% [................... ] 5505024 / 20515344\r", + " 26% [................... ] 5513216 / 20515344\r", + " 26% [................... ] 5521408 / 20515344\r", + " 26% [................... ] 5529600 / 20515344" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " 26% [................... ] 5537792 / 20515344\r", + " 27% [................... ] 5545984 / 20515344\r", + " 27% [................... ] 5554176 / 20515344\r", + " 27% [................... ] 5562368 / 20515344\r", + " 27% [................... ] 5570560 / 20515344\r", + " 27% [................... ] 5578752 / 20515344\r", + " 27% [................... ] 5586944 / 20515344\r", + " 27% [................... ] 5595136 / 20515344\r", + " 27% [................... ] 5603328 / 20515344\r", + " 27% [................... ] 5611520 / 20515344\r", + " 27% [................... ] 5619712 / 20515344\r", + " 27% [................... ] 5627904 / 20515344\r", + " 27% [................... ] 5636096 / 20515344\r", + " 27% [................... ] 5644288 / 20515344\r", + " 27% [................... ] 5652480 / 20515344\r", + " 27% [................... ] 5660672 / 20515344\r", + " 27% [................... ] 5668864 / 20515344\r", + " 27% [................... ] 5677056 / 20515344\r", + " 27% [................... ] 5685248 / 20515344\r", + " 27% [................... ] 5693440 / 20515344\r", + " 27% [.................... ] 5701632 / 20515344\r", + " 27% [.................... ] 5709824 / 20515344\r", + " 27% [.................... ] 5718016 / 20515344\r", + " 27% [.................... ] 5726208 / 20515344\r", + " 27% [.................... ] 5734400 / 20515344\r", + " 27% [.................... ] 5742592 / 20515344\r", + " 28% [.................... ] 5750784 / 20515344\r", + " 28% [.................... ] 5758976 / 20515344\r", + " 28% [.................... ] 5767168 / 20515344\r", + " 28% [.................... ] 5775360 / 20515344\r", + " 28% [.................... ] 5783552 / 20515344\r", + " 28% [.................... ] 5791744 / 20515344\r", + " 28% [.................... ] 5799936 / 20515344\r", + " 28% [.................... ] 5808128 / 20515344\r", + " 28% [.................... ] 5816320 / 20515344\r", + " 28% [.................... ] 5824512 / 20515344\r", + " 28% [.................... ] 5832704 / 20515344\r", + " 28% [.................... ] 5840896 / 20515344\r", + " 28% [.................... ] 5849088 / 20515344\r", + " 28% [.................... ] 5857280 / 20515344\r", + " 28% [.................... ] 5865472 / 20515344\r", + " 28% [.................... ] 5873664 / 20515344\r", + " 28% [.................... ] 5881856 / 20515344\r", + " 28% [.................... ] 5890048 / 20515344\r", + " 28% [.................... ] 5898240 / 20515344\r", + " 28% [.................... ] 5906432 / 20515344\r", + " 28% [.................... ] 5914624 / 20515344\r", + " 28% [.................... ] 5922816 / 20515344\r", + " 28% [.................... ] 5931008 / 20515344\r", + " 28% [.................... ] 5939200 / 20515344\r", + " 28% [.................... ] 5947392 / 20515344\r", + " 29% [.................... ] 5955584 / 20515344\r", + " 29% [.................... ] 5963776 / 20515344\r", + " 29% [.................... ] 5971968 / 20515344\r", + " 29% [.................... ] 5980160 / 20515344\r", + " 29% [..................... ] 5988352 / 20515344\r", + " 29% [..................... ] 5996544 / 20515344\r", + " 29% [..................... ] 6004736 / 20515344\r", + " 29% [..................... ] 6012928 / 20515344\r", + " 29% [..................... ] 6021120 / 20515344\r", + " 29% [..................... ] 6029312 / 20515344\r", + " 29% [..................... ] 6037504 / 20515344\r", + " 29% [..................... ] 6045696 / 20515344\r", + " 29% [..................... ] 6053888 / 20515344\r", + " 29% [..................... ] 6062080 / 20515344\r", + " 29% [..................... ] 6070272 / 20515344\r", + " 29% [..................... ] 6078464 / 20515344\r", + " 29% [..................... ] 6086656 / 20515344\r", + " 29% [..................... ] 6094848 / 20515344\r", + " 29% [..................... ] 6103040 / 20515344\r", + " 29% [..................... ] 6111232 / 20515344\r", + " 29% [..................... ] 6119424 / 20515344\r", + " 29% [..................... ] 6127616 / 20515344\r", + " 29% [..................... ] 6135808 / 20515344\r", + " 29% [..................... ] 6144000 / 20515344\r", + " 29% [..................... ] 6152192 / 20515344\r", + " 30% [..................... ] 6160384 / 20515344\r", + " 30% [..................... ] 6168576 / 20515344\r", + " 30% [..................... ] 6176768 / 20515344\r", + " 30% [..................... ] 6184960 / 20515344\r", + " 30% [..................... ] 6193152 / 20515344\r", + " 30% [..................... ] 6201344 / 20515344\r", + " 30% [..................... ] 6209536 / 20515344\r", + " 30% [..................... ] 6217728 / 20515344\r", + " 30% [..................... ] 6225920 / 20515344\r", + " 30% [..................... ] 6234112 / 20515344\r", + " 30% [..................... ] 6242304 / 20515344\r", + " 30% [..................... ] 6250496 / 20515344\r", + " 30% [..................... ] 6258688 / 20515344\r", + " 30% [..................... ] 6266880 / 20515344\r", + " 30% [...................... ] 6275072 / 20515344\r", + " 30% [...................... ] 6283264 / 20515344\r", + " 30% [...................... ] 6291456 / 20515344\r", + " 30% [...................... ] 6299648 / 20515344\r", + " 30% [...................... ] 6307840 / 20515344\r", + " 30% [...................... ] 6316032 / 20515344\r", + " 30% [...................... ] 6324224 / 20515344\r", + " 30% [...................... ] 6332416 / 20515344\r", + " 30% [...................... ] 6340608 / 20515344\r", + " 30% [...................... ] 6348800 / 20515344\r", + " 30% [...................... ] 6356992 / 20515344\r", + " 31% [...................... ] 6365184 / 20515344\r", + " 31% [...................... ] 6373376 / 20515344\r", + " 31% [...................... ] 6381568 / 20515344\r", + " 31% [...................... ] 6389760 / 20515344\r", + " 31% [...................... ] 6397952 / 20515344\r", + " 31% [...................... ] 6406144 / 20515344\r", + " 31% [...................... ] 6414336 / 20515344\r", + " 31% [...................... ] 6422528 / 20515344\r", + " 31% [...................... ] 6430720 / 20515344\r", + " 31% [...................... ] 6438912 / 20515344\r", + " 31% [...................... ] 6447104 / 20515344\r", + " 31% [...................... ] 6455296 / 20515344\r", + " 31% [...................... ] 6463488 / 20515344\r", + " 31% [...................... ] 6471680 / 20515344\r", + " 31% [...................... ] 6479872 / 20515344\r", + " 31% [...................... ] 6488064 / 20515344\r", + " 31% [...................... ] 6496256 / 20515344\r", + " 31% [...................... ] 6504448 / 20515344\r", + " 31% [...................... ] 6512640 / 20515344\r", + " 31% [...................... ] 6520832 / 20515344\r", + " 31% [...................... ] 6529024 / 20515344\r", + " 31% [...................... ] 6537216 / 20515344\r", + " 31% [...................... ] 6545408 / 20515344\r", + " 31% [....................... ] 6553600 / 20515344\r", + " 31% [....................... ] 6561792 / 20515344\r", + " 32% [....................... ] 6569984 / 20515344\r", + " 32% [....................... ] 6578176 / 20515344\r", + " 32% [....................... ] 6586368 / 20515344\r", + " 32% [....................... ] 6594560 / 20515344\r", + " 32% [....................... ] 6602752 / 20515344\r", + " 32% [....................... ] 6610944 / 20515344\r", + " 32% [....................... ] 6619136 / 20515344\r", + " 32% [....................... ] 6627328 / 20515344\r", + " 32% [....................... ] 6635520 / 20515344\r", + " 32% [....................... ] 6643712 / 20515344\r", + " 32% [....................... ] 6651904 / 20515344\r", + " 32% [....................... ] 6660096 / 20515344\r", + " 32% [....................... ] 6668288 / 20515344\r", + " 32% [....................... ] 6676480 / 20515344\r", + " 32% [....................... ] 6684672 / 20515344\r", + " 32% [....................... ] 6692864 / 20515344\r", + " 32% [....................... ] 6701056 / 20515344\r", + " 32% [....................... ] 6709248 / 20515344\r", + " 32% [....................... ] 6717440 / 20515344\r", + " 32% [....................... ] 6725632 / 20515344\r", + " 32% [....................... ] 6733824 / 20515344\r", + " 32% [....................... ] 6742016 / 20515344\r", + " 32% [....................... ] 6750208 / 20515344\r", + " 32% [....................... ] 6758400 / 20515344\r", + " 32% [....................... ] 6766592 / 20515344\r", + " 33% [....................... ] 6774784 / 20515344\r", + " 33% [....................... ] 6782976 / 20515344\r", + " 33% [....................... ] 6791168 / 20515344\r", + " 33% [....................... ] 6799360 / 20515344\r", + " 33% [....................... ] 6807552 / 20515344\r", + " 33% [....................... ] 6815744 / 20515344\r", + " 33% [....................... ] 6823936 / 20515344\r", + " 33% [....................... ] 6832128 / 20515344\r", + " 33% [........................ ] 6840320 / 20515344\r", + " 33% [........................ ] 6848512 / 20515344\r", + " 33% [........................ ] 6856704 / 20515344\r", + " 33% [........................ ] 6864896 / 20515344\r", + " 33% [........................ ] 6873088 / 20515344\r", + " 33% [........................ ] 6881280 / 20515344\r", + " 33% [........................ ] 6889472 / 20515344\r", + " 33% [........................ ] 6897664 / 20515344\r", + " 33% [........................ ] 6905856 / 20515344\r", + " 33% [........................ ] 6914048 / 20515344\r", + " 33% [........................ ] 6922240 / 20515344\r", + " 33% [........................ ] 6930432 / 20515344\r", + " 33% [........................ ] 6938624 / 20515344\r", + " 33% [........................ ] 6946816 / 20515344\r", + " 33% [........................ ] 6955008 / 20515344\r", + " 33% [........................ ] 6963200 / 20515344\r", + " 33% [........................ ] 6971392 / 20515344\r", + " 34% [........................ ] 6979584 / 20515344\r", + " 34% [........................ ] 6987776 / 20515344\r", + " 34% [........................ ] 6995968 / 20515344\r", + " 34% [........................ ] 7004160 / 20515344\r", + " 34% [........................ ] 7012352 / 20515344\r", + " 34% [........................ ] 7020544 / 20515344\r", + " 34% [........................ ] 7028736 / 20515344\r", + " 34% [........................ ] 7036928 / 20515344\r", + " 34% [........................ ] 7045120 / 20515344\r", + " 34% [........................ ] 7053312 / 20515344\r", + " 34% [........................ ] 7061504 / 20515344\r", + " 34% [........................ ] 7069696 / 20515344\r", + " 34% [........................ ] 7077888 / 20515344\r", + " 34% [........................ ] 7086080 / 20515344\r", + " 34% [........................ ] 7094272 / 20515344\r", + " 34% [........................ ] 7102464 / 20515344\r", + " 34% [........................ ] 7110656 / 20515344\r", + " 34% [........................ ] 7118848 / 20515344\r", + " 34% [......................... ] 7127040 / 20515344\r", + " 34% [......................... ] 7135232 / 20515344\r", + " 34% [......................... ] 7143424 / 20515344\r", + " 34% [......................... ] 7151616 / 20515344\r", + " 34% [......................... ] 7159808 / 20515344\r", + " 34% [......................... ] 7168000 / 20515344\r", + " 34% [......................... ] 7176192 / 20515344\r", + " 35% [......................... ] 7184384 / 20515344\r", + " 35% [......................... ] 7192576 / 20515344\r", + " 35% [......................... ] 7200768 / 20515344\r", + " 35% [......................... ] 7208960 / 20515344\r", + " 35% [......................... ] 7217152 / 20515344\r", + " 35% [......................... ] 7225344 / 20515344\r", + " 35% [......................... ] 7233536 / 20515344\r", + " 35% [......................... ] 7241728 / 20515344\r", + " 35% [......................... ] 7249920 / 20515344\r", + " 35% [......................... ] 7258112 / 20515344\r", + " 35% [......................... ] 7266304 / 20515344\r", + " 35% [......................... ] 7274496 / 20515344\r", + " 35% [......................... ] 7282688 / 20515344\r", + " 35% [......................... ] 7290880 / 20515344\r", + " 35% [......................... ] 7299072 / 20515344\r", + " 35% [......................... ] 7307264 / 20515344\r", + " 35% [......................... ] 7315456 / 20515344\r", + " 35% [......................... ] 7323648 / 20515344\r", + " 35% [......................... ] 7331840 / 20515344\r", + " 35% [......................... ] 7340032 / 20515344\r", + " 35% [......................... ] 7348224 / 20515344\r", + " 35% [......................... ] 7356416 / 20515344\r", + " 35% [......................... ] 7364608 / 20515344\r", + " 35% [......................... ] 7372800 / 20515344\r", + " 35% [......................... ] 7380992 / 20515344\r", + " 36% [......................... ] 7389184 / 20515344\r", + " 36% [......................... ] 7397376 / 20515344\r", + " 36% [......................... ] 7405568 / 20515344\r", + " 36% [.......................... ] 7413760 / 20515344\r", + " 36% [.......................... ] 7421952 / 20515344\r", + " 36% [.......................... ] 7430144 / 20515344\r", + " 36% [.......................... ] 7438336 / 20515344\r", + " 36% [.......................... ] 7446528 / 20515344\r", + " 36% [.......................... ] 7454720 / 20515344\r", + " 36% [.......................... ] 7462912 / 20515344\r", + " 36% [.......................... ] 7471104 / 20515344\r", + " 36% [.......................... ] 7479296 / 20515344\r", + " 36% [.......................... ] 7487488 / 20515344\r", + " 36% [.......................... ] 7495680 / 20515344\r", + " 36% [.......................... ] 7503872 / 20515344\r", + " 36% [.......................... ] 7512064 / 20515344\r", + " 36% [.......................... ] 7520256 / 20515344\r", + " 36% [.......................... ] 7528448 / 20515344\r", + " 36% [.......................... ] 7536640 / 20515344\r", + " 36% [.......................... ] 7544832 / 20515344\r", + " 36% [.......................... ] 7553024 / 20515344\r", + " 36% [.......................... ] 7561216 / 20515344\r", + " 36% [.......................... ] 7569408 / 20515344\r", + " 36% [.......................... ] 7577600 / 20515344\r", + " 36% [.......................... ] 7585792 / 20515344\r", + " 37% [.......................... ] 7593984 / 20515344\r", + " 37% [.......................... ] 7602176 / 20515344\r", + " 37% [.......................... ] 7610368 / 20515344\r", + " 37% [.......................... ] 7618560 / 20515344\r", + " 37% [.......................... ] 7626752 / 20515344\r", + " 37% [.......................... ] 7634944 / 20515344\r", + " 37% [.......................... ] 7643136 / 20515344\r", + " 37% [.......................... ] 7651328 / 20515344\r", + " 37% [.......................... ] 7659520 / 20515344\r", + " 37% [.......................... ] 7667712 / 20515344\r", + " 37% [.......................... ] 7675904 / 20515344\r", + " 37% [.......................... ] 7684096 / 20515344\r", + " 37% [.......................... ] 7692288 / 20515344\r", + " 37% [........................... ] 7700480 / 20515344\r", + " 37% [........................... ] 7708672 / 20515344\r", + " 37% [........................... ] 7716864 / 20515344\r", + " 37% [........................... ] 7725056 / 20515344\r", + " 37% [........................... ] 7733248 / 20515344\r", + " 37% [........................... ] 7741440 / 20515344\r", + " 37% [........................... ] 7749632 / 20515344\r", + " 37% [........................... ] 7757824 / 20515344\r", + " 37% [........................... ] 7766016 / 20515344\r", + " 37% [........................... ] 7774208 / 20515344\r", + " 37% [........................... ] 7782400 / 20515344\r", + " 37% [........................... ] 7790592 / 20515344\r", + " 38% [........................... ] 7798784 / 20515344\r", + " 38% [........................... ] 7806976 / 20515344\r", + " 38% [........................... ] 7815168 / 20515344\r", + " 38% [........................... ] 7823360 / 20515344\r", + " 38% [........................... ] 7831552 / 20515344\r", + " 38% [........................... ] 7839744 / 20515344\r", + " 38% [........................... ] 7847936 / 20515344\r", + " 38% [........................... ] 7856128 / 20515344\r", + " 38% [........................... ] 7864320 / 20515344\r", + " 38% [........................... ] 7872512 / 20515344\r", + " 38% [........................... ] 7880704 / 20515344\r", + " 38% [........................... ] 7888896 / 20515344\r", + " 38% [........................... ] 7897088 / 20515344\r", + " 38% [........................... ] 7905280 / 20515344\r", + " 38% [........................... ] 7913472 / 20515344\r", + " 38% [........................... ] 7921664 / 20515344\r", + " 38% [........................... ] 7929856 / 20515344\r", + " 38% [........................... ] 7938048 / 20515344\r", + " 38% [........................... ] 7946240 / 20515344\r", + " 38% [........................... ] 7954432 / 20515344\r", + " 38% [........................... ] 7962624 / 20515344\r", + " 38% [........................... ] 7970816 / 20515344\r", + " 38% [............................ ] 7979008 / 20515344\r", + " 38% [............................ ] 7987200 / 20515344\r", + " 38% [............................ ] 7995392 / 20515344\r", + " 39% [............................ ] 8003584 / 20515344\r", + " 39% [............................ ] 8011776 / 20515344\r", + " 39% [............................ ] 8019968 / 20515344\r", + " 39% [............................ ] 8028160 / 20515344\r", + " 39% [............................ ] 8036352 / 20515344\r", + " 39% [............................ ] 8044544 / 20515344\r", + " 39% [............................ ] 8052736 / 20515344\r", + " 39% [............................ ] 8060928 / 20515344\r", + " 39% [............................ ] 8069120 / 20515344\r", + " 39% [............................ ] 8077312 / 20515344\r", + " 39% [............................ ] 8085504 / 20515344\r", + " 39% [............................ ] 8093696 / 20515344\r", + " 39% [............................ ] 8101888 / 20515344\r", + " 39% [............................ ] 8110080 / 20515344\r", + " 39% [............................ ] 8118272 / 20515344\r", + " 39% [............................ ] 8126464 / 20515344\r", + " 39% [............................ ] 8134656 / 20515344\r", + " 39% [............................ ] 8142848 / 20515344\r", + " 39% [............................ ] 8151040 / 20515344\r", + " 39% [............................ ] 8159232 / 20515344\r", + " 39% [............................ ] 8167424 / 20515344\r", + " 39% [............................ ] 8175616 / 20515344\r", + " 39% [............................ ] 8183808 / 20515344\r", + " 39% [............................ ] 8192000 / 20515344\r", + " 39% [............................ ] 8200192 / 20515344\r", + " 40% [............................ ] 8208384 / 20515344\r", + " 40% [............................ ] 8216576 / 20515344\r", + " 40% [............................ ] 8224768 / 20515344\r", + " 40% [............................ ] 8232960 / 20515344\r", + " 40% [............................ ] 8241152 / 20515344\r", + " 40% [............................ ] 8249344 / 20515344\r", + " 40% [............................ ] 8257536 / 20515344\r", + " 40% [............................. ] 8265728 / 20515344\r", + " 40% [............................. ] 8273920 / 20515344\r", + " 40% [............................. ] 8282112 / 20515344\r", + " 40% [............................. ] 8290304 / 20515344\r", + " 40% [............................. ] 8298496 / 20515344\r", + " 40% [............................. ] 8306688 / 20515344\r", + " 40% [............................. ] 8314880 / 20515344\r", + " 40% [............................. ] 8323072 / 20515344\r", + " 40% [............................. ] 8331264 / 20515344\r", + " 40% [............................. ] 8339456 / 20515344\r", + " 40% [............................. ] 8347648 / 20515344\r", + " 40% [............................. ] 8355840 / 20515344\r", + " 40% [............................. ] 8364032 / 20515344\r", + " 40% [............................. ] 8372224 / 20515344\r", + " 40% [............................. ] 8380416 / 20515344\r", + " 40% [............................. ] 8388608 / 20515344\r", + " 40% [............................. ] 8396800 / 20515344\r", + " 40% [............................. ] 8404992 / 20515344\r", + " 41% [............................. ] 8413184 / 20515344\r", + " 41% [............................. ] 8421376 / 20515344\r", + " 41% [............................. ] 8429568 / 20515344\r", + " 41% [............................. ] 8437760 / 20515344\r", + " 41% [............................. ] 8445952 / 20515344\r", + " 41% [............................. ] 8454144 / 20515344\r", + " 41% [............................. ] 8462336 / 20515344\r", + " 41% [............................. ] 8470528 / 20515344\r", + " 41% [............................. ] 8478720 / 20515344\r", + " 41% [............................. ] 8486912 / 20515344\r", + " 41% [............................. ] 8495104 / 20515344\r", + " 41% [............................. ] 8503296 / 20515344\r", + " 41% [............................. ] 8511488 / 20515344\r", + " 41% [............................. ] 8519680 / 20515344\r", + " 41% [............................. ] 8527872 / 20515344\r", + " 41% [............................. ] 8536064 / 20515344\r", + " 41% [............................. ] 8544256 / 20515344\r", + " 41% [.............................. ] 8552448 / 20515344\r", + " 41% [.............................. ] 8560640 / 20515344\r", + " 41% [.............................. ] 8568832 / 20515344\r", + " 41% [.............................. ] 8577024 / 20515344\r", + " 41% [.............................. ] 8585216 / 20515344\r", + " 41% [.............................. ] 8593408 / 20515344\r", + " 41% [.............................. ] 8601600 / 20515344\r", + " 41% [.............................. ] 8609792 / 20515344\r", + " 42% [.............................. ] 8617984 / 20515344\r", + " 42% [.............................. ] 8626176 / 20515344\r", + " 42% [.............................. ] 8634368 / 20515344\r", + " 42% [.............................. ] 8642560 / 20515344\r", + " 42% [.............................. ] 8650752 / 20515344\r", + " 42% [.............................. ] 8658944 / 20515344\r", + " 42% [.............................. ] 8667136 / 20515344\r", + " 42% [.............................. ] 8675328 / 20515344\r", + " 42% [.............................. ] 8683520 / 20515344\r", + " 42% [.............................. ] 8691712 / 20515344\r", + " 42% [.............................. ] 8699904 / 20515344\r", + " 42% [.............................. ] 8708096 / 20515344\r", + " 42% [.............................. ] 8716288 / 20515344\r", + " 42% [.............................. ] 8724480 / 20515344\r", + " 42% [.............................. ] 8732672 / 20515344\r", + " 42% [.............................. ] 8740864 / 20515344\r", + " 42% [.............................. ] 8749056 / 20515344\r", + " 42% [.............................. ] 8757248 / 20515344\r", + " 42% [.............................. ] 8765440 / 20515344\r", + " 42% [.............................. ] 8773632 / 20515344\r", + " 42% [.............................. ] 8781824 / 20515344\r", + " 42% [.............................. ] 8790016 / 20515344\r", + " 42% [.............................. ] 8798208 / 20515344\r", + " 42% [.............................. ] 8806400 / 20515344\r", + " 42% [.............................. ] 8814592 / 20515344\r", + " 43% [.............................. ] 8822784 / 20515344\r", + " 43% [.............................. ] 8830976 / 20515344\r", + " 43% [............................... ] 8839168 / 20515344\r", + " 43% [............................... ] 8847360 / 20515344\r", + " 43% [............................... ] 8855552 / 20515344\r", + " 43% [............................... ] 8863744 / 20515344\r", + " 43% [............................... ] 8871936 / 20515344\r", + " 43% [............................... ] 8880128 / 20515344\r", + " 43% [............................... ] 8888320 / 20515344\r", + " 43% [............................... ] 8896512 / 20515344\r", + " 43% [............................... ] 8904704 / 20515344\r", + " 43% [............................... ] 8912896 / 20515344\r", + " 43% [............................... ] 8921088 / 20515344\r", + " 43% [............................... ] 8929280 / 20515344\r", + " 43% [............................... ] 8937472 / 20515344\r", + " 43% [............................... ] 8945664 / 20515344\r", + " 43% [............................... ] 8953856 / 20515344\r", + " 43% [............................... ] 8962048 / 20515344\r", + " 43% [............................... ] 8970240 / 20515344\r", + " 43% [............................... ] 8978432 / 20515344\r", + " 43% [............................... ] 8986624 / 20515344\r", + " 43% [............................... ] 8994816 / 20515344\r", + " 43% [............................... ] 9003008 / 20515344\r", + " 43% [............................... ] 9011200 / 20515344\r", + " 43% [............................... ] 9019392 / 20515344\r", + " 44% [............................... ] 9027584 / 20515344\r", + " 44% [............................... ] 9035776 / 20515344\r", + " 44% [............................... ] 9043968 / 20515344\r", + " 44% [............................... ] 9052160 / 20515344\r", + " 44% [............................... ] 9060352 / 20515344\r", + " 44% [............................... ] 9068544 / 20515344\r", + " 44% [............................... ] 9076736 / 20515344\r", + " 44% [............................... ] 9084928 / 20515344\r", + " 44% [............................... ] 9093120 / 20515344\r", + " 44% [............................... ] 9101312 / 20515344\r", + " 44% [............................... ] 9109504 / 20515344\r", + " 44% [............................... ] 9117696 / 20515344\r", + " 44% [................................ ] 9125888 / 20515344\r", + " 44% [................................ ] 9134080 / 20515344\r", + " 44% [................................ ] 9142272 / 20515344\r", + " 44% [................................ ] 9150464 / 20515344\r", + " 44% [................................ ] 9158656 / 20515344\r", + " 44% [................................ ] 9166848 / 20515344\r", + " 44% [................................ ] 9175040 / 20515344\r", + " 44% [................................ ] 9183232 / 20515344\r", + " 44% [................................ ] 9191424 / 20515344\r", + " 44% [................................ ] 9199616 / 20515344\r", + " 44% [................................ ] 9207808 / 20515344\r", + " 44% [................................ ] 9216000 / 20515344\r", + " 44% [................................ ] 9224192 / 20515344\r", + " 45% [................................ ] 9232384 / 20515344\r", + " 45% [................................ ] 9240576 / 20515344\r", + " 45% [................................ ] 9248768 / 20515344\r", + " 45% [................................ ] 9256960 / 20515344\r", + " 45% [................................ ] 9265152 / 20515344\r", + " 45% [................................ ] 9273344 / 20515344\r", + " 45% [................................ ] 9281536 / 20515344\r", + " 45% [................................ ] 9289728 / 20515344\r", + " 45% [................................ ] 9297920 / 20515344\r", + " 45% [................................ ] 9306112 / 20515344\r", + " 45% [................................ ] 9314304 / 20515344\r", + " 45% [................................ ] 9322496 / 20515344\r", + " 45% [................................ ] 9330688 / 20515344\r", + " 45% [................................ ] 9338880 / 20515344\r", + " 45% [................................ ] 9347072 / 20515344\r", + " 45% [................................ ] 9355264 / 20515344\r", + " 45% [................................ ] 9363456 / 20515344\r", + " 45% [................................ ] 9371648 / 20515344\r", + " 45% [................................ ] 9379840 / 20515344\r", + " 45% [................................ ] 9388032 / 20515344\r", + " 45% [................................ ] 9396224 / 20515344\r", + " 45% [................................. ] 9404416 / 20515344\r", + " 45% [................................. ] 9412608 / 20515344\r", + " 45% [................................. ] 9420800 / 20515344\r", + " 45% [................................. ] 9428992 / 20515344\r", + " 46% [................................. ] 9437184 / 20515344\r", + " 46% [................................. ] 9445376 / 20515344\r", + " 46% [................................. ] 9453568 / 20515344\r", + " 46% [................................. ] 9461760 / 20515344\r", + " 46% [................................. ] 9469952 / 20515344\r", + " 46% [................................. ] 9478144 / 20515344\r", + " 46% [................................. ] 9486336 / 20515344\r", + " 46% [................................. ] 9494528 / 20515344\r", + " 46% [................................. ] 9502720 / 20515344\r", + " 46% [................................. ] 9510912 / 20515344\r", + " 46% [................................. ] 9519104 / 20515344\r", + " 46% [................................. ] 9527296 / 20515344\r", + " 46% [................................. ] 9535488 / 20515344\r", + " 46% [................................. ] 9543680 / 20515344\r", + " 46% [................................. ] 9551872 / 20515344\r", + " 46% [................................. ] 9560064 / 20515344\r", + " 46% [................................. ] 9568256 / 20515344\r", + " 46% [................................. ] 9576448 / 20515344\r", + " 46% [................................. ] 9584640 / 20515344\r", + " 46% [................................. ] 9592832 / 20515344\r", + " 46% [................................. ] 9601024 / 20515344\r", + " 46% [................................. ] 9609216 / 20515344\r", + " 46% [................................. ] 9617408 / 20515344\r", + " 46% [................................. ] 9625600 / 20515344\r", + " 46% [................................. ] 9633792 / 20515344\r", + " 46% [................................. ] 9641984 / 20515344\r", + " 47% [................................. ] 9650176 / 20515344\r", + " 47% [................................. ] 9658368 / 20515344\r", + " 47% [................................. ] 9666560 / 20515344\r", + " 47% [................................. ] 9674752 / 20515344\r", + " 47% [................................. ] 9682944 / 20515344\r", + " 47% [.................................. ] 9691136 / 20515344\r", + " 47% [.................................. ] 9699328 / 20515344\r", + " 47% [.................................. ] 9707520 / 20515344\r", + " 47% [.................................. ] 9715712 / 20515344\r", + " 47% [.................................. ] 9723904 / 20515344\r", + " 47% [.................................. ] 9732096 / 20515344\r", + " 47% [.................................. ] 9740288 / 20515344\r", + " 47% [.................................. ] 9748480 / 20515344\r", + " 47% [.................................. ] 9756672 / 20515344\r", + " 47% [.................................. ] 9764864 / 20515344\r", + " 47% [.................................. ] 9773056 / 20515344\r", + " 47% [.................................. ] 9781248 / 20515344\r", + " 47% [.................................. ] 9789440 / 20515344\r", + " 47% [.................................. ] 9797632 / 20515344\r", + " 47% [.................................. ] 9805824 / 20515344\r", + " 47% [.................................. ] 9814016 / 20515344\r", + " 47% [.................................. ] 9822208 / 20515344\r", + " 47% [.................................. ] 9830400 / 20515344\r", + " 47% [.................................. ] 9838592 / 20515344\r", + " 47% [.................................. ] 9846784 / 20515344\r", + " 48% [.................................. ] 9854976 / 20515344\r", + " 48% [.................................. ] 9863168 / 20515344\r", + " 48% [.................................. ] 9871360 / 20515344\r", + " 48% [.................................. ] 9879552 / 20515344\r", + " 48% [.................................. ] 9887744 / 20515344\r", + " 48% [.................................. ] 9895936 / 20515344\r", + " 48% [.................................. ] 9904128 / 20515344\r", + " 48% [.................................. ] 9912320 / 20515344\r", + " 48% [.................................. ] 9920512 / 20515344\r", + " 48% [.................................. ] 9928704 / 20515344\r", + " 48% [.................................. ] 9936896 / 20515344\r", + " 48% [.................................. ] 9945088 / 20515344\r", + " 48% [.................................. ] 9953280 / 20515344\r", + " 48% [.................................. ] 9961472 / 20515344\r", + " 48% [.................................. ] 9969664 / 20515344\r", + " 48% [................................... ] 9977856 / 20515344\r", + " 48% [................................... ] 9986048 / 20515344\r", + " 48% [................................... ] 9994240 / 20515344\r", + " 48% [................................... ] 10002432 / 20515344\r", + " 48% [................................... ] 10010624 / 20515344\r", + " 48% [................................... ] 10018816 / 20515344\r", + " 48% [................................... ] 10027008 / 20515344\r", + " 48% [................................... ] 10035200 / 20515344\r", + " 48% [................................... ] 10043392 / 20515344\r", + " 48% [................................... ] 10051584 / 20515344\r", + " 49% [................................... ] 10059776 / 20515344\r", + " 49% [................................... ] 10067968 / 20515344\r", + " 49% [................................... ] 10076160 / 20515344\r", + " 49% [................................... ] 10084352 / 20515344\r", + " 49% [................................... ] 10092544 / 20515344\r", + " 49% [................................... ] 10100736 / 20515344\r", + " 49% [................................... ] 10108928 / 20515344\r", + " 49% [................................... ] 10117120 / 20515344\r", + " 49% [................................... ] 10125312 / 20515344\r", + " 49% [................................... ] 10133504 / 20515344\r", + " 49% [................................... ] 10141696 / 20515344\r", + " 49% [................................... ] 10149888 / 20515344\r", + " 49% [................................... ] 10158080 / 20515344\r", + " 49% [................................... ] 10166272 / 20515344\r", + " 49% [................................... ] 10174464 / 20515344\r", + " 49% [................................... ] 10182656 / 20515344\r", + " 49% [................................... ] 10190848 / 20515344\r", + " 49% [................................... ] 10199040 / 20515344\r", + " 49% [................................... ] 10207232 / 20515344\r", + " 49% [................................... ] 10215424 / 20515344\r", + " 49% [................................... ] 10223616 / 20515344\r", + " 49% [................................... ] 10231808 / 20515344\r", + " 49% [................................... ] 10240000 / 20515344\r", + " 49% [................................... ] 10248192 / 20515344\r", + " 49% [................................... ] 10256384 / 20515344\r", + " 50% [.................................... ] 10264576 / 20515344\r", + " 50% [.................................... ] 10272768 / 20515344\r", + " 50% [.................................... ] 10280960 / 20515344\r", + " 50% [.................................... ] 10289152 / 20515344\r", + " 50% [.................................... ] 10297344 / 20515344\r", + " 50% [.................................... ] 10305536 / 20515344\r", + " 50% [.................................... ] 10313728 / 20515344\r", + " 50% [.................................... ] 10321920 / 20515344\r", + " 50% [.................................... ] 10330112 / 20515344\r", + " 50% [.................................... ] 10338304 / 20515344\r", + " 50% [.................................... ] 10346496 / 20515344\r", + " 50% [.................................... ] 10354688 / 20515344\r", + " 50% [.................................... ] 10362880 / 20515344\r", + " 50% [.................................... ] 10371072 / 20515344\r", + " 50% [.................................... ] 10379264 / 20515344\r", + " 50% [.................................... ] 10387456 / 20515344\r", + " 50% [.................................... ] 10395648 / 20515344\r", + " 50% [.................................... ] 10403840 / 20515344\r", + " 50% [.................................... ] 10412032 / 20515344\r", + " 50% [.................................... ] 10420224 / 20515344\r", + " 50% [.................................... ] 10428416 / 20515344\r", + " 50% [.................................... ] 10436608 / 20515344\r", + " 50% [.................................... ] 10444800 / 20515344\r", + " 50% [.................................... ] 10452992 / 20515344\r", + " 50% [.................................... ] 10461184 / 20515344\r", + " 51% [.................................... ] 10469376 / 20515344\r", + " 51% [.................................... ] 10477568 / 20515344\r", + " 51% [.................................... ] 10485760 / 20515344\r", + " 51% [.................................... ] 10493952 / 20515344\r", + " 51% [.................................... ] 10502144 / 20515344\r", + " 51% [.................................... ] 10510336 / 20515344\r", + " 51% [.................................... ] 10518528 / 20515344\r", + " 51% [.................................... ] 10526720 / 20515344\r", + " 51% [.................................... ] 10534912 / 20515344\r", + " 51% [..................................... ] 10543104 / 20515344\r", + " 51% [..................................... ] 10551296 / 20515344\r", + " 51% [..................................... ] 10559488 / 20515344\r", + " 51% [..................................... ] 10567680 / 20515344\r", + " 51% [..................................... ] 10575872 / 20515344\r", + " 51% [..................................... ] 10584064 / 20515344\r", + " 51% [..................................... ] 10592256 / 20515344\r", + " 51% [..................................... ] 10600448 / 20515344\r", + " 51% [..................................... ] 10608640 / 20515344\r", + " 51% [..................................... ] 10616832 / 20515344\r", + " 51% [..................................... ] 10625024 / 20515344\r", + " 51% [..................................... ] 10633216 / 20515344\r", + " 51% [..................................... ] 10641408 / 20515344\r", + " 51% [..................................... ] 10649600 / 20515344\r", + " 51% [..................................... ] 10657792 / 20515344\r", + " 51% [..................................... ] 10665984 / 20515344\r", + " 52% [..................................... ] 10674176 / 20515344\r", + " 52% [..................................... ] 10682368 / 20515344\r", + " 52% [..................................... ] 10690560 / 20515344\r", + " 52% [..................................... ] 10698752 / 20515344\r", + " 52% [..................................... ] 10706944 / 20515344\r", + " 52% [..................................... ] 10715136 / 20515344\r", + " 52% [..................................... ] 10723328 / 20515344\r", + " 52% [..................................... ] 10731520 / 20515344\r", + " 52% [..................................... ] 10739712 / 20515344\r", + " 52% [..................................... ] 10747904 / 20515344\r", + " 52% [..................................... ] 10756096 / 20515344\r", + " 52% [..................................... ] 10764288 / 20515344\r", + " 52% [..................................... ] 10772480 / 20515344\r", + " 52% [..................................... ] 10780672 / 20515344\r", + " 52% [..................................... ] 10788864 / 20515344\r", + " 52% [..................................... ] 10797056 / 20515344\r", + " 52% [..................................... ] 10805248 / 20515344\r", + " 52% [..................................... ] 10813440 / 20515344\r", + " 52% [..................................... ] 10821632 / 20515344\r", + " 52% [...................................... ] 10829824 / 20515344\r", + " 52% [...................................... ] 10838016 / 20515344\r", + " 52% [...................................... ] 10846208 / 20515344\r", + " 52% [...................................... ] 10854400 / 20515344\r", + " 52% [...................................... ] 10862592 / 20515344\r", + " 52% [...................................... ] 10870784 / 20515344\r", + " 53% [...................................... ] 10878976 / 20515344\r", + " 53% [...................................... ] 10887168 / 20515344\r", + " 53% [...................................... ] 10895360 / 20515344\r", + " 53% [...................................... ] 10903552 / 20515344\r", + " 53% [...................................... ] 10911744 / 20515344\r", + " 53% [...................................... ] 10919936 / 20515344\r", + " 53% [...................................... ] 10928128 / 20515344\r", + " 53% [...................................... ] 10936320 / 20515344\r", + " 53% [...................................... ] 10944512 / 20515344\r", + " 53% [...................................... ] 10952704 / 20515344\r", + " 53% [...................................... ] 10960896 / 20515344\r", + " 53% [...................................... ] 10969088 / 20515344\r", + " 53% [...................................... ] 10977280 / 20515344\r", + " 53% [...................................... ] 10985472 / 20515344\r", + " 53% [...................................... ] 10993664 / 20515344\r", + " 53% [...................................... ] 11001856 / 20515344\r", + " 53% [...................................... ] 11010048 / 20515344\r", + " 53% [...................................... ] 11018240 / 20515344\r", + " 53% [...................................... ] 11026432 / 20515344\r", + " 53% [...................................... ] 11034624 / 20515344\r", + " 53% [...................................... ] 11042816 / 20515344\r", + " 53% [...................................... ] 11051008 / 20515344\r", + " 53% [...................................... ] 11059200 / 20515344\r", + " 53% [...................................... ] 11067392 / 20515344\r", + " 53% [...................................... ] 11075584 / 20515344\r", + " 54% [...................................... ] 11083776 / 20515344\r", + " 54% [...................................... ] 11091968 / 20515344\r", + " 54% [...................................... ] 11100160 / 20515344\r", + " 54% [...................................... ] 11108352 / 20515344\r", + " 54% [....................................... ] 11116544 / 20515344\r", + " 54% [....................................... ] 11124736 / 20515344\r", + " 54% [....................................... ] 11132928 / 20515344\r", + " 54% [....................................... ] 11141120 / 20515344\r", + " 54% [....................................... ] 11149312 / 20515344\r", + " 54% [....................................... ] 11157504 / 20515344\r", + " 54% [....................................... ] 11165696 / 20515344\r", + " 54% [....................................... ] 11173888 / 20515344\r", + " 54% [....................................... ] 11182080 / 20515344\r", + " 54% [....................................... ] 11190272 / 20515344\r", + " 54% [....................................... ] 11198464 / 20515344\r", + " 54% [....................................... ] 11206656 / 20515344\r", + " 54% [....................................... ] 11214848 / 20515344\r", + " 54% [....................................... ] 11223040 / 20515344\r", + " 54% [....................................... ] 11231232 / 20515344\r", + " 54% [....................................... ] 11239424 / 20515344\r", + " 54% [....................................... ] 11247616 / 20515344\r", + " 54% [....................................... ] 11255808 / 20515344\r", + " 54% [....................................... ] 11264000 / 20515344\r", + " 54% [....................................... ] 11272192 / 20515344\r", + " 54% [....................................... ] 11280384 / 20515344\r", + " 55% [....................................... ] 11288576 / 20515344\r", + " 55% [....................................... ] 11296768 / 20515344\r", + " 55% [....................................... ] 11304960 / 20515344\r", + " 55% [....................................... ] 11313152 / 20515344\r", + " 55% [....................................... ] 11321344 / 20515344\r", + " 55% [....................................... ] 11329536 / 20515344\r", + " 55% [....................................... ] 11337728 / 20515344\r", + " 55% [....................................... ] 11345920 / 20515344\r", + " 55% [....................................... ] 11354112 / 20515344\r", + " 55% [....................................... ] 11362304 / 20515344\r", + " 55% [....................................... ] 11370496 / 20515344\r", + " 55% [....................................... ] 11378688 / 20515344\r", + " 55% [....................................... ] 11386880 / 20515344\r", + " 55% [....................................... ] 11395072 / 20515344\r", + " 55% [........................................ ] 11403264 / 20515344\r", + " 55% [........................................ ] 11411456 / 20515344\r", + " 55% [........................................ ] 11419648 / 20515344\r", + " 55% [........................................ ] 11427840 / 20515344\r", + " 55% [........................................ ] 11436032 / 20515344\r", + " 55% [........................................ ] 11444224 / 20515344\r", + " 55% [........................................ ] 11452416 / 20515344\r", + " 55% [........................................ ] 11460608 / 20515344\r", + " 55% [........................................ ] 11468800 / 20515344\r", + " 55% [........................................ ] 11476992 / 20515344\r", + " 55% [........................................ ] 11485184 / 20515344\r", + " 56% [........................................ ] 11493376 / 20515344\r", + " 56% [........................................ ] 11501568 / 20515344\r", + " 56% [........................................ ] 11509760 / 20515344\r", + " 56% [........................................ ] 11517952 / 20515344\r", + " 56% [........................................ ] 11526144 / 20515344\r", + " 56% [........................................ ] 11534336 / 20515344\r", + " 56% [........................................ ] 11542528 / 20515344\r", + " 56% [........................................ ] 11550720 / 20515344\r", + " 56% [........................................ ] 11558912 / 20515344\r", + " 56% [........................................ ] 11567104 / 20515344\r", + " 56% [........................................ ] 11575296 / 20515344\r", + " 56% [........................................ ] 11583488 / 20515344\r", + " 56% [........................................ ] 11591680 / 20515344\r", + " 56% [........................................ ] 11599872 / 20515344\r", + " 56% [........................................ ] 11608064 / 20515344\r", + " 56% [........................................ ] 11616256 / 20515344\r", + " 56% [........................................ ] 11624448 / 20515344\r", + " 56% [........................................ ] 11632640 / 20515344\r", + " 56% [........................................ ] 11640832 / 20515344\r", + " 56% [........................................ ] 11649024 / 20515344\r", + " 56% [........................................ ] 11657216 / 20515344\r", + " 56% [........................................ ] 11665408 / 20515344\r", + " 56% [........................................ ] 11673600 / 20515344\r", + " 56% [........................................ ] 11681792 / 20515344\r", + " 56% [......................................... ] 11689984 / 20515344\r", + " 57% [......................................... ] 11698176 / 20515344\r", + " 57% [......................................... ] 11706368 / 20515344\r", + " 57% [......................................... ] 11714560 / 20515344\r", + " 57% [......................................... ] 11722752 / 20515344\r", + " 57% [......................................... ] 11730944 / 20515344\r", + " 57% [......................................... ] 11739136 / 20515344\r", + " 57% [......................................... ] 11747328 / 20515344\r", + " 57% [......................................... ] 11755520 / 20515344\r", + " 57% [......................................... ] 11763712 / 20515344\r", + " 57% [......................................... ] 11771904 / 20515344\r", + " 57% [......................................... ] 11780096 / 20515344\r", + " 57% [......................................... ] 11788288 / 20515344\r", + " 57% [......................................... ] 11796480 / 20515344\r", + " 57% [......................................... ] 11804672 / 20515344\r", + " 57% [......................................... ] 11812864 / 20515344\r", + " 57% [......................................... ] 11821056 / 20515344\r", + " 57% [......................................... ] 11829248 / 20515344\r", + " 57% [......................................... ] 11837440 / 20515344\r", + " 57% [......................................... ] 11845632 / 20515344\r", + " 57% [......................................... ] 11853824 / 20515344\r", + " 57% [......................................... ] 11862016 / 20515344\r", + " 57% [......................................... ] 11870208 / 20515344\r", + " 57% [......................................... ] 11878400 / 20515344\r", + " 57% [......................................... ] 11886592 / 20515344\r", + " 57% [......................................... ] 11894784 / 20515344\r", + " 58% [......................................... ] 11902976 / 20515344\r", + " 58% [......................................... ] 11911168 / 20515344\r", + " 58% [......................................... ] 11919360 / 20515344\r", + " 58% [......................................... ] 11927552 / 20515344\r", + " 58% [......................................... ] 11935744 / 20515344\r", + " 58% [......................................... ] 11943936 / 20515344\r", + " 58% [......................................... ] 11952128 / 20515344\r", + " 58% [......................................... ] 11960320 / 20515344\r", + " 58% [.......................................... ] 11968512 / 20515344\r", + " 58% [.......................................... ] 11976704 / 20515344\r", + " 58% [.......................................... ] 11984896 / 20515344\r", + " 58% [.......................................... ] 11993088 / 20515344\r", + " 58% [.......................................... ] 12001280 / 20515344\r", + " 58% [.......................................... ] 12009472 / 20515344\r", + " 58% [.......................................... ] 12017664 / 20515344\r", + " 58% [.......................................... ] 12025856 / 20515344\r", + " 58% [.......................................... ] 12034048 / 20515344\r", + " 58% [.......................................... ] 12042240 / 20515344\r", + " 58% [.......................................... ] 12050432 / 20515344\r", + " 58% [.......................................... ] 12058624 / 20515344\r", + " 58% [.......................................... ] 12066816 / 20515344\r", + " 58% [.......................................... ] 12075008 / 20515344\r", + " 58% [.......................................... ] 12083200 / 20515344\r", + " 58% [.......................................... ] 12091392 / 20515344\r", + " 58% [.......................................... ] 12099584 / 20515344\r", + " 59% [.......................................... ] 12107776 / 20515344\r", + " 59% [.......................................... ] 12115968 / 20515344\r", + " 59% [.......................................... ] 12124160 / 20515344\r", + " 59% [.......................................... ] 12132352 / 20515344\r", + " 59% [.......................................... ] 12140544 / 20515344\r", + " 59% [.......................................... ] 12148736 / 20515344\r", + " 59% [.......................................... ] 12156928 / 20515344\r", + " 59% [.......................................... ] 12165120 / 20515344\r", + " 59% [.......................................... ] 12173312 / 20515344\r", + " 59% [.......................................... ] 12181504 / 20515344\r", + " 59% [.......................................... ] 12189696 / 20515344\r", + " 59% [.......................................... ] 12197888 / 20515344\r", + " 59% [.......................................... ] 12206080 / 20515344\r", + " 59% [.......................................... ] 12214272 / 20515344" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " 59% [.......................................... ] 12222464 / 20515344\r", + " 59% [.......................................... ] 12230656 / 20515344\r", + " 59% [.......................................... ] 12238848 / 20515344\r", + " 59% [.......................................... ] 12247040 / 20515344\r", + " 59% [........................................... ] 12255232 / 20515344\r", + " 59% [........................................... ] 12263424 / 20515344\r", + " 59% [........................................... ] 12271616 / 20515344\r", + " 59% [........................................... ] 12279808 / 20515344\r", + " 59% [........................................... ] 12288000 / 20515344\r", + " 59% [........................................... ] 12296192 / 20515344\r", + " 59% [........................................... ] 12304384 / 20515344\r", + " 60% [........................................... ] 12312576 / 20515344\r", + " 60% [........................................... ] 12320768 / 20515344\r", + " 60% [........................................... ] 12328960 / 20515344\r", + " 60% [........................................... ] 12337152 / 20515344\r", + " 60% [........................................... ] 12345344 / 20515344\r", + " 60% [........................................... ] 12353536 / 20515344\r", + " 60% [........................................... ] 12361728 / 20515344\r", + " 60% [........................................... ] 12369920 / 20515344\r", + " 60% [........................................... ] 12378112 / 20515344\r", + " 60% [........................................... ] 12386304 / 20515344\r", + " 60% [........................................... ] 12394496 / 20515344\r", + " 60% [........................................... ] 12402688 / 20515344\r", + " 60% [........................................... ] 12410880 / 20515344\r", + " 60% [........................................... ] 12419072 / 20515344\r", + " 60% [........................................... ] 12427264 / 20515344\r", + " 60% [........................................... ] 12435456 / 20515344\r", + " 60% [........................................... ] 12443648 / 20515344\r", + " 60% [........................................... ] 12451840 / 20515344\r", + " 60% [........................................... ] 12460032 / 20515344\r", + " 60% [........................................... ] 12468224 / 20515344\r", + " 60% [........................................... ] 12476416 / 20515344\r", + " 60% [........................................... ] 12484608 / 20515344\r", + " 60% [........................................... ] 12492800 / 20515344\r", + " 60% [........................................... ] 12500992 / 20515344\r", + " 60% [........................................... ] 12509184 / 20515344\r", + " 61% [........................................... ] 12517376 / 20515344\r", + " 61% [........................................... ] 12525568 / 20515344\r", + " 61% [........................................... ] 12533760 / 20515344\r", + " 61% [............................................ ] 12541952 / 20515344\r", + " 61% [............................................ ] 12550144 / 20515344\r", + " 61% [............................................ ] 12558336 / 20515344\r", + " 61% [............................................ ] 12566528 / 20515344\r", + " 61% [............................................ ] 12574720 / 20515344\r", + " 61% [............................................ ] 12582912 / 20515344\r", + " 61% [............................................ ] 12591104 / 20515344\r", + " 61% [............................................ ] 12599296 / 20515344\r", + " 61% [............................................ ] 12607488 / 20515344\r", + " 61% [............................................ ] 12615680 / 20515344\r", + " 61% [............................................ ] 12623872 / 20515344\r", + " 61% [............................................ ] 12632064 / 20515344\r", + " 61% [............................................ ] 12640256 / 20515344\r", + " 61% [............................................ ] 12648448 / 20515344\r", + " 61% [............................................ ] 12656640 / 20515344\r", + " 61% [............................................ ] 12664832 / 20515344\r", + " 61% [............................................ ] 12673024 / 20515344\r", + " 61% [............................................ ] 12681216 / 20515344\r", + " 61% [............................................ ] 12689408 / 20515344\r", + " 61% [............................................ ] 12697600 / 20515344\r", + " 61% [............................................ ] 12705792 / 20515344\r", + " 61% [............................................ ] 12713984 / 20515344\r", + " 62% [............................................ ] 12722176 / 20515344\r", + " 62% [............................................ ] 12730368 / 20515344\r", + " 62% [............................................ ] 12738560 / 20515344\r", + " 62% [............................................ ] 12746752 / 20515344\r", + " 62% [............................................ ] 12754944 / 20515344\r", + " 62% [............................................ ] 12763136 / 20515344\r", + " 62% [............................................ ] 12771328 / 20515344\r", + " 62% [............................................ ] 12779520 / 20515344\r", + " 62% [............................................ ] 12787712 / 20515344\r", + " 62% [............................................ ] 12795904 / 20515344\r", + " 62% [............................................ ] 12804096 / 20515344\r", + " 62% [............................................ ] 12812288 / 20515344\r", + " 62% [............................................ ] 12820480 / 20515344\r", + " 62% [............................................. ] 12828672 / 20515344\r", + " 62% [............................................. ] 12836864 / 20515344\r", + " 62% [............................................. ] 12845056 / 20515344\r", + " 62% [............................................. ] 12853248 / 20515344\r", + " 62% [............................................. ] 12861440 / 20515344\r", + " 62% [............................................. ] 12869632 / 20515344\r", + " 62% [............................................. ] 12877824 / 20515344\r", + " 62% [............................................. ] 12886016 / 20515344\r", + " 62% [............................................. ] 12894208 / 20515344\r", + " 62% [............................................. ] 12902400 / 20515344\r", + " 62% [............................................. ] 12910592 / 20515344\r", + " 62% [............................................. ] 12918784 / 20515344\r", + " 63% [............................................. ] 12926976 / 20515344\r", + " 63% [............................................. ] 12935168 / 20515344\r", + " 63% [............................................. ] 12943360 / 20515344\r", + " 63% [............................................. ] 12951552 / 20515344\r", + " 63% [............................................. ] 12959744 / 20515344\r", + " 63% [............................................. ] 12967936 / 20515344\r", + " 63% [............................................. ] 12976128 / 20515344\r", + " 63% [............................................. ] 12984320 / 20515344\r", + " 63% [............................................. ] 12992512 / 20515344\r", + " 63% [............................................. ] 13000704 / 20515344\r", + " 63% [............................................. ] 13008896 / 20515344\r", + " 63% [............................................. ] 13017088 / 20515344\r", + " 63% [............................................. ] 13025280 / 20515344\r", + " 63% [............................................. ] 13033472 / 20515344\r", + " 63% [............................................. ] 13041664 / 20515344\r", + " 63% [............................................. ] 13049856 / 20515344\r", + " 63% [............................................. ] 13058048 / 20515344\r", + " 63% [............................................. ] 13066240 / 20515344\r", + " 63% [............................................. ] 13074432 / 20515344\r", + " 63% [............................................. ] 13082624 / 20515344\r", + " 63% [............................................. ] 13090816 / 20515344\r", + " 63% [............................................. ] 13099008 / 20515344\r", + " 63% [.............................................. ] 13107200 / 20515344\r", + " 63% [.............................................. ] 13115392 / 20515344\r", + " 63% [.............................................. ] 13123584 / 20515344\r", + " 64% [.............................................. ] 13131776 / 20515344\r", + " 64% [.............................................. ] 13139968 / 20515344\r", + " 64% [.............................................. ] 13148160 / 20515344\r", + " 64% [.............................................. ] 13156352 / 20515344\r", + " 64% [.............................................. ] 13164544 / 20515344\r", + " 64% [.............................................. ] 13172736 / 20515344\r", + " 64% [.............................................. ] 13180928 / 20515344\r", + " 64% [.............................................. ] 13189120 / 20515344\r", + " 64% [.............................................. ] 13197312 / 20515344\r", + " 64% [.............................................. ] 13205504 / 20515344\r", + " 64% [.............................................. ] 13213696 / 20515344\r", + " 64% [.............................................. ] 13221888 / 20515344\r", + " 64% [.............................................. ] 13230080 / 20515344\r", + " 64% [.............................................. ] 13238272 / 20515344\r", + " 64% [.............................................. ] 13246464 / 20515344\r", + " 64% [.............................................. ] 13254656 / 20515344\r", + " 64% [.............................................. ] 13262848 / 20515344\r", + " 64% [.............................................. ] 13271040 / 20515344\r", + " 64% [.............................................. ] 13279232 / 20515344\r", + " 64% [.............................................. ] 13287424 / 20515344\r", + " 64% [.............................................. ] 13295616 / 20515344\r", + " 64% [.............................................. ] 13303808 / 20515344\r", + " 64% [.............................................. ] 13312000 / 20515344\r", + " 64% [.............................................. ] 13320192 / 20515344\r", + " 64% [.............................................. ] 13328384 / 20515344\r", + " 65% [.............................................. ] 13336576 / 20515344\r", + " 65% [.............................................. ] 13344768 / 20515344\r", + " 65% [.............................................. ] 13352960 / 20515344\r", + " 65% [.............................................. ] 13361152 / 20515344\r", + " 65% [.............................................. ] 13369344 / 20515344\r", + " 65% [.............................................. ] 13377536 / 20515344\r", + " 65% [.............................................. ] 13385728 / 20515344\r", + " 65% [............................................... ] 13393920 / 20515344\r", + " 65% [............................................... ] 13402112 / 20515344\r", + " 65% [............................................... ] 13410304 / 20515344\r", + " 65% [............................................... ] 13418496 / 20515344\r", + " 65% [............................................... ] 13426688 / 20515344\r", + " 65% [............................................... ] 13434880 / 20515344\r", + " 65% [............................................... ] 13443072 / 20515344\r", + " 65% [............................................... ] 13451264 / 20515344\r", + " 65% [............................................... ] 13459456 / 20515344\r", + " 65% [............................................... ] 13467648 / 20515344\r", + " 65% [............................................... ] 13475840 / 20515344\r", + " 65% [............................................... ] 13484032 / 20515344\r", + " 65% [............................................... ] 13492224 / 20515344\r", + " 65% [............................................... ] 13500416 / 20515344\r", + " 65% [............................................... ] 13508608 / 20515344\r", + " 65% [............................................... ] 13516800 / 20515344\r", + " 65% [............................................... ] 13524992 / 20515344\r", + " 65% [............................................... ] 13533184 / 20515344\r", + " 66% [............................................... ] 13541376 / 20515344\r", + " 66% [............................................... ] 13549568 / 20515344\r", + " 66% [............................................... ] 13557760 / 20515344\r", + " 66% [............................................... ] 13565952 / 20515344\r", + " 66% [............................................... ] 13574144 / 20515344\r", + " 66% [............................................... ] 13582336 / 20515344\r", + " 66% [............................................... ] 13590528 / 20515344\r", + " 66% [............................................... ] 13598720 / 20515344\r", + " 66% [............................................... ] 13606912 / 20515344\r", + " 66% [............................................... ] 13615104 / 20515344\r", + " 66% [............................................... ] 13623296 / 20515344\r", + " 66% [............................................... ] 13631488 / 20515344\r", + " 66% [............................................... ] 13639680 / 20515344\r", + " 66% [............................................... ] 13647872 / 20515344\r", + " 66% [............................................... ] 13656064 / 20515344\r", + " 66% [............................................... ] 13664256 / 20515344\r", + " 66% [............................................... ] 13672448 / 20515344\r", + " 66% [................................................ ] 13680640 / 20515344\r", + " 66% [................................................ ] 13688832 / 20515344\r", + " 66% [................................................ ] 13697024 / 20515344\r", + " 66% [................................................ ] 13705216 / 20515344\r", + " 66% [................................................ ] 13713408 / 20515344\r", + " 66% [................................................ ] 13721600 / 20515344\r", + " 66% [................................................ ] 13729792 / 20515344\r", + " 66% [................................................ ] 13737984 / 20515344\r", + " 67% [................................................ ] 13746176 / 20515344\r", + " 67% [................................................ ] 13754368 / 20515344\r", + " 67% [................................................ ] 13762560 / 20515344\r", + " 67% [................................................ ] 13770752 / 20515344\r", + " 67% [................................................ ] 13778944 / 20515344\r", + " 67% [................................................ ] 13787136 / 20515344\r", + " 67% [................................................ ] 13795328 / 20515344\r", + " 67% [................................................ ] 13803520 / 20515344\r", + " 67% [................................................ ] 13811712 / 20515344\r", + " 67% [................................................ ] 13819904 / 20515344\r", + " 67% [................................................ ] 13828096 / 20515344\r", + " 67% [................................................ ] 13836288 / 20515344\r", + " 67% [................................................ ] 13844480 / 20515344\r", + " 67% [................................................ ] 13852672 / 20515344\r", + " 67% [................................................ ] 13860864 / 20515344\r", + " 67% [................................................ ] 13869056 / 20515344\r", + " 67% [................................................ ] 13877248 / 20515344\r", + " 67% [................................................ ] 13885440 / 20515344\r", + " 67% [................................................ ] 13893632 / 20515344\r", + " 67% [................................................ ] 13901824 / 20515344\r", + " 67% [................................................ ] 13910016 / 20515344\r", + " 67% [................................................ ] 13918208 / 20515344\r", + " 67% [................................................ ] 13926400 / 20515344\r", + " 67% [................................................ ] 13934592 / 20515344\r", + " 67% [................................................ ] 13942784 / 20515344\r", + " 68% [................................................ ] 13950976 / 20515344\r", + " 68% [................................................ ] 13959168 / 20515344\r", + " 68% [................................................. ] 13967360 / 20515344\r", + " 68% [................................................. ] 13975552 / 20515344\r", + " 68% [................................................. ] 13983744 / 20515344\r", + " 68% [................................................. ] 13991936 / 20515344\r", + " 68% [................................................. ] 14000128 / 20515344\r", + " 68% [................................................. ] 14008320 / 20515344\r", + " 68% [................................................. ] 14016512 / 20515344\r", + " 68% [................................................. ] 14024704 / 20515344\r", + " 68% [................................................. ] 14032896 / 20515344\r", + " 68% [................................................. ] 14041088 / 20515344\r", + " 68% [................................................. ] 14049280 / 20515344\r", + " 68% [................................................. ] 14057472 / 20515344\r", + " 68% [................................................. ] 14065664 / 20515344\r", + " 68% [................................................. ] 14073856 / 20515344\r", + " 68% [................................................. ] 14082048 / 20515344\r", + " 68% [................................................. ] 14090240 / 20515344\r", + " 68% [................................................. ] 14098432 / 20515344\r", + " 68% [................................................. ] 14106624 / 20515344\r", + " 68% [................................................. ] 14114816 / 20515344\r", + " 68% [................................................. ] 14123008 / 20515344\r", + " 68% [................................................. ] 14131200 / 20515344\r", + " 68% [................................................. ] 14139392 / 20515344\r", + " 68% [................................................. ] 14147584 / 20515344\r", + " 69% [................................................. ] 14155776 / 20515344\r", + " 69% [................................................. ] 14163968 / 20515344\r", + " 69% [................................................. ] 14172160 / 20515344\r", + " 69% [................................................. ] 14180352 / 20515344\r", + " 69% [................................................. ] 14188544 / 20515344\r", + " 69% [................................................. ] 14196736 / 20515344\r", + " 69% [................................................. ] 14204928 / 20515344\r", + " 69% [................................................. ] 14213120 / 20515344\r", + " 69% [................................................. ] 14221312 / 20515344\r", + " 69% [................................................. ] 14229504 / 20515344\r", + " 69% [................................................. ] 14237696 / 20515344\r", + " 69% [................................................. ] 14245888 / 20515344\r", + " 69% [.................................................. ] 14254080 / 20515344\r", + " 69% [.................................................. ] 14262272 / 20515344\r", + " 69% [.................................................. ] 14270464 / 20515344\r", + " 69% [.................................................. ] 14278656 / 20515344\r", + " 69% [.................................................. ] 14286848 / 20515344\r", + " 69% [.................................................. ] 14295040 / 20515344\r", + " 69% [.................................................. ] 14303232 / 20515344\r", + " 69% [.................................................. ] 14311424 / 20515344\r", + " 69% [.................................................. ] 14319616 / 20515344\r", + " 69% [.................................................. ] 14327808 / 20515344\r", + " 69% [.................................................. ] 14336000 / 20515344\r", + " 69% [.................................................. ] 14344192 / 20515344\r", + " 69% [.................................................. ] 14352384 / 20515344\r", + " 69% [.................................................. ] 14360576 / 20515344\r", + " 70% [.................................................. ] 14368768 / 20515344\r", + " 70% [.................................................. ] 14376960 / 20515344\r", + " 70% [.................................................. ] 14385152 / 20515344\r", + " 70% [.................................................. ] 14393344 / 20515344\r", + " 70% [.................................................. ] 14401536 / 20515344\r", + " 70% [.................................................. ] 14409728 / 20515344\r", + " 70% [.................................................. ] 14417920 / 20515344\r", + " 70% [.................................................. ] 14426112 / 20515344\r", + " 70% [.................................................. ] 14434304 / 20515344\r", + " 70% [.................................................. ] 14442496 / 20515344\r", + " 70% [.................................................. ] 14450688 / 20515344\r", + " 70% [.................................................. ] 14458880 / 20515344\r", + " 70% [.................................................. ] 14467072 / 20515344\r", + " 70% [.................................................. ] 14475264 / 20515344\r", + " 70% [.................................................. ] 14483456 / 20515344\r", + " 70% [.................................................. ] 14491648 / 20515344\r", + " 70% [.................................................. ] 14499840 / 20515344\r", + " 70% [.................................................. ] 14508032 / 20515344\r", + " 70% [.................................................. ] 14516224 / 20515344\r", + " 70% [.................................................. ] 14524416 / 20515344\r", + " 70% [................................................... ] 14532608 / 20515344\r", + " 70% [................................................... ] 14540800 / 20515344\r", + " 70% [................................................... ] 14548992 / 20515344\r", + " 70% [................................................... ] 14557184 / 20515344\r", + " 70% [................................................... ] 14565376 / 20515344\r", + " 71% [................................................... ] 14573568 / 20515344\r", + " 71% [................................................... ] 14581760 / 20515344\r", + " 71% [................................................... ] 14589952 / 20515344\r", + " 71% [................................................... ] 14598144 / 20515344\r", + " 71% [................................................... ] 14606336 / 20515344\r", + " 71% [................................................... ] 14614528 / 20515344\r", + " 71% [................................................... ] 14622720 / 20515344\r", + " 71% [................................................... ] 14630912 / 20515344\r", + " 71% [................................................... ] 14639104 / 20515344\r", + " 71% [................................................... ] 14647296 / 20515344\r", + " 71% [................................................... ] 14655488 / 20515344\r", + " 71% [................................................... ] 14663680 / 20515344\r", + " 71% [................................................... ] 14671872 / 20515344\r", + " 71% [................................................... ] 14680064 / 20515344\r", + " 71% [................................................... ] 14688256 / 20515344\r", + " 71% [................................................... ] 14696448 / 20515344\r", + " 71% [................................................... ] 14704640 / 20515344\r", + " 71% [................................................... ] 14712832 / 20515344\r", + " 71% [................................................... ] 14721024 / 20515344\r", + " 71% [................................................... ] 14729216 / 20515344\r", + " 71% [................................................... ] 14737408 / 20515344\r", + " 71% [................................................... ] 14745600 / 20515344\r", + " 71% [................................................... ] 14753792 / 20515344\r", + " 71% [................................................... ] 14761984 / 20515344\r", + " 71% [................................................... ] 14770176 / 20515344\r", + " 72% [................................................... ] 14778368 / 20515344\r", + " 72% [................................................... ] 14786560 / 20515344\r", + " 72% [................................................... ] 14794752 / 20515344\r", + " 72% [................................................... ] 14802944 / 20515344\r", + " 72% [................................................... ] 14811136 / 20515344\r", + " 72% [.................................................... ] 14819328 / 20515344\r", + " 72% [.................................................... ] 14827520 / 20515344\r", + " 72% [.................................................... ] 14835712 / 20515344\r", + " 72% [.................................................... ] 14843904 / 20515344\r", + " 72% [.................................................... ] 14852096 / 20515344\r", + " 72% [.................................................... ] 14860288 / 20515344\r", + " 72% [.................................................... ] 14868480 / 20515344\r", + " 72% [.................................................... ] 14876672 / 20515344\r", + " 72% [.................................................... ] 14884864 / 20515344\r", + " 72% [.................................................... ] 14893056 / 20515344\r", + " 72% [.................................................... ] 14901248 / 20515344\r", + " 72% [.................................................... ] 14909440 / 20515344\r", + " 72% [.................................................... ] 14917632 / 20515344\r", + " 72% [.................................................... ] 14925824 / 20515344\r", + " 72% [.................................................... ] 14934016 / 20515344\r", + " 72% [.................................................... ] 14942208 / 20515344\r", + " 72% [.................................................... ] 14950400 / 20515344\r", + " 72% [.................................................... ] 14958592 / 20515344\r", + " 72% [.................................................... ] 14966784 / 20515344\r", + " 72% [.................................................... ] 14974976 / 20515344\r", + " 73% [.................................................... ] 14983168 / 20515344\r", + " 73% [.................................................... ] 14991360 / 20515344\r", + " 73% [.................................................... ] 14999552 / 20515344\r", + " 73% [.................................................... ] 15007744 / 20515344\r", + " 73% [.................................................... ] 15015936 / 20515344\r", + " 73% [.................................................... ] 15024128 / 20515344\r", + " 73% [.................................................... ] 15032320 / 20515344\r", + " 73% [.................................................... ] 15040512 / 20515344\r", + " 73% [.................................................... ] 15048704 / 20515344\r", + " 73% [.................................................... ] 15056896 / 20515344\r", + " 73% [.................................................... ] 15065088 / 20515344\r", + " 73% [.................................................... ] 15073280 / 20515344\r", + " 73% [.................................................... ] 15081472 / 20515344\r", + " 73% [.................................................... ] 15089664 / 20515344\r", + " 73% [.................................................... ] 15097856 / 20515344\r", + " 73% [..................................................... ] 15106048 / 20515344\r", + " 73% [..................................................... ] 15114240 / 20515344\r", + " 73% [..................................................... ] 15122432 / 20515344\r", + " 73% [..................................................... ] 15130624 / 20515344\r", + " 73% [..................................................... ] 15138816 / 20515344\r", + " 73% [..................................................... ] 15147008 / 20515344\r", + " 73% [..................................................... ] 15155200 / 20515344\r", + " 73% [..................................................... ] 15163392 / 20515344\r", + " 73% [..................................................... ] 15171584 / 20515344\r", + " 73% [..................................................... ] 15179776 / 20515344\r", + " 74% [..................................................... ] 15187968 / 20515344\r", + " 74% [..................................................... ] 15196160 / 20515344\r", + " 74% [..................................................... ] 15204352 / 20515344\r", + " 74% [..................................................... ] 15212544 / 20515344\r", + " 74% [..................................................... ] 15220736 / 20515344\r", + " 74% [..................................................... ] 15228928 / 20515344\r", + " 74% [..................................................... ] 15237120 / 20515344\r", + " 74% [..................................................... ] 15245312 / 20515344\r", + " 74% [..................................................... ] 15253504 / 20515344\r", + " 74% [..................................................... ] 15261696 / 20515344\r", + " 74% [..................................................... ] 15269888 / 20515344\r", + " 74% [..................................................... ] 15278080 / 20515344\r", + " 74% [..................................................... ] 15286272 / 20515344\r", + " 74% [..................................................... ] 15294464 / 20515344\r", + " 74% [..................................................... ] 15302656 / 20515344\r", + " 74% [..................................................... ] 15310848 / 20515344\r", + " 74% [..................................................... ] 15319040 / 20515344\r", + " 74% [..................................................... ] 15327232 / 20515344\r", + " 74% [..................................................... ] 15335424 / 20515344\r", + " 74% [..................................................... ] 15343616 / 20515344\r", + " 74% [..................................................... ] 15351808 / 20515344\r", + " 74% [..................................................... ] 15360000 / 20515344\r", + " 74% [..................................................... ] 15368192 / 20515344\r", + " 74% [..................................................... ] 15376384 / 20515344\r", + " 74% [..................................................... ] 15384576 / 20515344\r", + " 75% [...................................................... ] 15392768 / 20515344\r", + " 75% [...................................................... ] 15400960 / 20515344\r", + " 75% [...................................................... ] 15409152 / 20515344\r", + " 75% [...................................................... ] 15417344 / 20515344\r", + " 75% [...................................................... ] 15425536 / 20515344\r", + " 75% [...................................................... ] 15433728 / 20515344\r", + " 75% [...................................................... ] 15441920 / 20515344\r", + " 75% [...................................................... ] 15450112 / 20515344\r", + " 75% [...................................................... ] 15458304 / 20515344\r", + " 75% [...................................................... ] 15466496 / 20515344\r", + " 75% [...................................................... ] 15474688 / 20515344\r", + " 75% [...................................................... ] 15482880 / 20515344\r", + " 75% [...................................................... ] 15491072 / 20515344\r", + " 75% [...................................................... ] 15499264 / 20515344\r", + " 75% [...................................................... ] 15507456 / 20515344\r", + " 75% [...................................................... ] 15515648 / 20515344\r", + " 75% [...................................................... ] 15523840 / 20515344\r", + " 75% [...................................................... ] 15532032 / 20515344\r", + " 75% [...................................................... ] 15540224 / 20515344\r", + " 75% [...................................................... ] 15548416 / 20515344\r", + " 75% [...................................................... ] 15556608 / 20515344\r", + " 75% [...................................................... ] 15564800 / 20515344\r", + " 75% [...................................................... ] 15572992 / 20515344\r", + " 75% [...................................................... ] 15581184 / 20515344\r", + " 75% [...................................................... ] 15589376 / 20515344\r", + " 76% [...................................................... ] 15597568 / 20515344\r", + " 76% [...................................................... ] 15605760 / 20515344\r", + " 76% [...................................................... ] 15613952 / 20515344\r", + " 76% [...................................................... ] 15622144 / 20515344\r", + " 76% [...................................................... ] 15630336 / 20515344\r", + " 76% [...................................................... ] 15638528 / 20515344\r", + " 76% [...................................................... ] 15646720 / 20515344\r", + " 76% [...................................................... ] 15654912 / 20515344\r", + " 76% [...................................................... ] 15663104 / 20515344\r", + " 76% [...................................................... ] 15671296 / 20515344\r", + " 76% [....................................................... ] 15679488 / 20515344\r", + " 76% [....................................................... ] 15687680 / 20515344\r", + " 76% [....................................................... ] 15695872 / 20515344\r", + " 76% [....................................................... ] 15704064 / 20515344\r", + " 76% [....................................................... ] 15712256 / 20515344\r", + " 76% [....................................................... ] 15720448 / 20515344\r", + " 76% [....................................................... ] 15728640 / 20515344\r", + " 76% [....................................................... ] 15736832 / 20515344\r", + " 76% [....................................................... ] 15745024 / 20515344\r", + " 76% [....................................................... ] 15753216 / 20515344\r", + " 76% [....................................................... ] 15761408 / 20515344\r", + " 76% [....................................................... ] 15769600 / 20515344\r", + " 76% [....................................................... ] 15777792 / 20515344\r", + " 76% [....................................................... ] 15785984 / 20515344\r", + " 76% [....................................................... ] 15794176 / 20515344\r", + " 77% [....................................................... ] 15802368 / 20515344\r", + " 77% [....................................................... ] 15810560 / 20515344\r", + " 77% [....................................................... ] 15818752 / 20515344\r", + " 77% [....................................................... ] 15826944 / 20515344\r", + " 77% [....................................................... ] 15835136 / 20515344\r", + " 77% [....................................................... ] 15843328 / 20515344\r", + " 77% [....................................................... ] 15851520 / 20515344\r", + " 77% [....................................................... ] 15859712 / 20515344\r", + " 77% [....................................................... ] 15867904 / 20515344\r", + " 77% [....................................................... ] 15876096 / 20515344\r", + " 77% [....................................................... ] 15884288 / 20515344\r", + " 77% [....................................................... ] 15892480 / 20515344\r", + " 77% [....................................................... ] 15900672 / 20515344\r", + " 77% [....................................................... ] 15908864 / 20515344\r", + " 77% [....................................................... ] 15917056 / 20515344\r", + " 77% [....................................................... ] 15925248 / 20515344\r", + " 77% [....................................................... ] 15933440 / 20515344\r", + " 77% [....................................................... ] 15941632 / 20515344\r", + " 77% [....................................................... ] 15949824 / 20515344\r", + " 77% [........................................................ ] 15958016 / 20515344\r", + " 77% [........................................................ ] 15966208 / 20515344\r", + " 77% [........................................................ ] 15974400 / 20515344\r", + " 77% [........................................................ ] 15982592 / 20515344\r", + " 77% [........................................................ ] 15990784 / 20515344\r", + " 77% [........................................................ ] 15998976 / 20515344\r", + " 78% [........................................................ ] 16007168 / 20515344\r", + " 78% [........................................................ ] 16015360 / 20515344\r", + " 78% [........................................................ ] 16023552 / 20515344\r", + " 78% [........................................................ ] 16031744 / 20515344\r", + " 78% [........................................................ ] 16039936 / 20515344\r", + " 78% [........................................................ ] 16048128 / 20515344\r", + " 78% [........................................................ ] 16056320 / 20515344\r", + " 78% [........................................................ ] 16064512 / 20515344\r", + " 78% [........................................................ ] 16072704 / 20515344\r", + " 78% [........................................................ ] 16080896 / 20515344\r", + " 78% [........................................................ ] 16089088 / 20515344\r", + " 78% [........................................................ ] 16097280 / 20515344\r", + " 78% [........................................................ ] 16105472 / 20515344\r", + " 78% [........................................................ ] 16113664 / 20515344\r", + " 78% [........................................................ ] 16121856 / 20515344\r", + " 78% [........................................................ ] 16130048 / 20515344\r", + " 78% [........................................................ ] 16138240 / 20515344\r", + " 78% [........................................................ ] 16146432 / 20515344\r", + " 78% [........................................................ ] 16154624 / 20515344\r", + " 78% [........................................................ ] 16162816 / 20515344\r", + " 78% [........................................................ ] 16171008 / 20515344\r", + " 78% [........................................................ ] 16179200 / 20515344\r", + " 78% [........................................................ ] 16187392 / 20515344\r", + " 78% [........................................................ ] 16195584 / 20515344\r", + " 78% [........................................................ ] 16203776 / 20515344\r", + " 79% [........................................................ ] 16211968 / 20515344\r", + " 79% [........................................................ ] 16220160 / 20515344\r", + " 79% [........................................................ ] 16228352 / 20515344\r", + " 79% [........................................................ ] 16236544 / 20515344\r", + " 79% [......................................................... ] 16244736 / 20515344\r", + " 79% [......................................................... ] 16252928 / 20515344\r", + " 79% [......................................................... ] 16261120 / 20515344\r", + " 79% [......................................................... ] 16269312 / 20515344\r", + " 79% [......................................................... ] 16277504 / 20515344\r", + " 79% [......................................................... ] 16285696 / 20515344\r", + " 79% [......................................................... ] 16293888 / 20515344\r", + " 79% [......................................................... ] 16302080 / 20515344\r", + " 79% [......................................................... ] 16310272 / 20515344\r", + " 79% [......................................................... ] 16318464 / 20515344\r", + " 79% [......................................................... ] 16326656 / 20515344\r", + " 79% [......................................................... ] 16334848 / 20515344\r", + " 79% [......................................................... ] 16343040 / 20515344\r", + " 79% [......................................................... ] 16351232 / 20515344\r", + " 79% [......................................................... ] 16359424 / 20515344\r", + " 79% [......................................................... ] 16367616 / 20515344\r", + " 79% [......................................................... ] 16375808 / 20515344\r", + " 79% [......................................................... ] 16384000 / 20515344\r", + " 79% [......................................................... ] 16392192 / 20515344\r", + " 79% [......................................................... ] 16400384 / 20515344\r", + " 79% [......................................................... ] 16408576 / 20515344\r", + " 80% [......................................................... ] 16416768 / 20515344\r", + " 80% [......................................................... ] 16424960 / 20515344\r", + " 80% [......................................................... ] 16433152 / 20515344\r", + " 80% [......................................................... ] 16441344 / 20515344\r", + " 80% [......................................................... ] 16449536 / 20515344\r", + " 80% [......................................................... ] 16457728 / 20515344\r", + " 80% [......................................................... ] 16465920 / 20515344\r", + " 80% [......................................................... ] 16474112 / 20515344\r", + " 80% [......................................................... ] 16482304 / 20515344\r", + " 80% [......................................................... ] 16490496 / 20515344\r", + " 80% [......................................................... ] 16498688 / 20515344\r", + " 80% [......................................................... ] 16506880 / 20515344\r", + " 80% [......................................................... ] 16515072 / 20515344\r", + " 80% [......................................................... ] 16523264 / 20515344\r", + " 80% [.......................................................... ] 16531456 / 20515344\r", + " 80% [.......................................................... ] 16539648 / 20515344\r", + " 80% [.......................................................... ] 16547840 / 20515344\r", + " 80% [.......................................................... ] 16556032 / 20515344\r", + " 80% [.......................................................... ] 16564224 / 20515344\r", + " 80% [.......................................................... ] 16572416 / 20515344\r", + " 80% [.......................................................... ] 16580608 / 20515344\r", + " 80% [.......................................................... ] 16588800 / 20515344\r", + " 80% [.......................................................... ] 16596992 / 20515344\r", + " 80% [.......................................................... ] 16605184 / 20515344\r", + " 80% [.......................................................... ] 16613376 / 20515344\r", + " 81% [.......................................................... ] 16621568 / 20515344\r", + " 81% [.......................................................... ] 16629760 / 20515344\r", + " 81% [.......................................................... ] 16637952 / 20515344\r", + " 81% [.......................................................... ] 16646144 / 20515344\r", + " 81% [.......................................................... ] 16654336 / 20515344\r", + " 81% [.......................................................... ] 16662528 / 20515344\r", + " 81% [.......................................................... ] 16670720 / 20515344\r", + " 81% [.......................................................... ] 16678912 / 20515344\r", + " 81% [.......................................................... ] 16687104 / 20515344\r", + " 81% [.......................................................... ] 16695296 / 20515344\r", + " 81% [.......................................................... ] 16703488 / 20515344\r", + " 81% [.......................................................... ] 16711680 / 20515344\r", + " 81% [.......................................................... ] 16719872 / 20515344\r", + " 81% [.......................................................... ] 16728064 / 20515344\r", + " 81% [.......................................................... ] 16736256 / 20515344\r", + " 81% [.......................................................... ] 16744448 / 20515344\r", + " 81% [.......................................................... ] 16752640 / 20515344\r", + " 81% [.......................................................... ] 16760832 / 20515344\r", + " 81% [.......................................................... ] 16769024 / 20515344\r", + " 81% [.......................................................... ] 16777216 / 20515344\r", + " 81% [.......................................................... ] 16785408 / 20515344\r", + " 81% [.......................................................... ] 16793600 / 20515344\r", + " 81% [.......................................................... ] 16801792 / 20515344\r", + " 81% [.......................................................... ] 16809984 / 20515344\r", + " 81% [........................................................... ] 16818176 / 20515344\r", + " 82% [........................................................... ] 16826368 / 20515344\r", + " 82% [........................................................... ] 16834560 / 20515344\r", + " 82% [........................................................... ] 16842752 / 20515344\r", + " 82% [........................................................... ] 16850944 / 20515344\r", + " 82% [........................................................... ] 16859136 / 20515344\r", + " 82% [........................................................... ] 16867328 / 20515344\r", + " 82% [........................................................... ] 16875520 / 20515344\r", + " 82% [........................................................... ] 16883712 / 20515344\r", + " 82% [........................................................... ] 16891904 / 20515344\r", + " 82% [........................................................... ] 16900096 / 20515344\r", + " 82% [........................................................... ] 16908288 / 20515344\r", + " 82% [........................................................... ] 16916480 / 20515344\r", + " 82% [........................................................... ] 16924672 / 20515344\r", + " 82% [........................................................... ] 16932864 / 20515344\r", + " 82% [........................................................... ] 16941056 / 20515344\r", + " 82% [........................................................... ] 16949248 / 20515344\r", + " 82% [........................................................... ] 16957440 / 20515344\r", + " 82% [........................................................... ] 16965632 / 20515344\r", + " 82% [........................................................... ] 16973824 / 20515344\r", + " 82% [........................................................... ] 16982016 / 20515344\r", + " 82% [........................................................... ] 16990208 / 20515344\r", + " 82% [........................................................... ] 16998400 / 20515344\r", + " 82% [........................................................... ] 17006592 / 20515344\r", + " 82% [........................................................... ] 17014784 / 20515344\r", + " 82% [........................................................... ] 17022976 / 20515344\r", + " 83% [........................................................... ] 17031168 / 20515344\r", + " 83% [........................................................... ] 17039360 / 20515344\r", + " 83% [........................................................... ] 17047552 / 20515344\r", + " 83% [........................................................... ] 17055744 / 20515344\r", + " 83% [........................................................... ] 17063936 / 20515344\r", + " 83% [........................................................... ] 17072128 / 20515344\r", + " 83% [........................................................... ] 17080320 / 20515344\r", + " 83% [........................................................... ] 17088512 / 20515344\r", + " 83% [............................................................ ] 17096704 / 20515344\r", + " 83% [............................................................ ] 17104896 / 20515344\r", + " 83% [............................................................ ] 17113088 / 20515344\r", + " 83% [............................................................ ] 17121280 / 20515344\r", + " 83% [............................................................ ] 17129472 / 20515344\r", + " 83% [............................................................ ] 17137664 / 20515344\r", + " 83% [............................................................ ] 17145856 / 20515344\r", + " 83% [............................................................ ] 17154048 / 20515344\r", + " 83% [............................................................ ] 17162240 / 20515344\r", + " 83% [............................................................ ] 17170432 / 20515344\r", + " 83% [............................................................ ] 17178624 / 20515344\r", + " 83% [............................................................ ] 17186816 / 20515344\r", + " 83% [............................................................ ] 17195008 / 20515344\r", + " 83% [............................................................ ] 17203200 / 20515344\r", + " 83% [............................................................ ] 17211392 / 20515344\r", + " 83% [............................................................ ] 17219584 / 20515344\r", + " 83% [............................................................ ] 17227776 / 20515344\r", + " 84% [............................................................ ] 17235968 / 20515344\r", + " 84% [............................................................ ] 17244160 / 20515344\r", + " 84% [............................................................ ] 17252352 / 20515344\r", + " 84% [............................................................ ] 17260544 / 20515344\r", + " 84% [............................................................ ] 17268736 / 20515344\r", + " 84% [............................................................ ] 17276928 / 20515344\r", + " 84% [............................................................ ] 17285120 / 20515344\r", + " 84% [............................................................ ] 17293312 / 20515344\r", + " 84% [............................................................ ] 17301504 / 20515344\r", + " 84% [............................................................ ] 17309696 / 20515344\r", + " 84% [............................................................ ] 17317888 / 20515344\r", + " 84% [............................................................ ] 17326080 / 20515344\r", + " 84% [............................................................ ] 17334272 / 20515344\r", + " 84% [............................................................ ] 17342464 / 20515344\r", + " 84% [............................................................ ] 17350656 / 20515344\r", + " 84% [............................................................ ] 17358848 / 20515344\r", + " 84% [............................................................ ] 17367040 / 20515344\r", + " 84% [............................................................ ] 17375232 / 20515344\r", + " 84% [............................................................. ] 17383424 / 20515344\r", + " 84% [............................................................. ] 17391616 / 20515344\r", + " 84% [............................................................. ] 17399808 / 20515344\r", + " 84% [............................................................. ] 17408000 / 20515344\r", + " 84% [............................................................. ] 17416192 / 20515344\r", + " 84% [............................................................. ] 17424384 / 20515344\r", + " 84% [............................................................. ] 17432576 / 20515344\r", + " 85% [............................................................. ] 17440768 / 20515344\r", + " 85% [............................................................. ] 17448960 / 20515344\r", + " 85% [............................................................. ] 17457152 / 20515344\r", + " 85% [............................................................. ] 17465344 / 20515344\r", + " 85% [............................................................. ] 17473536 / 20515344\r", + " 85% [............................................................. ] 17481728 / 20515344\r", + " 85% [............................................................. ] 17489920 / 20515344\r", + " 85% [............................................................. ] 17498112 / 20515344\r", + " 85% [............................................................. ] 17506304 / 20515344\r", + " 85% [............................................................. ] 17514496 / 20515344\r", + " 85% [............................................................. ] 17522688 / 20515344\r", + " 85% [............................................................. ] 17530880 / 20515344\r", + " 85% [............................................................. ] 17539072 / 20515344\r", + " 85% [............................................................. ] 17547264 / 20515344\r", + " 85% [............................................................. ] 17555456 / 20515344\r", + " 85% [............................................................. ] 17563648 / 20515344\r", + " 85% [............................................................. ] 17571840 / 20515344\r", + " 85% [............................................................. ] 17580032 / 20515344\r", + " 85% [............................................................. ] 17588224 / 20515344\r", + " 85% [............................................................. ] 17596416 / 20515344\r", + " 85% [............................................................. ] 17604608 / 20515344\r", + " 85% [............................................................. ] 17612800 / 20515344\r", + " 85% [............................................................. ] 17620992 / 20515344\r", + " 85% [............................................................. ] 17629184 / 20515344\r", + " 85% [............................................................. ] 17637376 / 20515344\r", + " 86% [............................................................. ] 17645568 / 20515344\r", + " 86% [............................................................. ] 17653760 / 20515344\r", + " 86% [............................................................. ] 17661952 / 20515344\r", + " 86% [.............................................................. ] 17670144 / 20515344\r", + " 86% [.............................................................. ] 17678336 / 20515344\r", + " 86% [.............................................................. ] 17686528 / 20515344\r", + " 86% [.............................................................. ] 17694720 / 20515344\r", + " 86% [.............................................................. ] 17702912 / 20515344\r", + " 86% [.............................................................. ] 17711104 / 20515344\r", + " 86% [.............................................................. ] 17719296 / 20515344\r", + " 86% [.............................................................. ] 17727488 / 20515344\r", + " 86% [.............................................................. ] 17735680 / 20515344\r", + " 86% [.............................................................. ] 17743872 / 20515344\r", + " 86% [.............................................................. ] 17752064 / 20515344\r", + " 86% [.............................................................. ] 17760256 / 20515344\r", + " 86% [.............................................................. ] 17768448 / 20515344\r", + " 86% [.............................................................. ] 17776640 / 20515344\r", + " 86% [.............................................................. ] 17784832 / 20515344\r", + " 86% [.............................................................. ] 17793024 / 20515344\r", + " 86% [.............................................................. ] 17801216 / 20515344\r", + " 86% [.............................................................. ] 17809408 / 20515344\r", + " 86% [.............................................................. ] 17817600 / 20515344\r", + " 86% [.............................................................. ] 17825792 / 20515344\r", + " 86% [.............................................................. ] 17833984 / 20515344\r", + " 86% [.............................................................. ] 17842176 / 20515344\r", + " 87% [.............................................................. ] 17850368 / 20515344\r", + " 87% [.............................................................. ] 17858560 / 20515344\r", + " 87% [.............................................................. ] 17866752 / 20515344\r", + " 87% [.............................................................. ] 17874944 / 20515344\r", + " 87% [.............................................................. ] 17883136 / 20515344\r", + " 87% [.............................................................. ] 17891328 / 20515344\r", + " 87% [.............................................................. ] 17899520 / 20515344\r", + " 87% [.............................................................. ] 17907712 / 20515344\r", + " 87% [.............................................................. ] 17915904 / 20515344\r", + " 87% [.............................................................. ] 17924096 / 20515344\r", + " 87% [.............................................................. ] 17932288 / 20515344\r", + " 87% [.............................................................. ] 17940480 / 20515344\r", + " 87% [.............................................................. ] 17948672 / 20515344\r", + " 87% [............................................................... ] 17956864 / 20515344\r", + " 87% [............................................................... ] 17965056 / 20515344\r", + " 87% [............................................................... ] 17973248 / 20515344\r", + " 87% [............................................................... ] 17981440 / 20515344\r", + " 87% [............................................................... ] 17989632 / 20515344\r", + " 87% [............................................................... ] 17997824 / 20515344\r", + " 87% [............................................................... ] 18006016 / 20515344\r", + " 87% [............................................................... ] 18014208 / 20515344\r", + " 87% [............................................................... ] 18022400 / 20515344\r", + " 87% [............................................................... ] 18030592 / 20515344\r", + " 87% [............................................................... ] 18038784 / 20515344\r", + " 87% [............................................................... ] 18046976 / 20515344\r", + " 88% [............................................................... ] 18055168 / 20515344\r", + " 88% [............................................................... ] 18063360 / 20515344\r", + " 88% [............................................................... ] 18071552 / 20515344\r", + " 88% [............................................................... ] 18079744 / 20515344\r", + " 88% [............................................................... ] 18087936 / 20515344\r", + " 88% [............................................................... ] 18096128 / 20515344" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " 88% [............................................................... ] 18104320 / 20515344\r", + " 88% [............................................................... ] 18112512 / 20515344\r", + " 88% [............................................................... ] 18120704 / 20515344\r", + " 88% [............................................................... ] 18128896 / 20515344\r", + " 88% [............................................................... ] 18137088 / 20515344\r", + " 88% [............................................................... ] 18145280 / 20515344\r", + " 88% [............................................................... ] 18153472 / 20515344\r", + " 88% [............................................................... ] 18161664 / 20515344\r", + " 88% [............................................................... ] 18169856 / 20515344\r", + " 88% [............................................................... ] 18178048 / 20515344\r", + " 88% [............................................................... ] 18186240 / 20515344\r", + " 88% [............................................................... ] 18194432 / 20515344\r", + " 88% [............................................................... ] 18202624 / 20515344\r", + " 88% [............................................................... ] 18210816 / 20515344\r", + " 88% [............................................................... ] 18219008 / 20515344\r", + " 88% [............................................................... ] 18227200 / 20515344\r", + " 88% [............................................................... ] 18235392 / 20515344\r", + " 88% [................................................................ ] 18243584 / 20515344\r", + " 88% [................................................................ ] 18251776 / 20515344\r", + " 89% [................................................................ ] 18259968 / 20515344\r", + " 89% [................................................................ ] 18268160 / 20515344\r", + " 89% [................................................................ ] 18276352 / 20515344\r", + " 89% [................................................................ ] 18284544 / 20515344\r", + " 89% [................................................................ ] 18292736 / 20515344\r", + " 89% [................................................................ ] 18300928 / 20515344\r", + " 89% [................................................................ ] 18309120 / 20515344\r", + " 89% [................................................................ ] 18317312 / 20515344\r", + " 89% [................................................................ ] 18325504 / 20515344\r", + " 89% [................................................................ ] 18333696 / 20515344\r", + " 89% [................................................................ ] 18341888 / 20515344\r", + " 89% [................................................................ ] 18350080 / 20515344\r", + " 89% [................................................................ ] 18358272 / 20515344\r", + " 89% [................................................................ ] 18366464 / 20515344\r", + " 89% [................................................................ ] 18374656 / 20515344\r", + " 89% [................................................................ ] 18382848 / 20515344\r", + " 89% [................................................................ ] 18391040 / 20515344\r", + " 89% [................................................................ ] 18399232 / 20515344\r", + " 89% [................................................................ ] 18407424 / 20515344\r", + " 89% [................................................................ ] 18415616 / 20515344\r", + " 89% [................................................................ ] 18423808 / 20515344\r", + " 89% [................................................................ ] 18432000 / 20515344\r", + " 89% [................................................................ ] 18440192 / 20515344\r", + " 89% [................................................................ ] 18448384 / 20515344\r", + " 89% [................................................................ ] 18456576 / 20515344\r", + " 90% [................................................................ ] 18464768 / 20515344\r", + " 90% [................................................................ ] 18472960 / 20515344\r", + " 90% [................................................................ ] 18481152 / 20515344\r", + " 90% [................................................................ ] 18489344 / 20515344\r", + " 90% [................................................................ ] 18497536 / 20515344\r", + " 90% [................................................................ ] 18505728 / 20515344\r", + " 90% [................................................................ ] 18513920 / 20515344\r", + " 90% [................................................................. ] 18522112 / 20515344\r", + " 90% [................................................................. ] 18530304 / 20515344\r", + " 90% [................................................................. ] 18538496 / 20515344\r", + " 90% [................................................................. ] 18546688 / 20515344\r", + " 90% [................................................................. ] 18554880 / 20515344\r", + " 90% [................................................................. ] 18563072 / 20515344\r", + " 90% [................................................................. ] 18571264 / 20515344\r", + " 90% [................................................................. ] 18579456 / 20515344\r", + " 90% [................................................................. ] 18587648 / 20515344\r", + " 90% [................................................................. ] 18595840 / 20515344\r", + " 90% [................................................................. ] 18604032 / 20515344\r", + " 90% [................................................................. ] 18612224 / 20515344\r", + " 90% [................................................................. ] 18620416 / 20515344\r", + " 90% [................................................................. ] 18628608 / 20515344\r", + " 90% [................................................................. ] 18636800 / 20515344\r", + " 90% [................................................................. ] 18644992 / 20515344\r", + " 90% [................................................................. ] 18653184 / 20515344\r", + " 90% [................................................................. ] 18661376 / 20515344\r", + " 91% [................................................................. ] 18669568 / 20515344\r", + " 91% [................................................................. ] 18677760 / 20515344\r", + " 91% [................................................................. ] 18685952 / 20515344\r", + " 91% [................................................................. ] 18694144 / 20515344\r", + " 91% [................................................................. ] 18702336 / 20515344\r", + " 91% [................................................................. ] 18710528 / 20515344\r", + " 91% [................................................................. ] 18718720 / 20515344\r", + " 91% [................................................................. ] 18726912 / 20515344\r", + " 91% [................................................................. ] 18735104 / 20515344\r", + " 91% [................................................................. ] 18743296 / 20515344\r", + " 91% [................................................................. ] 18751488 / 20515344\r", + " 91% [................................................................. ] 18759680 / 20515344\r", + " 91% [................................................................. ] 18767872 / 20515344\r", + " 91% [................................................................. ] 18776064 / 20515344\r", + " 91% [................................................................. ] 18784256 / 20515344\r", + " 91% [................................................................. ] 18792448 / 20515344\r", + " 91% [................................................................. ] 18800640 / 20515344\r", + " 91% [.................................................................. ] 18808832 / 20515344\r", + " 91% [.................................................................. ] 18817024 / 20515344\r", + " 91% [.................................................................. ] 18825216 / 20515344\r", + " 91% [.................................................................. ] 18833408 / 20515344\r", + " 91% [.................................................................. ] 18841600 / 20515344\r", + " 91% [.................................................................. ] 18849792 / 20515344\r", + " 91% [.................................................................. ] 18857984 / 20515344\r", + " 91% [.................................................................. ] 18866176 / 20515344\r", + " 92% [.................................................................. ] 18874368 / 20515344\r", + " 92% [.................................................................. ] 18882560 / 20515344\r", + " 92% [.................................................................. ] 18890752 / 20515344\r", + " 92% [.................................................................. ] 18898944 / 20515344\r", + " 92% [.................................................................. ] 18907136 / 20515344\r", + " 92% [.................................................................. ] 18915328 / 20515344\r", + " 92% [.................................................................. ] 18923520 / 20515344\r", + " 92% [.................................................................. ] 18931712 / 20515344\r", + " 92% [.................................................................. ] 18939904 / 20515344\r", + " 92% [.................................................................. ] 18948096 / 20515344\r", + " 92% [.................................................................. ] 18956288 / 20515344\r", + " 92% [.................................................................. ] 18964480 / 20515344\r", + " 92% [.................................................................. ] 18972672 / 20515344\r", + " 92% [.................................................................. ] 18980864 / 20515344\r", + " 92% [.................................................................. ] 18989056 / 20515344\r", + " 92% [.................................................................. ] 18997248 / 20515344\r", + " 92% [.................................................................. ] 19005440 / 20515344\r", + " 92% [.................................................................. ] 19013632 / 20515344\r", + " 92% [.................................................................. ] 19021824 / 20515344\r", + " 92% [.................................................................. ] 19030016 / 20515344\r", + " 92% [.................................................................. ] 19038208 / 20515344\r", + " 92% [.................................................................. ] 19046400 / 20515344\r", + " 92% [.................................................................. ] 19054592 / 20515344\r", + " 92% [.................................................................. ] 19062784 / 20515344\r", + " 92% [.................................................................. ] 19070976 / 20515344\r", + " 92% [.................................................................. ] 19079168 / 20515344\r", + " 93% [.................................................................. ] 19087360 / 20515344\r", + " 93% [................................................................... ] 19095552 / 20515344\r", + " 93% [................................................................... ] 19103744 / 20515344\r", + " 93% [................................................................... ] 19111936 / 20515344\r", + " 93% [................................................................... ] 19120128 / 20515344\r", + " 93% [................................................................... ] 19128320 / 20515344\r", + " 93% [................................................................... ] 19136512 / 20515344\r", + " 93% [................................................................... ] 19144704 / 20515344\r", + " 93% [................................................................... ] 19152896 / 20515344\r", + " 93% [................................................................... ] 19161088 / 20515344\r", + " 93% [................................................................... ] 19169280 / 20515344\r", + " 93% [................................................................... ] 19177472 / 20515344\r", + " 93% [................................................................... ] 19185664 / 20515344\r", + " 93% [................................................................... ] 19193856 / 20515344\r", + " 93% [................................................................... ] 19202048 / 20515344\r", + " 93% [................................................................... ] 19210240 / 20515344\r", + " 93% [................................................................... ] 19218432 / 20515344\r", + " 93% [................................................................... ] 19226624 / 20515344\r", + " 93% [................................................................... ] 19234816 / 20515344\r", + " 93% [................................................................... ] 19243008 / 20515344\r", + " 93% [................................................................... ] 19251200 / 20515344\r", + " 93% [................................................................... ] 19259392 / 20515344\r", + " 93% [................................................................... ] 19267584 / 20515344\r", + " 93% [................................................................... ] 19275776 / 20515344\r", + " 93% [................................................................... ] 19283968 / 20515344\r", + " 94% [................................................................... ] 19292160 / 20515344\r", + " 94% [................................................................... ] 19300352 / 20515344\r", + " 94% [................................................................... ] 19308544 / 20515344\r", + " 94% [................................................................... ] 19316736 / 20515344\r", + " 94% [................................................................... ] 19324928 / 20515344\r", + " 94% [................................................................... ] 19333120 / 20515344\r", + " 94% [................................................................... ] 19341312 / 20515344\r", + " 94% [................................................................... ] 19349504 / 20515344\r", + " 94% [................................................................... ] 19357696 / 20515344\r", + " 94% [................................................................... ] 19365888 / 20515344\r", + " 94% [................................................................... ] 19374080 / 20515344\r", + " 94% [.................................................................... ] 19382272 / 20515344\r", + " 94% [.................................................................... ] 19390464 / 20515344\r", + " 94% [.................................................................... ] 19398656 / 20515344\r", + " 94% [.................................................................... ] 19406848 / 20515344\r", + " 94% [.................................................................... ] 19415040 / 20515344\r", + " 94% [.................................................................... ] 19423232 / 20515344\r", + " 94% [.................................................................... ] 19431424 / 20515344\r", + " 94% [.................................................................... ] 19439616 / 20515344\r", + " 94% [.................................................................... ] 19447808 / 20515344\r", + " 94% [.................................................................... ] 19456000 / 20515344\r", + " 94% [.................................................................... ] 19464192 / 20515344\r", + " 94% [.................................................................... ] 19472384 / 20515344\r", + " 94% [.................................................................... ] 19480576 / 20515344\r", + " 94% [.................................................................... ] 19488768 / 20515344\r", + " 95% [.................................................................... ] 19496960 / 20515344\r", + " 95% [.................................................................... ] 19505152 / 20515344\r", + " 95% [.................................................................... ] 19513344 / 20515344\r", + " 95% [.................................................................... ] 19521536 / 20515344\r", + " 95% [.................................................................... ] 19529728 / 20515344\r", + " 95% [.................................................................... ] 19537920 / 20515344\r", + " 95% [.................................................................... ] 19546112 / 20515344\r", + " 95% [.................................................................... ] 19554304 / 20515344\r", + " 95% [.................................................................... ] 19562496 / 20515344\r", + " 95% [.................................................................... ] 19570688 / 20515344\r", + " 95% [.................................................................... ] 19578880 / 20515344\r", + " 95% [.................................................................... ] 19587072 / 20515344\r", + " 95% [.................................................................... ] 19595264 / 20515344\r", + " 95% [.................................................................... ] 19603456 / 20515344\r", + " 95% [.................................................................... ] 19611648 / 20515344\r", + " 95% [.................................................................... ] 19619840 / 20515344\r", + " 95% [.................................................................... ] 19628032 / 20515344\r", + " 95% [.................................................................... ] 19636224 / 20515344\r", + " 95% [.................................................................... ] 19644416 / 20515344\r", + " 95% [.................................................................... ] 19652608 / 20515344\r", + " 95% [..................................................................... ] 19660800 / 20515344\r", + " 95% [..................................................................... ] 19668992 / 20515344\r", + " 95% [..................................................................... ] 19677184 / 20515344\r", + " 95% [..................................................................... ] 19685376 / 20515344\r", + " 95% [..................................................................... ] 19693568 / 20515344\r", + " 96% [..................................................................... ] 19701760 / 20515344\r", + " 96% [..................................................................... ] 19709952 / 20515344\r", + " 96% [..................................................................... ] 19718144 / 20515344\r", + " 96% [..................................................................... ] 19726336 / 20515344\r", + " 96% [..................................................................... ] 19734528 / 20515344\r", + " 96% [..................................................................... ] 19742720 / 20515344\r", + " 96% [..................................................................... ] 19750912 / 20515344\r", + " 96% [..................................................................... ] 19759104 / 20515344\r", + " 96% [..................................................................... ] 19767296 / 20515344\r", + " 96% [..................................................................... ] 19775488 / 20515344\r", + " 96% [..................................................................... ] 19783680 / 20515344\r", + " 96% [..................................................................... ] 19791872 / 20515344\r", + " 96% [..................................................................... ] 19800064 / 20515344\r", + " 96% [..................................................................... ] 19808256 / 20515344\r", + " 96% [..................................................................... ] 19816448 / 20515344\r", + " 96% [..................................................................... ] 19824640 / 20515344\r", + " 96% [..................................................................... ] 19832832 / 20515344\r", + " 96% [..................................................................... ] 19841024 / 20515344\r", + " 96% [..................................................................... ] 19849216 / 20515344\r", + " 96% [..................................................................... ] 19857408 / 20515344\r", + " 96% [..................................................................... ] 19865600 / 20515344\r", + " 96% [..................................................................... ] 19873792 / 20515344\r", + " 96% [..................................................................... ] 19881984 / 20515344\r", + " 96% [..................................................................... ] 19890176 / 20515344\r", + " 96% [..................................................................... ] 19898368 / 20515344\r", + " 97% [..................................................................... ] 19906560 / 20515344\r", + " 97% [..................................................................... ] 19914752 / 20515344\r", + " 97% [..................................................................... ] 19922944 / 20515344\r", + " 97% [..................................................................... ] 19931136 / 20515344\r", + " 97% [..................................................................... ] 19939328 / 20515344\r", + " 97% [...................................................................... ] 19947520 / 20515344\r", + " 97% [...................................................................... ] 19955712 / 20515344\r", + " 97% [...................................................................... ] 19963904 / 20515344\r", + " 97% [...................................................................... ] 19972096 / 20515344\r", + " 97% [...................................................................... ] 19980288 / 20515344\r", + " 97% [...................................................................... ] 19988480 / 20515344\r", + " 97% [...................................................................... ] 19996672 / 20515344\r", + " 97% [...................................................................... ] 20004864 / 20515344\r", + " 97% [...................................................................... ] 20013056 / 20515344\r", + " 97% [...................................................................... ] 20021248 / 20515344\r", + " 97% [...................................................................... ] 20029440 / 20515344\r", + " 97% [...................................................................... ] 20037632 / 20515344\r", + " 97% [...................................................................... ] 20045824 / 20515344\r", + " 97% [...................................................................... ] 20054016 / 20515344\r", + " 97% [...................................................................... ] 20062208 / 20515344\r", + " 97% [...................................................................... ] 20070400 / 20515344\r", + " 97% [...................................................................... ] 20078592 / 20515344\r", + " 97% [...................................................................... ] 20086784 / 20515344\r", + " 97% [...................................................................... ] 20094976 / 20515344\r", + " 97% [...................................................................... ] 20103168 / 20515344\r", + " 98% [...................................................................... ] 20111360 / 20515344\r", + " 98% [...................................................................... ] 20119552 / 20515344\r", + " 98% [...................................................................... ] 20127744 / 20515344\r", + " 98% [...................................................................... ] 20135936 / 20515344\r", + " 98% [...................................................................... ] 20144128 / 20515344\r", + " 98% [...................................................................... ] 20152320 / 20515344\r", + " 98% [...................................................................... ] 20160512 / 20515344\r", + " 98% [...................................................................... ] 20168704 / 20515344\r", + " 98% [...................................................................... ] 20176896 / 20515344\r", + " 98% [...................................................................... ] 20185088 / 20515344\r", + " 98% [...................................................................... ] 20193280 / 20515344\r", + " 98% [...................................................................... ] 20201472 / 20515344\r", + " 98% [...................................................................... ] 20209664 / 20515344\r", + " 98% [...................................................................... ] 20217856 / 20515344\r", + " 98% [...................................................................... ] 20226048 / 20515344\r", + " 98% [....................................................................... ] 20234240 / 20515344\r", + " 98% [....................................................................... ] 20242432 / 20515344\r", + " 98% [....................................................................... ] 20250624 / 20515344\r", + " 98% [....................................................................... ] 20258816 / 20515344\r", + " 98% [....................................................................... ] 20267008 / 20515344\r", + " 98% [....................................................................... ] 20275200 / 20515344\r", + " 98% [....................................................................... ] 20283392 / 20515344\r", + " 98% [....................................................................... ] 20291584 / 20515344\r", + " 98% [....................................................................... ] 20299776 / 20515344\r", + " 98% [....................................................................... ] 20307968 / 20515344\r", + " 99% [....................................................................... ] 20316160 / 20515344\r", + " 99% [....................................................................... ] 20324352 / 20515344\r", + " 99% [....................................................................... ] 20332544 / 20515344\r", + " 99% [....................................................................... ] 20340736 / 20515344\r", + " 99% [....................................................................... ] 20348928 / 20515344\r", + " 99% [....................................................................... ] 20357120 / 20515344\r", + " 99% [....................................................................... ] 20365312 / 20515344\r", + " 99% [....................................................................... ] 20373504 / 20515344\r", + " 99% [....................................................................... ] 20381696 / 20515344\r", + " 99% [....................................................................... ] 20389888 / 20515344\r", + " 99% [....................................................................... ] 20398080 / 20515344\r", + " 99% [....................................................................... ] 20406272 / 20515344\r", + " 99% [....................................................................... ] 20414464 / 20515344\r", + " 99% [....................................................................... ] 20422656 / 20515344\r", + " 99% [....................................................................... ] 20430848 / 20515344\r", + " 99% [....................................................................... ] 20439040 / 20515344\r", + " 99% [....................................................................... ] 20447232 / 20515344\r", + " 99% [....................................................................... ] 20455424 / 20515344\r", + " 99% [....................................................................... ] 20463616 / 20515344\r", + " 99% [....................................................................... ] 20471808 / 20515344\r", + " 99% [....................................................................... ] 20480000 / 20515344\r", + " 99% [....................................................................... ] 20488192 / 20515344\r", + " 99% [....................................................................... ] 20496384 / 20515344\r", + " 99% [....................................................................... ] 20504576 / 20515344\r", + " 99% [....................................................................... ] 20512768 / 20515344\r", + "100% [........................................................................] 20515344 / 20515344" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + " 1 file(s) moved.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "x ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/\n", + "x ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/checkpoint/\n", + "x ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/checkpoint/ckpt-0.data-00000-of-00001\n", + "x ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/checkpoint/checkpoint\n", + "x ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/checkpoint/ckpt-0.index\n", + "x ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/pipeline.config\n", + "x ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/saved_model/\n", + "x ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/saved_model/saved_model.pb\n", + "x ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/saved_model/variables/\n", + "x ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/saved_model/variables/variables.data-00000-of-00001\n", + "x ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/saved_model/variables/variables.index\n" + ] + } + ], + "source": [ + "if os.name =='posix':\n", + " !wget {PRETRAINED_MODEL_URL}\n", + " !mv {PRETRAINED_MODEL_NAME+'.tar.gz'} {paths['PRETRAINED_MODEL_PATH']}\n", + " !cd {paths['PRETRAINED_MODEL_PATH']} && tar -zxvf {PRETRAINED_MODEL_NAME+'.tar.gz'}\n", + "if os.name == 'nt':\n", + " wget.download(PRETRAINED_MODEL_URL)\n", + " !move {PRETRAINED_MODEL_NAME+'.tar.gz'} {paths['PRETRAINED_MODEL_PATH']}\n", + " !cd {paths['PRETRAINED_MODEL_PATH']} && tar -zxvf {PRETRAINED_MODEL_NAME+'.tar.gz'}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "M5KJTnkfpfDC" + }, + "source": [ + "# 2. Create Label Map" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "id": "p1BVDWo7pfDC" + }, + "outputs": [], + "source": [ + "labels = [{'name':'licence', 'id':1}]\n", + "\n", + "with open(files['LABELMAP'], 'w') as f:\n", + " for label in labels:\n", + " f.write('item { \\n')\n", + " f.write('\\tname:\\'{}\\'\\n'.format(label['name']))\n", + " f.write('\\tid:{}\\n'.format(label['id']))\n", + " f.write('}\\n')" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "C88zyVELpfDC" + }, + "source": [ + "# 3. Create TF records" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "kvf5WccwrFGq", + "outputId": "49902aeb-0bd7-4298-e1a0-5b4a64eb2064" + }, + "outputs": [], + "source": [ + "# OPTIONAL IF RUNNING ON COLAB\n", + "ARCHIVE_FILES = os.path.join(paths['IMAGE_PATH'], 'archive.tar.gz')\n", + "if os.path.exists(ARCHIVE_FILES):\n", + " !tar -zxvf {ARCHIVE_FILES}" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "KWpb_BVUpfDD", + "outputId": "56ce2a3f-3933-4ee6-8a9d-d5ec65f7d73c" + }, + "outputs": [], + "source": [ + "if not os.path.exists(files['TF_RECORD_SCRIPT']):\n", + " !git clone https://github.com/nicknochnack/GenerateTFRecord {paths['SCRIPTS_PATH']}" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "UPFToGZqpfDD", + "outputId": "0ebb456f-aadc-4a1f-96e6-fbfec1923e1c" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Successfully created the TFRecord file: Tensorflow\\workspace\\annotations\\train.record\n", + "Successfully created the TFRecord file: Tensorflow\\workspace\\annotations\\test.record\n" + ] + } + ], + "source": [ + "!python {files['TF_RECORD_SCRIPT']} -x {os.path.join(paths['IMAGE_PATH'], 'train')} -l {files['LABELMAP']} -o {os.path.join(paths['ANNOTATION_PATH'], 'train.record')} \n", + "!python {files['TF_RECORD_SCRIPT']} -x {os.path.join(paths['IMAGE_PATH'], 'test')} -l {files['LABELMAP']} -o {os.path.join(paths['ANNOTATION_PATH'], 'test.record')} " + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "qT4QU7pLpfDE" + }, + "source": [ + "# 4. Copy Model Config to Training Folder" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "id": "cOjuTFbwpfDF" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " 1 file(s) copied.\n" + ] + } + ], + "source": [ + "if os.name =='posix':\n", + " !cp {os.path.join(paths['PRETRAINED_MODEL_PATH'], PRETRAINED_MODEL_NAME, 'pipeline.config')} {os.path.join(paths['CHECKPOINT_PATH'])}\n", + "if os.name == 'nt':\n", + " !copy {os.path.join(paths['PRETRAINED_MODEL_PATH'], PRETRAINED_MODEL_NAME, 'pipeline.config')} {os.path.join(paths['CHECKPOINT_PATH'])}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Ga8gpNslpfDF" + }, + "source": [ + "# 5. Update Config For Transfer Learning" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "id": "Z9hRrO_ppfDF" + }, + "outputs": [], + "source": [ + "import tensorflow as tf\n", + "from object_detection.utils import config_util\n", + "from object_detection.protos import pipeline_pb2\n", + "from google.protobuf import text_format" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "id": "c2A0mn4ipfDF" + }, + "outputs": [], + "source": [ + "config = config_util.get_configs_from_pipeline_file(files['PIPELINE_CONFIG'])" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "collapsed": true, + "id": "uQA13-afpfDF", + "outputId": "907496a4-a39d-4b13-8c2c-e5978ecb1f10" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "{'model': ssd {\n", + " num_classes: 90\n", + " image_resizer {\n", + " fixed_shape_resizer {\n", + " height: 320\n", + " width: 320\n", + " }\n", + " }\n", + " feature_extractor {\n", + " type: \"ssd_mobilenet_v2_fpn_keras\"\n", + " depth_multiplier: 1.0\n", + " min_depth: 16\n", + " conv_hyperparams {\n", + " regularizer {\n", + " l2_regularizer {\n", + " weight: 3.9999998989515007e-05\n", + " }\n", + " }\n", + " initializer {\n", + " random_normal_initializer {\n", + " mean: 0.0\n", + " stddev: 0.009999999776482582\n", + " }\n", + " }\n", + " activation: RELU_6\n", + " batch_norm {\n", + " decay: 0.996999979019165\n", + " scale: true\n", + " epsilon: 0.0010000000474974513\n", + " }\n", + " }\n", + " use_depthwise: true\n", + " override_base_feature_extractor_hyperparams: true\n", + " fpn {\n", + " min_level: 3\n", + " max_level: 7\n", + " additional_layer_depth: 128\n", + " }\n", + " }\n", + " box_coder {\n", + " faster_rcnn_box_coder {\n", + " y_scale: 10.0\n", + " x_scale: 10.0\n", + " height_scale: 5.0\n", + " width_scale: 5.0\n", + " }\n", + " }\n", + " matcher {\n", + " argmax_matcher {\n", + " matched_threshold: 0.5\n", + " unmatched_threshold: 0.5\n", + " ignore_thresholds: false\n", + " negatives_lower_than_unmatched: true\n", + " force_match_for_each_row: true\n", + " use_matmul_gather: true\n", + " }\n", + " }\n", + " similarity_calculator {\n", + " iou_similarity {\n", + " }\n", + " }\n", + " box_predictor {\n", + " weight_shared_convolutional_box_predictor {\n", + " conv_hyperparams {\n", + " regularizer {\n", + " l2_regularizer {\n", + " weight: 3.9999998989515007e-05\n", + " }\n", + " }\n", + " initializer {\n", + " random_normal_initializer {\n", + " mean: 0.0\n", + " stddev: 0.009999999776482582\n", + " }\n", + " }\n", + " activation: RELU_6\n", + " batch_norm {\n", + " decay: 0.996999979019165\n", + " scale: true\n", + " epsilon: 0.0010000000474974513\n", + " }\n", + " }\n", + " depth: 128\n", + " num_layers_before_predictor: 4\n", + " kernel_size: 3\n", + " class_prediction_bias_init: -4.599999904632568\n", + " share_prediction_tower: true\n", + " use_depthwise: true\n", + " }\n", + " }\n", + " anchor_generator {\n", + " multiscale_anchor_generator {\n", + " min_level: 3\n", + " max_level: 7\n", + " anchor_scale: 4.0\n", + " aspect_ratios: 1.0\n", + " aspect_ratios: 2.0\n", + " aspect_ratios: 0.5\n", + " scales_per_octave: 2\n", + " }\n", + " }\n", + " post_processing {\n", + " batch_non_max_suppression {\n", + " score_threshold: 9.99999993922529e-09\n", + " iou_threshold: 0.6000000238418579\n", + " max_detections_per_class: 100\n", + " max_total_detections: 100\n", + " use_static_shapes: false\n", + " }\n", + " score_converter: SIGMOID\n", + " }\n", + " normalize_loss_by_num_matches: true\n", + " loss {\n", + " localization_loss {\n", + " weighted_smooth_l1 {\n", + " }\n", + " }\n", + " classification_loss {\n", + " weighted_sigmoid_focal {\n", + " gamma: 2.0\n", + " alpha: 0.25\n", + " }\n", + " }\n", + " classification_weight: 1.0\n", + " localization_weight: 1.0\n", + " }\n", + " encode_background_as_zeros: true\n", + " normalize_loc_loss_by_codesize: true\n", + " inplace_batchnorm_update: true\n", + " freeze_batchnorm: false\n", + " },\n", + " 'train_config': batch_size: 128\n", + " data_augmentation_options {\n", + " random_horizontal_flip {\n", + " }\n", + " }\n", + " data_augmentation_options {\n", + " random_crop_image {\n", + " min_object_covered: 0.0\n", + " min_aspect_ratio: 0.75\n", + " max_aspect_ratio: 3.0\n", + " min_area: 0.75\n", + " max_area: 1.0\n", + " overlap_thresh: 0.0\n", + " }\n", + " }\n", + " sync_replicas: true\n", + " optimizer {\n", + " momentum_optimizer {\n", + " learning_rate {\n", + " cosine_decay_learning_rate {\n", + " learning_rate_base: 0.07999999821186066\n", + " total_steps: 50000\n", + " warmup_learning_rate: 0.026666000485420227\n", + " warmup_steps: 1000\n", + " }\n", + " }\n", + " momentum_optimizer_value: 0.8999999761581421\n", + " }\n", + " use_moving_average: false\n", + " }\n", + " fine_tune_checkpoint: \"PATH_TO_BE_CONFIGURED\"\n", + " num_steps: 50000\n", + " startup_delay_steps: 0.0\n", + " replicas_to_aggregate: 8\n", + " max_number_of_boxes: 100\n", + " unpad_groundtruth_tensors: false\n", + " fine_tune_checkpoint_type: \"classification\"\n", + " fine_tune_checkpoint_version: V2,\n", + " 'train_input_config': label_map_path: \"PATH_TO_BE_CONFIGURED\"\n", + " tf_record_input_reader {\n", + " input_path: \"PATH_TO_BE_CONFIGURED\"\n", + " },\n", + " 'eval_config': metrics_set: \"coco_detection_metrics\"\n", + " use_moving_averages: false,\n", + " 'eval_input_configs': [label_map_path: \"PATH_TO_BE_CONFIGURED\"\n", + " shuffle: false\n", + " num_epochs: 1\n", + " tf_record_input_reader {\n", + " input_path: \"PATH_TO_BE_CONFIGURED\"\n", + " }\n", + " ],\n", + " 'eval_input_config': label_map_path: \"PATH_TO_BE_CONFIGURED\"\n", + " shuffle: false\n", + " num_epochs: 1\n", + " tf_record_input_reader {\n", + " input_path: \"PATH_TO_BE_CONFIGURED\"\n", + " }}" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "config" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "id": "9vK5lotDpfDF" + }, + "outputs": [], + "source": [ + "pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()\n", + "with tf.io.gfile.GFile(files['PIPELINE_CONFIG'], \"r\") as f: \n", + " proto_str = f.read() \n", + " text_format.Merge(proto_str, pipeline_config) " + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "id": "rP43Ph0JpfDG" + }, + "outputs": [], + "source": [ + "pipeline_config.model.ssd.num_classes = len(labels)\n", + "pipeline_config.train_config.batch_size = 4\n", + "pipeline_config.train_config.fine_tune_checkpoint = os.path.join(paths['PRETRAINED_MODEL_PATH'], PRETRAINED_MODEL_NAME, 'checkpoint', 'ckpt-0')\n", + "pipeline_config.train_config.fine_tune_checkpoint_type = \"detection\"\n", + "pipeline_config.train_input_reader.label_map_path= files['LABELMAP']\n", + "pipeline_config.train_input_reader.tf_record_input_reader.input_path[:] = [os.path.join(paths['ANNOTATION_PATH'], 'train.record')]\n", + "pipeline_config.eval_input_reader[0].label_map_path = files['LABELMAP']\n", + "pipeline_config.eval_input_reader[0].tf_record_input_reader.input_path[:] = [os.path.join(paths['ANNOTATION_PATH'], 'test.record')]" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": { + "id": "oJvfgwWqpfDG" + }, + "outputs": [], + "source": [ + "config_text = text_format.MessageToString(pipeline_config) \n", + "with tf.io.gfile.GFile(files['PIPELINE_CONFIG'], \"wb\") as f: \n", + " f.write(config_text) " + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Zr3ON7xMpfDG" + }, + "source": [ + "# 6. Train the model" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": { + "id": "B-Y2UQmQpfDG" + }, + "outputs": [], + "source": [ + "TRAINING_SCRIPT = os.path.join(paths['APIMODEL_PATH'], 'research', 'object_detection', 'model_main_tf2.py')" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "id": "jMP2XDfQpfDH" + }, + "outputs": [], + "source": [ + "command = \"python {} --model_dir={} --pipeline_config_path={} --num_train_steps=10000\".format(TRAINING_SCRIPT, paths['CHECKPOINT_PATH'],files['PIPELINE_CONFIG'])" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "A4OXXi-ApfDH", + "outputId": "117a0e83-012b-466e-b7a6-ccaa349ac5ab" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "python Tensorflow\\models\\research\\object_detection\\model_main_tf2.py --model_dir=Tensorflow\\workspace\\models\\my_ssd_mobnet --pipeline_config_path=Tensorflow\\workspace\\models\\my_ssd_mobnet\\pipeline.config --num_train_steps=10000\n" + ] + } + ], + "source": [ + "print(command)" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "collapsed": true, + "id": "i3ZsJR-qpfDH", + "outputId": "cabec5e1-45e6-4f2f-d9cf-297d9c1d0225" + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\tensorflow_addons\\utils\\ensure_tf_install.py:53: UserWarning: Tensorflow Addons supports using Python ops for all Tensorflow versions above or equal to 2.6.0 and strictly below 2.9.0 (nightly versions are not supported). \n", + " The versions of TensorFlow you are currently using is 2.12.0 and is not supported. \n", + "Some things might work, some things might not.\n", + "If you were to encounter a bug, do not file an issue.\n", + "If you want to make sure you're using a tested and supported configuration, either change the TensorFlow version or the TensorFlow Addons's version. \n", + "You can find the compatibility matrix in TensorFlow Addon's readme:\n", + "https://github.com/tensorflow/addons\n", + " warnings.warn(\n", + "WARNING:tensorflow:There are non-GPU devices in `tf.distribute.Strategy`, not using nccl allreduce.\n", + "W0618 21:18:08.964130 8716 cross_device_ops.py:1387] There are non-GPU devices in `tf.distribute.Strategy`, not using nccl allreduce.\n", + "INFO:tensorflow:Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:CPU:0',)\n", + "I0618 21:18:08.979934 8716 mirrored_strategy.py:374] Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:CPU:0',)\n", + "INFO:tensorflow:Maybe overwriting train_steps: 10000\n", + "I0618 21:18:08.979934 8716 config_util.py:552] Maybe overwriting train_steps: 10000\n", + "INFO:tensorflow:Maybe overwriting use_bfloat16: False\n", + "I0618 21:18:08.979934 8716 config_util.py:552] Maybe overwriting use_bfloat16: False\n", + "WARNING:tensorflow:From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\model_lib_v2.py:563: StrategyBase.experimental_distribute_datasets_from_function (from tensorflow.python.distribute.distribute_lib) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "rename to distribute_datasets_from_function\n", + "W0618 21:18:09.010843 8716 deprecation.py:364] From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\model_lib_v2.py:563: StrategyBase.experimental_distribute_datasets_from_function (from tensorflow.python.distribute.distribute_lib) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "rename to distribute_datasets_from_function\n", + "INFO:tensorflow:Reading unweighted datasets: ['Tensorflow\\\\workspace\\\\annotations\\\\train.record']\n", + "I0618 21:18:09.026458 8716 dataset_builder.py:162] Reading unweighted datasets: ['Tensorflow\\\\workspace\\\\annotations\\\\train.record']\n", + "INFO:tensorflow:Reading record datasets for input file: ['Tensorflow\\\\workspace\\\\annotations\\\\train.record']\n", + "I0618 21:18:09.026458 8716 dataset_builder.py:79] Reading record datasets for input file: ['Tensorflow\\\\workspace\\\\annotations\\\\train.record']\n", + "INFO:tensorflow:Number of filenames to read: 1\n", + "I0618 21:18:09.026458 8716 dataset_builder.py:80] Number of filenames to read: 1\n", + "WARNING:tensorflow:num_readers has been reduced to 1 to match input file shards.\n", + "W0618 21:18:09.026458 8716 dataset_builder.py:86] num_readers has been reduced to 1 to match input file shards.\n", + "WARNING:tensorflow:From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\builders\\dataset_builder.py:100: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "Use `tf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.AUTOTUNE)` instead. If sloppy execution is desired, use `tf.data.Options.deterministic`.\n", + "W0618 21:18:09.026458 8716 deprecation.py:364] From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\builders\\dataset_builder.py:100: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "Use `tf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.AUTOTUNE)` instead. If sloppy execution is desired, use `tf.data.Options.deterministic`.\n", + "WARNING:tensorflow:From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\builders\\dataset_builder.py:235: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "Use `tf.data.Dataset.map()\n", + "W0618 21:18:09.057794 8716 deprecation.py:364] From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\builders\\dataset_builder.py:235: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "Use `tf.data.Dataset.map()\n", + "WARNING:tensorflow:From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\tensorflow\\python\\util\\dispatch.py:1176: sparse_to_dense (from tensorflow.python.ops.sparse_ops) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "Create a `tf.sparse.SparseTensor` and use `tf.sparse.to_dense` instead.\n", + "W0618 21:18:15.768315 8716 deprecation.py:364] From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\tensorflow\\python\\util\\dispatch.py:1176: sparse_to_dense (from tensorflow.python.ops.sparse_ops) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "Create a `tf.sparse.SparseTensor` and use `tf.sparse.to_dense` instead.\n", + "WARNING:tensorflow:From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\tensorflow\\python\\util\\dispatch.py:1176: sample_distorted_bounding_box (from tensorflow.python.ops.image_ops_impl) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "`seed2` arg is deprecated.Use sample_distorted_bounding_box_v2 instead.\n", + "W0618 21:18:18.930223 8716 deprecation.py:364] From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\tensorflow\\python\\util\\dispatch.py:1176: sample_distorted_bounding_box (from tensorflow.python.ops.image_ops_impl) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "`seed2` arg is deprecated.Use sample_distorted_bounding_box_v2 instead.\n", + "WARNING:tensorflow:From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\tensorflow\\python\\util\\dispatch.py:1176: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "Use `tf.cast` instead.\n", + "W0618 21:18:21.329123 8716 deprecation.py:364] From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\tensorflow\\python\\util\\dispatch.py:1176: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n", + "Instructions for updating:\n", + "Use `tf.cast` instead.\n", + "WARNING:tensorflow:From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\builders\\optimizer_builder.py:124: The name tf.keras.optimizers.SGD is deprecated. Please use tf.keras.optimizers.legacy.SGD instead.\n", + "\n", + "W0618 21:18:24.713399 8716 module_wrapper.py:149] From C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\builders\\optimizer_builder.py:124: The name tf.keras.optimizers.SGD is deprecated. Please use tf.keras.optimizers.legacy.SGD instead.\n", + "\n", + "2023-06-18 21:18:25.257472: W tensorflow/core/framework/dataset.cc:807] Input of GeneratorDatasetOp::Dataset will not be optimized because the dataset does not implement the AsGraphDefInternal() method needed to apply optimizations.\n", + "C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\keras\\backend.py:452: UserWarning: `tf.keras.backend.set_learning_phase` is deprecated and will be removed after 2020-10-11. To update it, simply pass a True/False value to the `training` argument of the `__call__` method of your layer or model.\n", + " warnings.warn(\n", + "I0618 21:18:32.699578 21512 api.py:459] feature_map_spatial_dims: [(40, 40), (20, 20), (10, 10), (5, 5), (3, 3)]\n", + "I0618 21:18:42.531612 17488 api.py:459] feature_map_spatial_dims: [(40, 40), (20, 20), (10, 10), (5, 5), (3, 3)]\n", + "WARNING:tensorflow:Detecting that an object or model or tf.train.Checkpoint is being deleted with unrestored values. See the following logs for the specific values in question. To silence these warnings, use `status.expect_partial()`. See https://www.tensorflow.org/api_docs/python/tf/train/Checkpoint#restorefor details about the status object returned by the restore function.\n", + "W0618 21:18:48.718192 8716 checkpoint.py:205] Detecting that an object or model or tf.train.Checkpoint is being deleted with unrestored values. See the following logs for the specific values in question. To silence these warnings, use `status.expect_partial()`. See https://www.tensorflow.org/api_docs/python/tf/train/Checkpoint#restorefor details about the status object returned by the restore function.\n", + "WARNING:tensorflow:Value in checkpoint could not be found in the restored object: (root).optimizer.iter\n", + "W0618 21:18:48.718192 8716 checkpoint.py:214] Value in checkpoint could not be found in the restored object: (root).optimizer.iter\n", + "WARNING:tensorflow:Value in checkpoint could not be found in the restored object: (root).optimizer.decay\n", + "W0618 21:18:48.718192 8716 checkpoint.py:214] Value in checkpoint could not be found in the restored object: (root).optimizer.decay\n", + "WARNING:tensorflow:Value in checkpoint could not be found in the restored object: (root).optimizer.momentum\n", + "W0618 21:18:48.718192 8716 checkpoint.py:214] Value in checkpoint could not be found in the restored object: (root).optimizer.momentum\n" + ] + } + ], + "source": [ + "!{command}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4_YRZu7npfDH" + }, + "source": [ + "# 7. Evaluate the Model" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "80L7-fdPpfDH" + }, + "outputs": [], + "source": [ + "command = \"python {} --model_dir={} --pipeline_config_path={} --checkpoint_dir={}\".format(TRAINING_SCRIPT, paths['CHECKPOINT_PATH'],files['PIPELINE_CONFIG'], paths['CHECKPOINT_PATH'])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "lYsgEPx9pfDH", + "outputId": "8632d48b-91d2-45d9-bcb8-c1b172bf6eed" + }, + "outputs": [], + "source": [ + "print(command)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "lqTV2jGBpfDH" + }, + "outputs": [], + "source": [ + "!{command}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "orvRk02UpfDI" + }, + "source": [ + "# 8. Load Train Model From Checkpoint" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": { + "id": "8TYk4_oIpfDI" + }, + "outputs": [], + "source": [ + "import os\n", + "import tensorflow as tf\n", + "from object_detection.utils import label_map_util\n", + "from object_detection.utils import visualization_utils as viz_utils\n", + "from object_detection.builders import model_builder\n", + "from object_detection.utils import config_util" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": {}, + "outputs": [], + "source": [ + "# Prevent GPU complete consumption\n", + "gpus = tf.config.list_physical_devices('GPU')\n", + "if gpus:\n", + " try: \n", + " tf.config.experimental.set_virtual_device_configuration(\n", + " gpus[0], [tf.config.experimental.VirtualDeviceConfiguration(memory_limit=5120)])\n", + " except RunTimeError as e:\n", + " print(e)" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "id": "tDnQg-cYpfDI" + }, + "outputs": [], + "source": [ + "# Load pipeline config and build a detection model\n", + "configs = config_util.get_configs_from_pipeline_file(files['PIPELINE_CONFIG'])\n", + "detection_model = model_builder.build(model_config=configs['model'], is_training=False)\n", + "\n", + "# Restore checkpoint\n", + "ckpt = tf.compat.v2.train.Checkpoint(model=detection_model)\n", + "ckpt.restore(os.path.join(paths['CHECKPOINT_PATH'], 'ckpt-11')).expect_partial()\n", + "\n", + "@tf.function\n", + "def detect_fn(image):\n", + " image, shapes = detection_model.preprocess(image)\n", + " prediction_dict = detection_model.predict(image, shapes)\n", + " detections = detection_model.postprocess(prediction_dict, shapes)\n", + " return detections" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "0EmsmbBZpfDI" + }, + "source": [ + "# 9. Detect from an Image" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": { + "id": "Y_MKiuZ4pfDI" + }, + "outputs": [], + "source": [ + "import cv2 \n", + "import numpy as np\n", + "from matplotlib import pyplot as plt\n", + "%matplotlib inline" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "id": "cBDbIhNapfDI" + }, + "outputs": [], + "source": [ + "category_index = label_map_util.create_category_index_from_labelmap(files['LABELMAP'])" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "id": "Lx3crOhOzITB" + }, + "outputs": [], + "source": [ + "IMAGE_PATH = os.path.join(paths['IMAGE_PATH'],'test', 'Cars433.png')" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 269 + }, + "id": "Tpzn1SMry1yK", + "outputId": "c392a2c5-10fe-4fc4-9998-a1d4c7db2bd3" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "img = cv2.imread(IMAGE_PATH)\n", + "image_np = np.array(img)\n", + "\n", + "input_tensor = tf.convert_to_tensor(np.expand_dims(image_np, 0), dtype=tf.float32)\n", + "detections = detect_fn(input_tensor)\n", + "\n", + "num_detections = int(detections.pop('num_detections'))\n", + "detections = {key: value[0, :num_detections].numpy()\n", + " for key, value in detections.items()}\n", + "detections['num_detections'] = num_detections\n", + "\n", + "# detection_classes should be ints.\n", + "detections['detection_classes'] = detections['detection_classes'].astype(np.int64)\n", + "\n", + "label_id_offset = 1\n", + "image_np_with_detections = image_np.copy()\n", + "\n", + "viz_utils.visualize_boxes_and_labels_on_image_array(\n", + " image_np_with_detections,\n", + " detections['detection_boxes'],\n", + " detections['detection_classes']+label_id_offset,\n", + " detections['detection_scores'],\n", + " category_index,\n", + " use_normalized_coordinates=True,\n", + " max_boxes_to_draw=5,\n", + " min_score_thresh=.8,\n", + " agnostic_mode=False)\n", + "\n", + "plt.imshow(cv2.cvtColor(image_np_with_detections, cv2.COLOR_BGR2RGB))\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "dict_keys(['detection_boxes', 'detection_scores', 'detection_classes', 'raw_detection_boxes', 'raw_detection_scores', 'detection_multiclass_scores', 'detection_anchor_indices', 'num_detections'])" + ] + }, + "execution_count": 52, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "detections.keys()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Apply OCR to Detection" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: easyocr in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (1.6.2)\n", + "Requirement already satisfied: torch in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (2.0.0+cu117)\n", + "Requirement already satisfied: torchvision>=0.5 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (0.15.1+cu117)\n", + "Requirement already satisfied: opencv-python-headless<=4.5.4.60 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (4.5.4.60)\n", + "Requirement already satisfied: scipy in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (1.9.1)\n", + "Requirement already satisfied: numpy in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (1.23.5)\n", + "Requirement already satisfied: Pillow in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (9.4.0)\n", + "Requirement already satisfied: scikit-image in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (0.20.0)\n", + "Requirement already satisfied: python-bidi in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (0.4.2)\n", + "Requirement already satisfied: PyYAML in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (5.1)\n", + "Requirement already satisfied: Shapely in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (2.0.1)\n", + "Requirement already satisfied: pyclipper in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (1.3.0.post4)\n", + "Requirement already satisfied: ninja in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from easyocr) (1.11.1)\n", + "Requirement already satisfied: requests in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from torchvision>=0.5->easyocr) (2.28.2)\n", + "Requirement already satisfied: filelock in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from torch->easyocr) (3.9.0)\n", + "Requirement already satisfied: typing-extensions in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from torch->easyocr) (4.5.0)\n", + "Requirement already satisfied: sympy in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from torch->easyocr) (1.11.1)\n", + "Requirement already satisfied: networkx in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from torch->easyocr) (3.0)\n", + "Requirement already satisfied: jinja2 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from torch->easyocr) (3.1.2)\n", + "Requirement already satisfied: six in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from python-bidi->easyocr) (1.16.0)\n", + "Requirement already satisfied: imageio>=2.4.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from scikit-image->easyocr) (2.27.0)\n", + "Requirement already satisfied: tifffile>=2019.7.26 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from scikit-image->easyocr) (2023.4.12)\n", + "Requirement already satisfied: PyWavelets>=1.1.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from scikit-image->easyocr) (1.4.1)\n", + "Requirement already satisfied: packaging>=20.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from scikit-image->easyocr) (23.0)\n", + "Requirement already satisfied: lazy_loader>=0.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from scikit-image->easyocr) (0.2)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from jinja2->torch->easyocr) (2.1.2)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from requests->torchvision>=0.5->easyocr) (3.1.0)\n", + "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from requests->torchvision>=0.5->easyocr) (3.4)\n", + "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from requests->torchvision>=0.5->easyocr) (1.26.15)\n", + "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from requests->torchvision>=0.5->easyocr) (2022.12.7)\n", + "Requirement already satisfied: mpmath>=0.19 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from sympy->torch->easyocr) (1.3.0)\n" + ] + } + ], + "source": [ + "!pip install easyocr" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Looking in links: https://download.pytorch.org/whl/torch_stable.html\n", + "Collecting torch==1.8.1+cu111\n", + " Downloading https://download.pytorch.org/whl/cu111/torch-1.8.1%2Bcu111-cp39-cp39-win_amd64.whl (3055.6 MB)\n", + " 0.0/3.1 GB ? eta -:--:--\n", + " 0.0/3.1 GB 3.6 MB/s eta 0:14:01\n", + " 0.0/3.1 GB 2.2 MB/s eta 0:22:50\n", + " 0.0/3.1 GB 2.0 MB/s eta 0:24:52\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:19:01\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:25\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:49\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:25\n", + " 0.0/3.1 GB 3.2 MB/s eta 0:15:42\n", + " 0.0/3.1 GB 3.4 MB/s eta 0:14:55\n", + " 0.0/3.1 GB 3.3 MB/s eta 0:15:38\n", + " 0.0/3.1 GB 3.4 MB/s eta 0:15:03\n", + " 0.0/3.1 GB 3.4 MB/s eta 0:15:11\n", + " 0.0/3.1 GB 3.4 MB/s eta 0:14:58\n", + " 0.0/3.1 GB 3.4 MB/s eta 0:14:48\n", + " 0.0/3.1 GB 3.3 MB/s eta 0:15:23\n", + " 0.0/3.1 GB 3.4 MB/s eta 0:14:54\n", + " 0.0/3.1 GB 3.4 MB/s eta 0:15:09\n", + " 0.0/3.1 GB 3.3 MB/s eta 0:15:28\n", + " 0.0/3.1 GB 3.3 MB/s eta 0:15:15\n", + " 0.0/3.1 GB 3.3 MB/s eta 0:15:32\n", + " 0.0/3.1 GB 3.2 MB/s eta 0:15:41\n", + " 0.0/3.1 GB 3.3 MB/s eta 0:15:35\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:10\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:41\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:34\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:18\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:34\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:22\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:35\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:30\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:29\n", + " 0.0/3.1 GB 3.0 MB/s eta 0:16:54\n", + " 0.0/3.1 GB 3.0 MB/s eta 0:17:13\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:31\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:27\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:37\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:31\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:34\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:17:53\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:17:58\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:14\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:17\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:46\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:53\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:54\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:19:01\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:59\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:46\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:48\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:44\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:29\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:23\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:33\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:23\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:25\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:21\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:15\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:10\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:02\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:03\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:17:54\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:17:54\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:17:58\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:17:55\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:03\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:06\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:04\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:17:56\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:44\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:17:58\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:04\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:04\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:04\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:07\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:11\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:17\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:22\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:25\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:28\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:36\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:41\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:45\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:45\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:45\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:32\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:36\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:36\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:36\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:27\n", + " 0.0/3.1 GB 2.7 MB/s eta 0:18:36\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:22\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:12\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:12\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:08\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:17\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:07\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:18:17\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:17:58\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:39\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:39\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:44\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:17:49\n", + " 0.0/3.1 GB 2.8 MB/s eta 0:17:58\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:39\n", + " 0.0/3.1 GB 2.9 MB/s eta 0:17:30\n", + " 0.0/3.1 GB 3.0 MB/s eta 0:17:07\n", + " 0.0/3.1 GB 3.0 MB/s eta 0:16:53\n", + " 0.0/3.1 GB 3.0 MB/s eta 0:16:53\n", + " 0.0/3.1 GB 3.0 MB/s eta 0:16:52\n", + " 0.0/3.1 GB 3.0 MB/s eta 0:16:53\n", + " 0.0/3.1 GB 3.0 MB/s eta 0:16:53\n", + " 0.0/3.1 GB 3.0 MB/s eta 0:16:48\n", + " 0.0/3.1 GB 3.0 MB/s eta 0:16:47\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:34\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:29\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:24\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:24\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:20\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:15\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:15\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:15\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:19\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:15\n", + " 0.0/3.1 GB 3.2 MB/s eta 0:16:01\n", + " 0.0/3.1 GB 3.2 MB/s eta 0:15:56\n", + " 0.0/3.1 GB 3.2 MB/s eta 0:16:00\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:14\n", + " 0.0/3.1 GB 3.1 MB/s eta 0:16:14\n", + " 0.0/3.1 GB 3.2 MB/s eta 0:15:56\n", + " 0.0/3.1 GB 3.2 MB/s eta 0:15:47\n", + " 0.0/3.1 GB 3.3 MB/s eta 0:15:23\n", + " 0.0/3.1 GB 3.3 MB/s eta 0:15:09\n", + " 0.0/3.1 GB 3.4 MB/s eta 0:15:00\n", + " 0.0/3.1 GB 3.4 MB/s eta 0:14:51\n", + " 0.0/3.1 GB 3.5 MB/s eta 0:14:32\n", + " 0.0/3.1 GB 3.5 MB/s eta 0:14:32\n", + " 0.0/3.1 GB 3.5 MB/s eta 0:14:18\n", + " 0.0/3.1 GB 3.5 MB/s eta 0:14:23\n", + " 0.0/3.1 GB 3.5 MB/s eta 0:14:18\n", + " 0.0/3.1 GB 3.5 MB/s eta 0:14:18\n", + " 0.0/3.1 GB 3.6 MB/s eta 0:14:04\n", + " 0.0/3.1 GB 3.6 MB/s eta 0:13:54\n", + " 0.0/3.1 GB 3.6 MB/s eta 0:13:59\n", + " 0.0/3.1 GB 3.6 MB/s eta 0:13:59\n", + " 0.0/3.1 GB 3.6 MB/s eta 0:13:59\n", + " 0.0/3.1 GB 3.6 MB/s eta 0:13:54\n", + " 0.0/3.1 GB 3.7 MB/s eta 0:13:45\n", + " 0.0/3.1 GB 3.7 MB/s eta 0:13:45\n", + " 0.0/3.1 GB 3.7 MB/s eta 0:13:40\n", + " 0.0/3.1 GB 3.7 MB/s eta 0:13:31\n", + " 0.0/3.1 GB 3.7 MB/s eta 0:13:31\n", + " 0.0/3.1 GB 3.8 MB/s eta 0:13:17\n", + " 0.0/3.1 GB 3.8 MB/s eta 0:13:12\n", + " 0.0/3.1 GB 3.8 MB/s eta 0:13:12\n", + " 0.0/3.1 GB 3.9 MB/s eta 0:13:07\n", + " 0.0/3.1 GB 3.8 MB/s eta 0:13:12\n", + " 0.0/3.1 GB 4.0 MB/s eta 0:12:44\n", + " 0.0/3.1 GB 3.9 MB/s eta 0:12:53\n", + " 0.0/3.1 GB 4.0 MB/s eta 0:12:44\n", + " 0.0/3.1 GB 4.0 MB/s eta 0:12:44\n", + " 0.0/3.1 GB 4.0 MB/s eta 0:12:30\n", + " 0.0/3.1 GB 4.1 MB/s eta 0:12:26\n", + " 0.0/3.1 GB 4.1 MB/s eta 0:12:21\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:07\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:07\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:57\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:57\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:57\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:07\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:07\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:06\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:06\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:57\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:43\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:43\n", + " 0.0/3.1 GB 4.4 MB/s eta 0:11:29\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:11\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:15\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:11\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:15\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:15\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:19\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:15\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:10\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:10\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:10\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:10\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:15\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:19\n", + " 0.0/3.1 GB 4.5 MB/s eta 0:11:19\n", + " 0.0/3.1 GB 4.4 MB/s eta 0:11:24\n", + " 0.0/3.1 GB 4.4 MB/s eta 0:11:29\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:42\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:42\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:51\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:47\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:56\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:05\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:05\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:52\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:42\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:46\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:51\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:56\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:00\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:51\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:51\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:51\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:51\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:05\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:51\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:55\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:55\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:00\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:00\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:00\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:04\n", + " 0.0/3.1 GB 4.1 MB/s eta 0:12:09\n", + " 0.0/3.1 GB 4.1 MB/s eta 0:12:14\n", + " 0.0/3.1 GB 4.1 MB/s eta 0:12:14\n", + " 0.0/3.1 GB 4.1 MB/s eta 0:12:14\n", + " 0.0/3.1 GB 4.1 MB/s eta 0:12:09\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:04\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:04\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:59\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:59\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:55\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:50\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:50\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:59\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:54\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:54\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:40\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:45\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:45\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:54\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:59\n", + " 0.0/3.1 GB 4.1 MB/s eta 0:12:08\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:03\n", + " 0.0/3.1 GB 4.1 MB/s eta 0:12:08\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:03\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:03\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:03\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:03\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:03\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:49\n", + " 0.0/3.1 GB 4.4 MB/s eta 0:11:31\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:35\n", + " 0.0/3.1 GB 4.4 MB/s eta 0:11:31\n", + " 0.0/3.1 GB 4.4 MB/s eta 0:11:31\n", + " 0.0/3.1 GB 4.4 MB/s eta 0:11:31\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:35\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:40\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:44\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:40\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:40\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:44\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:49\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:39\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:44\n", + " 0.0/3.1 GB 4.4 MB/s eta 0:11:30\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:39\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:44\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:48\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:44\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:44\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:44\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:34\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:44\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:35\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:34\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:34\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:39\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:48\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:48\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:39\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:39\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:43\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:48\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:12:01\n", + " 0.0/3.1 GB 4.2 MB/s eta 0:11:52\n", + " 0.0/3.1 GB 4.3 MB/s eta 0:11:47\n", + " 0.1/3.1 GB 4.3 MB/s eta 0:11:47\n", + " 0.1/3.1 GB 4.2 MB/s eta 0:11:57\n", + " 0.1/3.1 GB 4.1 MB/s eta 0:12:06\n", + " 0.1/3.1 GB 4.1 MB/s eta 0:12:06\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:24\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:33\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:47\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:47\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:51\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:51\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:33\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:38\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:37\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:42\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:42\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:42\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:37\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:33\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:33\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:42\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:46\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:51\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:46\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:42\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:46\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:42\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:37\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:32\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:28\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:28\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:27\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:32\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:41\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:46\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:50\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:04\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:08\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:59\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:59\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:59\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:04\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:04\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:04\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:03\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:04\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:04\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:59\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:59\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:59\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:59\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:59\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:08\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:17\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:22\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:17\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:08\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:16\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:21\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:17\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:17\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:07\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:49\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:45\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:35\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:44\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:44\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:03\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:12\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:25\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:30\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:39\n", + " 0.1/3.1 GB 3.6 MB/s eta 0:13:43\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:39\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:34\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:39\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:34\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:30\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:25\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:16\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:16\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:15\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:29\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:34\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:34\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:34\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:34\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:34\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:38\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:33\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:24\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:20\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:20\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:15\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:01\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:06\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:52\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:52\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:01\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:52\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:01\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:01\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:05\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:10\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:15\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:10\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:05\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:52\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:52\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:42\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:42\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:42\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:51\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:56\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:05\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:14\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:09\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:14\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:10\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:09\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:14\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:18\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:23\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:23\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:14\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:32\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:28\n", + " 0.1/3.1 GB 4.1 MB/s eta 0:12:14\n", + " 0.1/3.1 GB 4.1 MB/s eta 0:12:10\n", + " 0.1/3.1 GB 4.1 MB/s eta 0:12:05\n", + " 0.1/3.1 GB 4.1 MB/s eta 0:12:09\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:19\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:28\n", + " 0.1/3.1 GB 4.0 MB/s eta 0:12:32\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:37\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:41\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:46\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:46\n", + " 0.1/3.1 GB 3.9 MB/s eta 0:12:50\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:08\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:12:59\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:08\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:13\n", + " 0.1/3.1 GB 3.8 MB/s eta 0:13:13\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:17\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:22\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:31\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:35\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:35\n", + " 0.1/3.1 GB 3.7 MB/s eta 0:13:35\n", + " 0.1/3.1 GB 3.6 MB/s eta 0:13:40\n", + " 0.1/3.1 GB 3.6 MB/s eta 0:13:49\n", + " 0.1/3.1 GB 3.6 MB/s eta 0:13:58\n", + " 0.1/3.1 GB 3.5 MB/s eta 0:14:03\n", + " 0.1/3.1 GB 3.5 MB/s eta 0:14:16\n", + " 0.1/3.1 GB 3.5 MB/s eta 0:14:21\n", + " 0.1/3.1 GB 3.4 MB/s eta 0:14:25\n", + " 0.1/3.1 GB 3.5 MB/s eta 0:14:21\n", + " 0.1/3.1 GB 3.4 MB/s eta 0:14:25\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:30\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:34\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:43\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:43\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:48\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:48\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:48\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:52\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:57\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:52\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:52\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:56\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:56\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:15:10\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:19\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:24\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:33\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:37\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:46\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:55\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:04\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:09\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:09\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:13\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:18\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:04\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:04\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:59\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:04\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:59\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:04\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:08\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:13\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:08\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:54\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:04\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:13\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:22\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:26\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:44\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:53\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:58\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:07\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:12\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:21\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:25\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:34\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:43\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:52\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:15\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:19\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:19\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:10\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:10\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:15\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:15\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:28\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:28\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:33\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:28\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:18:01\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:18:01\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:56\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:56\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:56\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:56\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:51\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:56\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:56\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:18:00\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:05\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:09\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:18:00\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:55\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:42\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:42\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:46\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:42\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:42\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:51\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:55\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:18:00\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:51\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:55\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:51\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:55\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:55\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:04\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:08\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:08\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:13\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:08\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:08\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:13\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:59\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:59\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:50\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:50\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:54\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:08\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:08\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:08\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:35\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:31\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:21\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:26\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:30\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:30\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:26\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:39\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:25\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:35\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:30\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:39\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:44\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:44\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:43\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:53\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:01\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:01\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:57\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:06\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:15\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:10\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:15\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:48\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:43\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:48\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:52\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:57\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:48\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:34\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:29\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:29\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:16\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:16\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:29\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:20\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:11\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:11\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:20\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:02\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:02\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:57\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:11\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:11\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:10\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:19\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:24\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:19\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:29\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:29\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:42\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:42\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:55\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:51\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:42\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:33\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:42\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:46\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:51\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:59\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:55\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:13\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:13\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:27\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:22\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:27\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:27\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:54\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:58\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:58\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:58\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:58\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:58\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:11\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:16\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:16\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:34\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:39\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:48\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:06\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:06\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:24\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:24\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:37\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:37\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:51\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:37\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:42\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:46\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:00\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:09\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:22\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:27\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:26\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:36\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:40\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:40\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:36\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:31\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:40\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:44\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:49\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:35\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:35\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:13\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:12\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:22\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:26\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:39\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:48\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:44\n", + " - 0.1/3.1 GB 2.1 MB/s eta 0:22:58\n", + " - 0.1/3.1 GB 2.1 MB/s eta 0:23:06\n", + " - 0.1/3.1 GB 2.1 MB/s eta 0:23:15\n", + " - 0.1/3.1 GB 2.1 MB/s eta 0:23:11\n", + " - 0.1/3.1 GB 2.1 MB/s eta 0:23:15\n", + " - 0.1/3.1 GB 2.1 MB/s eta 0:23:20\n", + " - 0.1/3.1 GB 2.1 MB/s eta 0:23:11\n", + " - 0.1/3.1 GB 2.1 MB/s eta 0:23:15\n", + " - 0.1/3.1 GB 2.1 MB/s eta 0:23:11\n", + " - 0.1/3.1 GB 2.1 MB/s eta 0:23:06\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:52\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:43\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:39\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:22:21\n", + " - 0.1/3.1 GB 2.2 MB/s eta 0:21:58\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:44\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:40\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:30\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:22\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:12\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:03\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:12\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:03\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:08\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:21:12\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:54\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:20:58\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:49\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:45\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:49\n", + " - 0.1/3.1 GB 2.3 MB/s eta 0:20:58\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:49\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:45\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:40\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:31\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:35\n", + " - 0.1/3.1 GB 2.4 MB/s eta 0:20:26\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:55\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:46\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:36\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:36\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:41\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:23\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:51\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:46\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:19\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:24\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:15\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:48\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:58\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:36\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:22\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:08\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:08\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:37\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:10\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:52\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:38\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:42\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:16\n", + " - 0.1/3.1 GB 3.5 MB/s eta 0:14:11\n", + " - 0.1/3.1 GB 3.5 MB/s eta 0:14:06\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:15\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:20\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:35\n", + " - 0.1/3.1 GB 3.7 MB/s eta 0:13:21\n", + " - 0.1/3.1 GB 3.7 MB/s eta 0:13:17\n", + " - 0.1/3.1 GB 3.7 MB/s eta 0:13:26\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:35\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:35\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:35\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:48\n", + " - 0.1/3.1 GB 3.5 MB/s eta 0:13:52\n", + " - 0.1/3.1 GB 3.5 MB/s eta 0:14:02\n", + " - 0.1/3.1 GB 3.5 MB/s eta 0:14:06\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:15\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:20\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:24\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:24\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:33\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:37\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:37\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:42\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:37\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:37\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:37\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:24\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:28\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:41\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:42\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:42\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:55\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:55\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:59\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:50\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:50\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:46\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:55\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:59\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:15:04\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:15:04\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:13\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:21\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:21\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:21\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:53\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:57\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:02\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:16:02\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:11\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:11\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:42\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:33\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:47\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:47\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:51\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:00\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:09\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:14\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:09\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:09\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:09\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:09\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:09\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:13\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:00\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:55\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:59\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:46\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:37\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:23\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:23\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:23\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:19\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:14\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:18\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:19\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:27\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:32\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:41\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:45\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:49\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:45\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:07\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:12\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:21\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:21\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:39\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:48\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:30\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:34\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:39\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:43\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:48\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:52\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:01\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:56\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:38\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:34\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:25\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:25\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:38\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:30\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:30\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:16\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:07\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:02\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:11\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:15\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:15\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:20\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:29\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:29\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:33\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:15\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:20\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:15\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:20\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:15\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:15\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:28\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:42\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:46\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:00\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:00\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:09\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:18\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:13\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:13\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:04\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:08\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:24\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:37\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:41\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:33\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:37\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:41\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:28\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:19\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:19\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:28\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:28\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:50\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:55\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:46\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:59\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:59\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:04\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:04\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:17\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:35\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:39\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:35\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:35\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:43\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:48\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:57\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:01\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:01\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:06\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:10\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:10\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:15\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:19\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:19\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:23\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:23\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:23\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:32\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:27\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:32\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:32\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:36\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:45\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:41\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:32\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:36\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:32\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:18\n", + " - 0.1/3.1 GB 2.5 MB/s eta 0:19:13\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:51\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:42\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:37\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:29\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:24\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:24\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:10\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:10\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:24\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:28\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:19\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:06\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:10\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:24\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:24\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:28\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:28\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:32\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:41\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:46\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:50\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:55\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:59\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:59\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:54\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:59\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:19:03\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:54\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:58\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:54\n", + " - 0.1/3.1 GB 2.6 MB/s eta 0:18:41\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:18\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:18:18\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:51\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:51\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:51\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:56\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:51\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:33\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:07\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:17:02\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:53\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:08\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:55\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:28\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:19\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:19\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:10\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:19\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:19\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:24\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:19\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:23\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:19\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:23\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:14\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:28\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:36\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:37\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:50\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:45\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:54\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:15:59\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:15:58\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:50\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:49\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:45\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:36\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:36\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:45\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:45\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:40\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:31\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:31\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:27\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:40\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:49\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:49\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:49\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:49\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:49\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:49\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:49\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:49\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:49\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:32\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:40\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:58\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:49\n", + " - 0.1/3.1 GB 2.7 MB/s eta 0:17:44\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:40\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:09\n", + " - 0.1/3.1 GB 2.8 MB/s eta 0:17:04\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:46\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:55\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:51\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:37\n", + " - 0.1/3.1 GB 2.9 MB/s eta 0:16:37\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:24\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:16:19\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:52\n", + " - 0.1/3.1 GB 3.0 MB/s eta 0:15:57\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:53\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:53\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:52\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:44\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:34\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:30\n", + " - 0.1/3.1 GB 3.1 MB/s eta 0:15:30\n", + " - 0.1/3.1 GB 3.2 MB/s eta 0:15:12\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:50\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:41\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:32\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:32\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:36\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:36\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:32\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:45\n", + " - 0.1/3.1 GB 3.3 MB/s eta 0:14:31\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:09\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:09\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:04\n", + " - 0.1/3.1 GB 3.4 MB/s eta 0:14:13\n", + " - 0.1/3.1 GB 3.5 MB/s eta 0:14:00\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:38\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:24\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:25\n", + " - 0.1/3.1 GB 3.7 MB/s eta 0:13:02\n", + " - 0.1/3.1 GB 3.7 MB/s eta 0:13:11\n", + " - 0.1/3.1 GB 3.7 MB/s eta 0:13:06\n", + " - 0.1/3.1 GB 3.7 MB/s eta 0:13:06\n", + " - 0.1/3.1 GB 3.7 MB/s eta 0:13:15\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:24\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:28\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:28\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:24\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:19\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:24\n", + " - 0.1/3.1 GB 3.6 MB/s eta 0:13:33\n", + " - 0.2/3.1 GB 3.6 MB/s eta 0:13:28\n", + " - 0.2/3.1 GB 3.7 MB/s eta 0:13:10\n", + " - 0.2/3.1 GB 4.3 MB/s eta 0:11:15\n", + " - 0.2/3.1 GB 4.4 MB/s eta 0:11:02\n", + " - 0.2/3.1 GB 4.3 MB/s eta 0:11:11\n", + " - 0.2/3.1 GB 4.3 MB/s eta 0:11:11\n", + " - 0.2/3.1 GB 4.4 MB/s eta 0:11:01\n", + " - 0.2/3.1 GB 4.3 MB/s eta 0:11:10\n", + " - 0.2/3.1 GB 4.3 MB/s eta 0:11:24\n", + " - 0.2/3.1 GB 4.2 MB/s eta 0:11:33\n", + " - 0.2/3.1 GB 4.2 MB/s eta 0:11:37\n", + " - 0.2/3.1 GB 4.1 MB/s eta 0:11:46\n", + " - 0.2/3.1 GB 4.1 MB/s eta 0:11:55\n", + " - 0.2/3.1 GB 4.0 MB/s eta 0:11:59\n", + " - 0.2/3.1 GB 4.0 MB/s eta 0:11:59\n", + " - 0.2/3.1 GB 4.0 MB/s eta 0:11:59\n", + " - 0.2/3.1 GB 4.1 MB/s eta 0:11:55\n", + " - 0.2/3.1 GB 4.1 MB/s eta 0:11:46\n", + " - 0.2/3.1 GB 4.1 MB/s eta 0:11:50\n", + " - 0.2/3.1 GB 4.1 MB/s eta 0:11:41\n", + " -- 0.2/3.1 GB 4.0 MB/s eta 0:11:59\n", + " -- 0.2/3.1 GB 4.0 MB/s eta 0:12:08\n", + " -- 0.2/3.1 GB 4.0 MB/s eta 0:12:12\n", + " -- 0.2/3.1 GB 4.0 MB/s eta 0:12:08\n", + " -- 0.2/3.1 GB 3.9 MB/s eta 0:12:21\n", + " -- 0.2/3.1 GB 4.0 MB/s eta 0:12:08\n", + " -- 0.2/3.1 GB 3.9 MB/s eta 0:12:16\n", + " -- 0.2/3.1 GB 4.0 MB/s eta 0:12:12\n", + " -- 0.2/3.1 GB 3.9 MB/s eta 0:12:30\n", + " -- 0.2/3.1 GB 3.9 MB/s eta 0:12:34\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:43\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:38\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:47\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:47\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:56\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:00\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:09\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:18\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:27\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:36\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:40\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:53\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:44\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:58\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:53\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:58\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:06\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:53\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:06\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:57\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:02\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:06\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:02\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:06\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:06\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:06\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:28\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:33\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:32\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:46\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:46\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:59\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:59\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:08\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:07\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:12\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:59\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:45\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:36\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:41\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:45\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:45\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:41\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:45\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:41\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:45\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:49\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:54\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:45\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:45\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:03\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:11\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:11\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:49\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:36\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:27\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:27\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:22\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:27\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:31\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:40\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:44\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:49\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:26\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:31\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:22\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:26\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:22\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:22\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:04\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:08\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:04\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:00\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:04\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:50\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:42\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:28\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:24\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:11\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:02\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:01\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:02\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:06\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:10\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:06\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:06\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:06\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:19\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:15\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:01\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:01\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:19\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:27\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:23\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:23\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:14\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:19\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:14\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:14\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:23\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:23\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:23\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:27\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:40\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:45\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:54\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:49\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:45\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:49\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:02\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:02\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:20\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:29\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:38\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:37\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:42\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:46\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:46\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:55\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:08\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:59\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:50\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:04\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:03\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:03\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:21\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:17\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:17\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:30\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:30\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:08\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:03\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:08\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:08\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:12\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:21\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:25\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:29\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:16\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:21\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:25\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:29\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:34\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:29\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:33\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:33\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:29\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:33\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:29\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:37\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:33\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:33\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:33\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:37\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:33\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:33\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:33\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:32\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:28\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:28\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:28\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:37\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:37\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:59\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:16:03\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:16:12\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:16:03\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:16:08\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:59\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:58\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:59\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:28\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:23\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:32\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:28\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:28\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:32\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:32\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:23\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:27\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:19\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:10\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:57\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:52\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:52\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:56\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:56\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:25\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:34\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:21\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:17\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:03\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:13:59\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:33\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:15\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:02\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:53\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:53\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:10\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:01\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:06\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:14\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:23\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:14\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:19\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:19\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:18\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:18\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:19\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:18\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:18\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:19\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:18\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:23\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:23\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:14\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:23\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:18\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:09\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:14\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:18\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:18\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:13\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:13\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:13\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:22\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:42\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:34\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:29\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:34\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:38\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:34\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:42\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:47\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:51\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:51\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:42\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:34\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:34\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:29\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:33\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:42\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:46\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:46\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:51\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:59\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:42\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:33\n", + " -- 0.2/3.1 GB 3.9 MB/s eta 0:12:24\n", + " -- 0.2/3.1 GB 3.8 MB/s eta 0:12:29\n", + " -- 0.2/3.1 GB 3.9 MB/s eta 0:12:20\n", + " -- 0.2/3.1 GB 3.9 MB/s eta 0:12:20\n", + " -- 0.2/3.1 GB 3.9 MB/s eta 0:12:20\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:59\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:13:03\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:12\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:12\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:12\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:21\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:34\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:43\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:34\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:43\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:47\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:13:51\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:13:51\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:13:51\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:38\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:42\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:47\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:13:51\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:04\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:08\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:13\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:13\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:17\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:21\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:30\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:30\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:30\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:39\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:43\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:47\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:51\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:00\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:09\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:18\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:18\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:26\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:26\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:35\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:35\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:39\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:39\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:53\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:57\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:16:05\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:16:05\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:14\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:16:05\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:10\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:14\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:18\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:23\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:14\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:22\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:13\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:18\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:22\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:14\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:14\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:35\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:35\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:35\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:39\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:48\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:52\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:44\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:48\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:44\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:39\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:35\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:35\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:34\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:39\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:43\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:48\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:56\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:17\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:25\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:21\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:25\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:30\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:30\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:21\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:16\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:16\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:21\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:08\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:21\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:16\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:16\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:16\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:07\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:45\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:37\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:41\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:41\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:41\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:37\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:41\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:32\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:23\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:01\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:15:01\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:06\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:53\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:39\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:44\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:39\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:00\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:05\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:09\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:17\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:04\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:00\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:13:51\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:42\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:13:51\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:00\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:13:55\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:08\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:00\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:04\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:04\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:13:46\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:37\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:33\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:20\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:29\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:20\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:29\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:20\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:33\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:28\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:33\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:37\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:33\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:24\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:28\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:24\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:28\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:19\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:11\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:06\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:06\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:02\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:02\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:06\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:49\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:48\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:44\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:48\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:53\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:06\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.7 MB/s eta 0:12:57\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:06\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:10\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:10\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:05\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:05\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:06\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:10\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:10\n", + " -- 0.2/3.1 GB 3.6 MB/s eta 0:13:14\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:31\n", + " -- 0.2/3.1 GB 3.5 MB/s eta 0:13:35\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:13:49\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:13:49\n", + " -- 0.2/3.1 GB 3.4 MB/s eta 0:14:06\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:15\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:19\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:28\n", + " -- 0.2/3.1 GB 3.3 MB/s eta 0:14:28\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:45\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:49\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:40\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:36\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:45\n", + " -- 0.2/3.1 GB 3.2 MB/s eta 0:14:49\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:06\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:11\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:28\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:28\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:36\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:41\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:54\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:02\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:58\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:53\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:45\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:40\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:36\n", + " -- 0.2/3.1 GB 3.1 MB/s eta 0:15:23\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:36\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:45\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:45\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:11\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:19\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:19\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:06\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:02\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:06\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:19\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:10\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:06\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:57\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:57\n", + " -- 0.2/3.1 GB 3.0 MB/s eta 0:15:57\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:06\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:01\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:01\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:06\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:01\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:10\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:14\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:09\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:09\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:14\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:14\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:01\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:09\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:09\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:22\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:26\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:31\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:31\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:35\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:39\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:43\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:48\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:52\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:17:01\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:17:05\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:13\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:17:09\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:17:00\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:17:05\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:17:09\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:13\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:13\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:13\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:17\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:22\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:17\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:17\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:17:04\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:56\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:47\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:43\n", + " -- 0.2/3.1 GB 2.9 MB/s eta 0:16:30\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:38\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:38\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:38\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:55\n", + " -- 0.2/3.1 GB 2.8 MB/s eta 0:16:55\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:26\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:39\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:43\n", + " -- 0.2/3.1 GB 2.6 MB/s eta 0:17:51\n", + " -- 0.2/3.1 GB 2.6 MB/s eta 0:17:56\n", + " -- 0.2/3.1 GB 2.6 MB/s eta 0:17:56\n", + " -- 0.2/3.1 GB 2.6 MB/s eta 0:17:51\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:43\n", + " -- 0.2/3.1 GB 2.6 MB/s eta 0:17:51\n", + " -- 0.2/3.1 GB 2.6 MB/s eta 0:17:55\n", + " -- 0.2/3.1 GB 2.6 MB/s eta 0:18:00\n", + " -- 0.2/3.1 GB 2.6 MB/s eta 0:17:51\n", + " -- 0.2/3.1 GB 2.7 MB/s eta 0:17:30\n", + " --- 0.2/3.1 GB 2.7 MB/s eta 0:17:38\n", + " --- 0.2/3.1 GB 2.7 MB/s eta 0:17:38\n", + " --- 0.2/3.1 GB 2.7 MB/s eta 0:17:42\n", + " --- 0.2/3.1 GB 2.7 MB/s eta 0:17:38\n", + " --- 0.2/3.1 GB 2.7 MB/s eta 0:17:46\n", + " --- 0.2/3.1 GB 2.6 MB/s eta 0:17:51\n", + " --- 0.2/3.1 GB 2.6 MB/s eta 0:17:59\n", + " --- 0.2/3.1 GB 2.6 MB/s eta 0:18:04\n", + " --- 0.2/3.1 GB 2.6 MB/s eta 0:17:59\n", + " --- 0.2/3.1 GB 2.7 MB/s eta 0:17:25\n", + " --- 0.2/3.1 GB 2.7 MB/s eta 0:17:29\n", + " --- 0.2/3.1 GB 2.7 MB/s eta 0:17:38\n", + " --- 0.2/3.1 GB 2.7 MB/s eta 0:17:46\n", + " --- 0.2/3.1 GB 2.6 MB/s eta 0:17:59\n", + " --- 0.2/3.1 GB 2.6 MB/s eta 0:18:04\n", + " --- 0.2/3.1 GB 2.6 MB/s eta 0:18:12\n", + " --- 0.2/3.1 GB 2.6 MB/s eta 0:18:21\n", + " --- 0.2/3.1 GB 2.6 MB/s eta 0:18:25\n", + " --- 0.2/3.1 GB 2.5 MB/s eta 0:18:38\n", + " --- 0.2/3.1 GB 2.5 MB/s eta 0:18:38\n", + " --- 0.2/3.1 GB 2.5 MB/s eta 0:18:42\n", + " --- 0.2/3.1 GB 2.5 MB/s eta 0:18:55\n", + " --- 0.2/3.1 GB 2.5 MB/s eta 0:18:59\n", + " --- 0.2/3.1 GB 2.5 MB/s eta 0:18:59\n", + " --- 0.2/3.1 GB 2.4 MB/s eta 0:19:17\n", + " --- 0.2/3.1 GB 2.4 MB/s eta 0:19:25\n", + " --- 0.2/3.1 GB 2.4 MB/s eta 0:19:38\n", + " --- 0.2/3.1 GB 2.4 MB/s eta 0:19:46\n", + " --- 0.2/3.1 GB 2.4 MB/s eta 0:19:47\n", + " --- 0.2/3.1 GB 2.4 MB/s eta 0:19:47\n", + " --- 0.2/3.1 GB 2.4 MB/s eta 0:19:47\n", + " --- 0.2/3.1 GB 2.4 MB/s eta 0:19:47\n", + " --- 0.2/3.1 GB 2.4 MB/s eta 0:19:47\n", + " --- 0.2/3.1 GB 2.4 MB/s eta 0:19:47\n", + " --- 0.2/3.1 GB 2.4 MB/s eta 0:19:47\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:13\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:13\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:13\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:52\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:05\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:13\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:22\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:13\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:30\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:21\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:21\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:30\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:30\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:21\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:12\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:12\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:29\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:34\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:38\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:29\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:34\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:34\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:33\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:25\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:25\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:12\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:46\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:50\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:41\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:21:54\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:41\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:50\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:21:58\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:21:58\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:16\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:16\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:07\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:07\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:07\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:02\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:21:53\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:32\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:19\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:15\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:20:57\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:01\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:01\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:01\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:01\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:01\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:01\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:45\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:23\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:06\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:20:57\n", + " --- 0.2/3.1 GB 2.3 MB/s eta 0:20:48\n", + " --- 0.2/3.1 GB 2.3 MB/s eta 0:20:48\n", + " --- 0.2/3.1 GB 2.3 MB/s eta 0:20:40\n", + " --- 0.2/3.1 GB 2.3 MB/s eta 0:20:40\n", + " --- 0.2/3.1 GB 2.3 MB/s eta 0:20:44\n", + " --- 0.2/3.1 GB 2.3 MB/s eta 0:20:39\n", + " --- 0.2/3.1 GB 2.3 MB/s eta 0:20:44\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:20:56\n", + " --- 0.2/3.1 GB 2.3 MB/s eta 0:20:48\n", + " --- 0.2/3.1 GB 2.3 MB/s eta 0:20:52\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:20:56\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:09\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:18\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:31\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:35\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:39\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:48\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:48\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:48\n", + " --- 0.2/3.1 GB 2.2 MB/s eta 0:21:48\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:22\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:22\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:44\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:35\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:48\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:52\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:35\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 2.1 MB/s eta 0:22:09\n", + " --- 0.2/3.1 GB 1.9 MB/s eta 0:24:57\n", + " --- 0.2/3.1 GB 1.9 MB/s eta 0:24:57\n", + " --- 0.2/3.1 GB 1.9 MB/s eta 0:24:57\n", + " --- 0.2/3.1 GB 1.9 MB/s eta 0:24:57\n", + " --- 0.2/3.1 GB 1.9 MB/s eta 0:24:57\n", + " --- 0.2/3.1 GB 1.9 MB/s eta 0:24:57\n", + " --- 0.2/3.1 GB 1.8 MB/s eta 0:26:05\n", + " --- 0.2/3.1 GB 1.8 MB/s eta 0:26:01\n", + " --- 0.2/3.1 GB 1.8 MB/s eta 0:26:01\n", + " --- 0.2/3.1 GB 1.8 MB/s eta 0:26:14\n", + " --- 0.2/3.1 GB 1.8 MB/s eta 0:26:14\n", + " --- 0.2/3.1 GB 1.8 MB/s eta 0:26:14\n", + " --- 0.2/3.1 GB 1.8 MB/s eta 0:26:14\n", + " --- 0.2/3.1 GB 1.8 MB/s eta 0:26:14\n", + " --- 0.2/3.1 GB 1.8 MB/s eta 0:26:14\n", + " --- 0.2/3.1 GB 1.8 MB/s eta 0:26:14\n", + " --- 0.2/3.1 GB 1.7 MB/s eta 0:27:40\n", + " --- 0.2/3.1 GB 1.7 MB/s eta 0:27:53\n", + " --- 0.2/3.1 GB 1.7 MB/s eta 0:27:53\n", + " --- 0.2/3.1 GB 1.7 MB/s eta 0:28:14\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:36\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:44\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:57\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:57\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:10\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:10\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:19\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:19\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:19\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:57\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:30:10\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:30:06\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:30:06\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:30:06\n", + " --- 0.2/3.1 GB 1.5 MB/s eta 0:30:19\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:30:06\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:30:06\n", + " --- 0.2/3.1 GB 1.5 MB/s eta 0:30:27\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:30:10\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:52\n", + " --- 0.2/3.1 GB 1.7 MB/s eta 0:28:22\n", + " --- 0.2/3.1 GB 1.7 MB/s eta 0:28:09\n", + " --- 0.2/3.1 GB 1.7 MB/s eta 0:28:05\n", + " --- 0.2/3.1 GB 1.7 MB/s eta 0:28:18\n", + " --- 0.2/3.1 GB 1.7 MB/s eta 0:28:13\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:30\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:43\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:52\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:52\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:09\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:18\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:22\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:39\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:39\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:52\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:52\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:56\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:56\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:30:00\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:30:05\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:30:13\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:56\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:47\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:51\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:55\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:55\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:38\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:38\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:42\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:42\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:20\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:16\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:58\n", + " --- 0.2/3.1 GB 1.7 MB/s eta 0:28:20\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:32\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:24\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:24\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:32\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:36\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:36\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:32\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:32\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:45\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:49\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:49\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:19\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:27\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:36\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:49\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:30:02\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:53\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:44\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:01\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:28:57\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:01\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:01\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:10\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:10\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:18\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:22\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:14\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:05\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:05\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:05\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:31\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:22\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:22\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:43\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:35\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:35\n", + " --- 0.2/3.1 GB 1.6 MB/s eta 0:29:43\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:29:17\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:29:22\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:29:17\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:28:47\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:28:26\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:28:17\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:28:17\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:28:17\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:28:43\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:28:47\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:29:00\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:29:00\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:29:21\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:29:25\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:29:25\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:29:25\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:30:04\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:08\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:13\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:59\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:51\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:55\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:55\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:17\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:47\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:08\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:16\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:12\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:20:55\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:20:59\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:20:51\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:29\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:29\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:29\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:29\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:29\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:08\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:20:55\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:33\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:12\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:12\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:12\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:29\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:29\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:20:50\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:20:54\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:20:54\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:03\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:03\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:07\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:11\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:20\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:20\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:32\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:32\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:45\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:50\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:58\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:58\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:19\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:19\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:19\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:19\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:23\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:32\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:36\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:32\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:36\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:49\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:57\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:57\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:57\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:57\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:57\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:57\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:57\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:18\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:18\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:18\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:18\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:18\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:18\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:36\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:53\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:01\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:52\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:48\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:44\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:43\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:52\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:56\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:05\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:52\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:25:09\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:43\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:52\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:25:00\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:43\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:26\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:34\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:30\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:30\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:30\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:30\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:25\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:43\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:51\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:55\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:34\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:34\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:12\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:12\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:12\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:46\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:21\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:25\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:25\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:38\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:38\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:55\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:55\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:25:07\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:25:03\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:12\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:25:03\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:42\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:42\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:42\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:20\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:24\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:29\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:20\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:24\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:20\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:20\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:33\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:41\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:41\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:41\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:41\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:50\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:50\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:58\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:58\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:54\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:58\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:25:06\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:49\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:23:45\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:23:54\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:23:49\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:23:54\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:23:53\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:23:10\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:23:06\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:58\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:49\n", + " --- 0.3/3.1 GB 2.0 MB/s eta 0:22:49\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:36\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:02\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:15\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:10\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:10\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:10\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:02\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:57\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:49\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:53\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:48\n", + " --- 0.3/3.1 GB 2.2 MB/s eta 0:21:36\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:15\n", + " --- 0.3/3.1 GB 2.4 MB/s eta 0:19:06\n", + " --- 0.3/3.1 GB 2.4 MB/s eta 0:19:02\n", + " --- 0.3/3.1 GB 2.4 MB/s eta 0:19:02\n", + " --- 0.3/3.1 GB 2.4 MB/s eta 0:19:28\n", + " --- 0.3/3.1 GB 2.4 MB/s eta 0:19:28\n", + " --- 0.3/3.1 GB 2.4 MB/s eta 0:19:36\n", + " --- 0.3/3.1 GB 2.4 MB/s eta 0:19:40\n", + " --- 0.3/3.1 GB 2.4 MB/s eta 0:19:45\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:19:49\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:06\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:06\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:06\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:06\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:06\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:06\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:06\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:06\n", + " --- 0.3/3.1 GB 2.3 MB/s eta 0:20:06\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:57\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:21:57\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:27\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:35\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:35\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:35\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:35\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:35\n", + " --- 0.3/3.1 GB 2.1 MB/s eta 0:22:35\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:23:52\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:00\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:09\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:21\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:30\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:38\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:38\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:51\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:55\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:55\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:55\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:55\n", + " --- 0.3/3.1 GB 1.9 MB/s eta 0:24:55\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:55\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:59\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:59\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:59\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:59\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:50\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:03\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:03\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:11\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:24\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:33\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:33\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:41\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:41\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:49\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:53\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:28:02\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:28:02\n", + " --- 0.3/3.1 GB 1.6 MB/s eta 0:28:10\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:28:06\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:11\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:23\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:10\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:53\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:02\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:53\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:19\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:27\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:36\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:02\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:23\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:32\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:36\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:36\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:02\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:02\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:14\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:18\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:22\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:48\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:44\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:25:44\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:01\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:14\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:23\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:31\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:48\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:01\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:56\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:01\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:01\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:00\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:56\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:56\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:18\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:09\n", + " --- 0.3/3.1 GB 1.8 MB/s eta 0:26:09\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:39\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:34\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:34\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:26:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:00\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:00\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:34\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:42\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.7 MB/s eta 0:27:47\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:30:32\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:30:32\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:30:53\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:31:02\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:31:06\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:31:06\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:31:40\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:31:49\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:31:49\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:31:49\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:31:49\n", + " --- 0.3/3.1 GB 1.5 MB/s eta 0:31:49\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:32:44\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:32:44\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:32:57\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:32:57\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:33:18\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:33:18\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:33:26\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:33:22\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:33:22\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:33:22\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:34:00\n", + " --- 0.3/3.1 GB 1.4 MB/s eta 0:34:00\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:34:25\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:34:30\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:34:47\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:34:47\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:34:55\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:34:59\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:35:08\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:34:59\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:35:07\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:35:16\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:35:24\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:35:33\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:35:33\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:35:54\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:35:58\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:35:58\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:36:32\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:36:36\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:36:53\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:36:32\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:36:27\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:36:32\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:36:36\n", + " --- 0.3/3.1 GB 1.3 MB/s eta 0:36:36\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:37:05\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:37:18\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:37:18\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:37:18\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:37:18\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:37:18\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:37:18\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:37:18\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:37:18\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:37:18\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:38:51\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:38:51\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:38:51\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:39:34\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:39:42\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:04\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:40:16\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:36\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:36\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:10\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:10\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:35\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:35\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:48\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:05\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:18\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:18\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:18\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:56\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:56\n", + " --- 0.3/3.1 GB 999.6 kB/s eta 0:46:21\n", + " --- 0.3/3.1 GB 999.6 kB/s eta 0:46:21\n", + " --- 0.3/3.1 GB 999.6 kB/s eta 0:46:21\n", + " --- 0.3/3.1 GB 987.5 kB/s eta 0:46:55\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 986.0 kB/s eta 0:46:59\n", + " --- 0.3/3.1 GB 923.4 kB/s eta 0:50:10\n", + " --- 0.3/3.1 GB 923.4 kB/s eta 0:50:10\n", + " --- 0.3/3.1 GB 916.9 kB/s eta 0:50:32\n", + " --- 0.3/3.1 GB 911.8 kB/s eta 0:50:49\n", + " --- 0.3/3.1 GB 911.8 kB/s eta 0:50:49\n", + " --- 0.3/3.1 GB 904.3 kB/s eta 0:51:14\n", + " --- 0.3/3.1 GB 903.0 kB/s eta 0:51:18\n", + " --- 0.3/3.1 GB 899.3 kB/s eta 0:51:31\n", + " --- 0.3/3.1 GB 898.1 kB/s eta 0:51:35\n", + " --- 0.3/3.1 GB 893.2 kB/s eta 0:51:52\n", + " --- 0.3/3.1 GB 893.2 kB/s eta 0:51:52\n", + " --- 0.3/3.1 GB 888.3 kB/s eta 0:52:09\n", + " --- 0.3/3.1 GB 888.3 kB/s eta 0:52:09\n", + " --- 0.3/3.1 GB 888.3 kB/s eta 0:52:09\n", + " --- 0.3/3.1 GB 877.6 kB/s eta 0:52:47\n", + " --- 0.3/3.1 GB 877.6 kB/s eta 0:52:47\n", + " --- 0.3/3.1 GB 874.1 kB/s eta 0:53:00\n", + " --- 0.3/3.1 GB 874.1 kB/s eta 0:53:00\n", + " --- 0.3/3.1 GB 874.1 kB/s eta 0:53:00\n", + " --- 0.3/3.1 GB 874.1 kB/s eta 0:53:00\n", + " --- 0.3/3.1 GB 861.5 kB/s eta 0:53:46\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:59\n", + " --- 0.3/3.1 GB 856.9 kB/s eta 0:54:03\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:59\n", + " --- 0.3/3.1 GB 868.3 kB/s eta 0:53:20\n", + " --- 0.3/3.1 GB 864.9 kB/s eta 0:53:33\n", + " --- 0.3/3.1 GB 862.6 kB/s eta 0:53:42\n", + " --- 0.3/3.1 GB 863.8 kB/s eta 0:53:37\n", + " --- 0.3/3.1 GB 863.8 kB/s eta 0:53:37\n", + " --- 0.3/3.1 GB 861.5 kB/s eta 0:53:46\n", + " --- 0.3/3.1 GB 866.0 kB/s eta 0:53:28\n", + " --- 0.3/3.1 GB 943.4 kB/s eta 0:49:05\n", + " --- 0.3/3.1 GB 942.0 kB/s eta 0:49:10\n", + " --- 0.3/3.1 GB 942.0 kB/s eta 0:49:10\n", + " --- 0.3/3.1 GB 942.0 kB/s eta 0:49:10\n", + " --- 0.3/3.1 GB 932.7 kB/s eta 0:49:39\n", + " --- 0.3/3.1 GB 937.9 kB/s eta 0:49:22\n", + " --- 0.3/3.1 GB 957.2 kB/s eta 0:48:22\n", + " --- 0.3/3.1 GB 974.3 kB/s eta 0:47:32\n", + " --- 0.3/3.1 GB 969.9 kB/s eta 0:47:44\n", + " --- 0.3/3.1 GB 971.4 kB/s eta 0:47:40\n", + " --- 0.3/3.1 GB 969.9 kB/s eta 0:47:44\n", + " --- 0.3/3.1 GB 971.3 kB/s eta 0:47:40\n", + " --- 0.3/3.1 GB 968.5 kB/s eta 0:47:48\n", + " --- 0.3/3.1 GB 968.5 kB/s eta 0:47:48\n", + " --- 0.3/3.1 GB 968.5 kB/s eta 0:47:48\n", + " --- 0.3/3.1 GB 961.4 kB/s eta 0:48:09\n", + " --- 0.3/3.1 GB 967.1 kB/s eta 0:47:52\n", + " --- 0.3/3.1 GB 965.7 kB/s eta 0:47:56\n", + " --- 0.3/3.1 GB 958.6 kB/s eta 0:48:17\n", + " --- 0.3/3.1 GB 962.8 kB/s eta 0:48:05\n", + " --- 0.3/3.1 GB 962.8 kB/s eta 0:48:05\n", + " --- 0.3/3.1 GB 968.5 kB/s eta 0:47:47\n", + " --- 0.3/3.1 GB 968.5 kB/s eta 0:47:47\n", + " --- 0.3/3.1 GB 965.7 kB/s eta 0:47:55\n", + " --- 0.3/3.1 GB 965.7 kB/s eta 0:47:55\n", + " --- 0.3/3.1 GB 965.7 kB/s eta 0:47:55\n", + " --- 0.3/3.1 GB 965.7 kB/s eta 0:47:55\n", + " --- 0.3/3.1 GB 965.7 kB/s eta 0:47:55\n", + " --- 0.3/3.1 GB 948.9 kB/s eta 0:48:46\n", + " --- 0.3/3.1 GB 946.1 kB/s eta 0:48:55\n", + " --- 0.3/3.1 GB 944.8 kB/s eta 0:48:59\n", + " --- 0.3/3.1 GB 944.7 kB/s eta 0:48:59\n", + " --- 0.3/3.1 GB 940.7 kB/s eta 0:49:11\n", + " --- 0.3/3.1 GB 939.4 kB/s eta 0:49:15\n", + " --- 0.3/3.1 GB 938.0 kB/s eta 0:49:20\n", + " --- 0.3/3.1 GB 936.6 kB/s eta 0:49:24\n", + " --- 0.3/3.1 GB 932.6 kB/s eta 0:49:37\n", + " --- 0.3/3.1 GB 928.6 kB/s eta 0:49:50\n", + " --- 0.3/3.1 GB 923.4 kB/s eta 0:50:06\n", + " --- 0.3/3.1 GB 918.2 kB/s eta 0:50:23\n", + " --- 0.3/3.1 GB 917.0 kB/s eta 0:50:27\n", + " --- 0.3/3.1 GB 915.7 kB/s eta 0:50:31\n", + " --- 0.3/3.1 GB 911.8 kB/s eta 0:50:44\n", + " --- 0.3/3.1 GB 911.8 kB/s eta 0:50:44\n", + " --- 0.3/3.1 GB 905.5 kB/s eta 0:51:05\n", + " --- 0.3/3.1 GB 903.0 kB/s eta 0:51:14\n", + " --- 0.3/3.1 GB 900.5 kB/s eta 0:51:22\n", + " --- 0.3/3.1 GB 898.1 kB/s eta 0:51:31\n", + " --- 0.3/3.1 GB 896.9 kB/s eta 0:51:35\n", + " --- 0.3/3.1 GB 896.9 kB/s eta 0:51:35\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:52:00\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:52:00\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:52:00\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:52:00\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:52:00\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:52:00\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:52:00\n", + " --- 0.3/3.1 GB 875.2 kB/s eta 0:52:51\n", + " --- 0.3/3.1 GB 875.2 kB/s eta 0:52:51\n", + " --- 0.3/3.1 GB 874.1 kB/s eta 0:52:55\n", + " --- 0.3/3.1 GB 884.8 kB/s eta 0:52:16\n", + " --- 0.3/3.1 GB 888.4 kB/s eta 0:52:03\n", + " --- 0.3/3.1 GB 887.2 kB/s eta 0:52:08\n", + " --- 0.3/3.1 GB 888.3 kB/s eta 0:52:03\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:51:59\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:51:59\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:51:59\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:51:59\n", + " --- 0.3/3.1 GB 889.5 kB/s eta 0:51:59\n", + " --- 0.3/3.1 GB 878.8 kB/s eta 0:52:37\n", + " --- 0.3/3.1 GB 890.8 kB/s eta 0:51:54\n", + " --- 0.3/3.1 GB 890.8 kB/s eta 0:51:54\n", + " --- 0.3/3.1 GB 890.8 kB/s eta 0:51:54\n", + " --- 0.3/3.1 GB 890.8 kB/s eta 0:51:54\n", + " --- 0.3/3.1 GB 890.8 kB/s eta 0:51:54\n", + " --- 0.3/3.1 GB 890.8 kB/s eta 0:51:54\n", + " --- 0.3/3.1 GB 890.8 kB/s eta 0:51:54\n", + " --- 0.3/3.1 GB 890.8 kB/s eta 0:51:54\n", + " --- 0.3/3.1 GB 864.9 kB/s eta 0:53:28\n", + " --- 0.3/3.1 GB 864.9 kB/s eta 0:53:28\n", + " --- 0.3/3.1 GB 864.9 kB/s eta 0:53:28\n", + " --- 0.3/3.1 GB 864.9 kB/s eta 0:53:28\n", + " --- 0.3/3.1 GB 864.9 kB/s eta 0:53:28\n", + " --- 0.3/3.1 GB 854.8 kB/s eta 0:54:06\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 858.1 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 811.3 kB/s eta 0:56:59\n", + " --- 0.3/3.1 GB 808.3 kB/s eta 0:57:12\n", + " --- 0.3/3.1 GB 808.3 kB/s eta 0:57:12\n", + " --- 0.3/3.1 GB 804.3 kB/s eta 0:57:29\n", + " --- 0.3/3.1 GB 804.3 kB/s eta 0:57:29\n", + " --- 0.3/3.1 GB 799.4 kB/s eta 0:57:50\n", + " --- 0.3/3.1 GB 795.5 kB/s eta 0:58:07\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:20\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:19\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:19\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:19\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:19\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:19\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:19\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:19\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:19\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:19\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:19\n", + " --- 0.3/3.1 GB 792.6 kB/s eta 0:58:19\n", + " --- 0.3/3.1 GB 762.2 kB/s eta 1:00:39\n", + " --- 0.3/3.1 GB 759.5 kB/s eta 1:00:52\n", + " --- 0.3/3.1 GB 757.8 kB/s eta 1:01:00\n", + " --- 0.3/3.1 GB 755.1 kB/s eta 1:01:13\n", + " --- 0.3/3.1 GB 754.2 kB/s eta 1:01:17\n", + " --- 0.3/3.1 GB 753.4 kB/s eta 1:01:21\n", + " --- 0.3/3.1 GB 757.8 kB/s eta 1:01:00\n", + " --- 0.3/3.1 GB 756.0 kB/s eta 1:01:08\n", + " --- 0.3/3.1 GB 756.0 kB/s eta 1:01:08\n", + " --- 0.3/3.1 GB 750.8 kB/s eta 1:01:34\n", + " --- 0.3/3.1 GB 749.9 kB/s eta 1:01:38\n", + " --- 0.3/3.1 GB 751.6 kB/s eta 1:01:29\n", + " --- 0.3/3.1 GB 803.3 kB/s eta 0:57:32\n", + " --- 0.3/3.1 GB 810.3 kB/s eta 0:57:02\n", + " --- 0.3/3.1 GB 841.5 kB/s eta 0:54:55\n", + " --- 0.3/3.1 GB 849.2 kB/s eta 0:54:25\n", + " --- 0.3/3.1 GB 849.2 kB/s eta 0:54:25\n", + " --- 0.3/3.1 GB 847.0 kB/s eta 0:54:33\n", + " --- 0.3/3.1 GB 844.8 kB/s eta 0:54:41\n", + " --- 0.3/3.1 GB 844.8 kB/s eta 0:54:41\n", + " --- 0.3/3.1 GB 844.8 kB/s eta 0:54:41\n", + " --- 0.3/3.1 GB 844.8 kB/s eta 0:54:41\n", + " --- 0.3/3.1 GB 855.8 kB/s eta 0:53:59\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:16\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:16\n", + " --- 0.3/3.1 GB 853.6 kB/s eta 0:54:07\n", + " --- 0.3/3.1 GB 853.6 kB/s eta 0:54:07\n", + " --- 0.3/3.1 GB 853.6 kB/s eta 0:54:07\n", + " --- 0.3/3.1 GB 853.6 kB/s eta 0:54:07\n", + " --- 0.3/3.1 GB 840.4 kB/s eta 0:54:58\n", + " --- 0.3/3.1 GB 840.4 kB/s eta 0:54:58\n", + " --- 0.3/3.1 GB 838.2 kB/s eta 0:55:06\n", + " --- 0.3/3.1 GB 839.4 kB/s eta 0:55:02\n", + " --- 0.3/3.1 GB 837.3 kB/s eta 0:55:10\n", + " --- 0.3/3.1 GB 839.4 kB/s eta 0:55:01\n", + " --- 0.3/3.1 GB 843.7 kB/s eta 0:54:44\n", + " --- 0.3/3.1 GB 856.9 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 856.9 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 856.9 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 856.9 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 856.9 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 856.9 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 856.9 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 856.9 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 856.9 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 856.9 kB/s eta 0:53:53\n", + " --- 0.3/3.1 GB 826.6 kB/s eta 0:55:52\n", + " --- 0.3/3.1 GB 827.6 kB/s eta 0:55:48\n", + " --- 0.3/3.1 GB 827.7 kB/s eta 0:55:47\n", + " --- 0.3/3.1 GB 829.8 kB/s eta 0:55:38\n", + " --- 0.3/3.1 GB 831.9 kB/s eta 0:55:30\n", + " --- 0.3/3.1 GB 839.4 kB/s eta 0:55:00\n", + " --- 0.3/3.1 GB 955.8 kB/s eta 0:48:18\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:29\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:45\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:39:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:39:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:39:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:39:16\n", + " --- 0.3/3.1 GB 1.2 MB/s eta 0:39:16\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:20\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:47\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:43\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:43\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:43\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:43\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:43\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:50\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:58\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:59\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:11\n", + " --- 0.3/3.1 GB 954.4 kB/s eta 0:48:21\n", + " --- 0.3/3.1 GB 953.0 kB/s eta 0:48:25\n", + " --- 0.3/3.1 GB 957.1 kB/s eta 0:48:13\n", + " --- 0.3/3.1 GB 961.4 kB/s eta 0:48:00\n", + " --- 0.3/3.1 GB 958.6 kB/s eta 0:48:08\n", + " --- 0.3/3.1 GB 958.6 kB/s eta 0:48:08\n", + " --- 0.3/3.1 GB 955.8 kB/s eta 0:48:16\n", + " --- 0.3/3.1 GB 967.1 kB/s eta 0:47:43\n", + " --- 0.3/3.1 GB 968.5 kB/s eta 0:47:38\n", + " --- 0.3/3.1 GB 969.9 kB/s eta 0:47:34\n", + " --- 0.3/3.1 GB 972.8 kB/s eta 0:47:25\n", + " --- 0.3/3.1 GB 974.3 kB/s eta 0:47:21\n", + " --- 0.3/3.1 GB 993.5 kB/s eta 0:46:26\n", + " --- 0.3/3.1 GB 993.5 kB/s eta 0:46:26\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:46:00\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:46:00\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:46:00\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:59\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:55\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:09\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:13\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:21\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:25\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:30\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:30\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:30\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:30\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:30\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 990.5 kB/s eta 0:46:33\n", + " --- 0.3/3.1 GB 939.4 kB/s eta 0:49:05\n", + " --- 0.3/3.1 GB 940.7 kB/s eta 0:49:01\n", + " --- 0.3/3.1 GB 938.0 kB/s eta 0:49:09\n", + " --- 0.3/3.1 GB 936.6 kB/s eta 0:49:13\n", + " --- 0.3/3.1 GB 931.2 kB/s eta 0:49:30\n", + " --- 0.3/3.1 GB 931.2 kB/s eta 0:49:30\n", + " --- 0.3/3.1 GB 928.7 kB/s eta 0:49:38\n", + " --- 0.3/3.1 GB 928.7 kB/s eta 0:49:38\n", + " --- 0.3/3.1 GB 928.7 kB/s eta 0:49:38\n", + " --- 0.3/3.1 GB 928.7 kB/s eta 0:49:38\n", + " --- 0.3/3.1 GB 928.7 kB/s eta 0:49:38\n", + " --- 0.3/3.1 GB 928.7 kB/s eta 0:49:38\n", + " --- 0.3/3.1 GB 928.7 kB/s eta 0:49:38\n", + " --- 0.3/3.1 GB 928.7 kB/s eta 0:49:38\n", + " --- 0.3/3.1 GB 910.6 kB/s eta 0:50:37\n", + " --- 0.3/3.1 GB 913.1 kB/s eta 0:50:29\n", + " --- 0.3/3.1 GB 910.6 kB/s eta 0:50:37\n", + " --- 0.3/3.1 GB 922.2 kB/s eta 0:49:59\n", + " --- 0.3/3.1 GB 919.5 kB/s eta 0:50:08\n", + " --- 0.3/3.1 GB 919.5 kB/s eta 0:50:08\n", + " --- 0.3/3.1 GB 919.5 kB/s eta 0:50:08\n", + " --- 0.3/3.1 GB 919.5 kB/s eta 0:50:08\n", + " --- 0.3/3.1 GB 903.0 kB/s eta 0:51:03\n", + " --- 0.3/3.1 GB 900.5 kB/s eta 0:51:11\n", + " --- 0.3/3.1 GB 899.3 kB/s eta 0:51:15\n", + " --- 0.3/3.1 GB 901.9 kB/s eta 0:51:07\n", + " --- 0.3/3.1 GB 896.9 kB/s eta 0:51:24\n", + " --- 0.3/3.1 GB 895.6 kB/s eta 0:51:28\n", + " --- 0.3/3.1 GB 895.6 kB/s eta 0:51:28\n", + " --- 0.3/3.1 GB 890.7 kB/s eta 0:51:45\n", + " --- 0.3/3.1 GB 896.9 kB/s eta 0:51:23\n", + " --- 0.3/3.1 GB 918.2 kB/s eta 0:50:12\n", + " --- 0.3/3.1 GB 914.4 kB/s eta 0:50:24\n", + " --- 0.3/3.1 GB 914.4 kB/s eta 0:50:24\n", + " --- 0.3/3.1 GB 904.2 kB/s eta 0:50:58\n", + " --- 0.3/3.1 GB 904.2 kB/s eta 0:50:58\n", + " --- 0.3/3.1 GB 904.2 kB/s eta 0:50:58\n", + " --- 0.3/3.1 GB 904.2 kB/s eta 0:50:58\n", + " --- 0.3/3.1 GB 904.2 kB/s eta 0:50:58\n", + " --- 0.3/3.1 GB 904.2 kB/s eta 0:50:58\n", + " --- 0.3/3.1 GB 904.2 kB/s eta 0:50:58\n", + " --- 0.3/3.1 GB 880.0 kB/s eta 0:52:22\n", + " --- 0.3/3.1 GB 880.0 kB/s eta 0:52:22\n", + " --- 0.3/3.1 GB 880.0 kB/s eta 0:52:22\n", + " --- 0.3/3.1 GB 880.0 kB/s eta 0:52:22\n", + " --- 0.3/3.1 GB 880.0 kB/s eta 0:52:22\n", + " --- 0.3/3.1 GB 880.0 kB/s eta 0:52:22\n", + " --- 0.3/3.1 GB 880.0 kB/s eta 0:52:22\n", + " --- 0.3/3.1 GB 880.0 kB/s eta 0:52:22\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 851.3 kB/s eta 0:54:08\n", + " --- 0.3/3.1 GB 816.3 kB/s eta 0:56:28\n", + " --- 0.3/3.1 GB 816.3 kB/s eta 0:56:28\n", + " --- 0.3/3.1 GB 816.3 kB/s eta 0:56:28\n", + " --- 0.3/3.1 GB 816.3 kB/s eta 0:56:28\n", + " --- 0.3/3.1 GB 802.3 kB/s eta 0:57:27\n", + " --- 0.3/3.1 GB 802.3 kB/s eta 0:57:27\n", + " --- 0.3/3.1 GB 802.3 kB/s eta 0:57:27\n", + " --- 0.3/3.1 GB 802.3 kB/s eta 0:57:27\n", + " --- 0.3/3.1 GB 790.7 kB/s eta 0:58:17\n", + " --- 0.3/3.1 GB 790.7 kB/s eta 0:58:17\n", + " --- 0.3/3.1 GB 790.7 kB/s eta 0:58:17\n", + " --- 0.3/3.1 GB 785.0 kB/s eta 0:58:42\n", + " --- 0.3/3.1 GB 785.0 kB/s eta 0:58:42\n", + " --- 0.3/3.1 GB 785.0 kB/s eta 0:58:42\n", + " --- 0.3/3.1 GB 785.0 kB/s eta 0:58:42\n", + " --- 0.3/3.1 GB 785.0 kB/s eta 0:58:42\n", + " --- 0.3/3.1 GB 785.0 kB/s eta 0:58:42\n", + " --- 0.3/3.1 GB 785.0 kB/s eta 0:58:42\n", + " --- 0.3/3.1 GB 764.0 kB/s eta 1:00:19\n", + " --- 0.3/3.1 GB 764.0 kB/s eta 1:00:19\n", + " --- 0.3/3.1 GB 761.3 kB/s eta 1:00:32\n", + " --- 0.3/3.1 GB 761.3 kB/s eta 1:00:32\n", + " --- 0.3/3.1 GB 756.9 kB/s eta 1:00:53\n", + " --- 0.3/3.1 GB 756.9 kB/s eta 1:00:53\n", + " --- 0.3/3.1 GB 750.8 kB/s eta 1:01:23\n", + " --- 0.3/3.1 GB 750.8 kB/s eta 1:01:23\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 746.5 kB/s eta 1:01:44\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 714.8 kB/s eta 1:04:28\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 589.3 kB/s eta 1:18:12\n", + " --- 0.3/3.1 GB 562.5 kB/s eta 1:21:56\n", + " --- 0.3/3.1 GB 562.5 kB/s eta 1:21:56\n", + " --- 0.3/3.1 GB 562.5 kB/s eta 1:21:56\n", + " --- 0.3/3.1 GB 562.5 kB/s eta 1:21:56\n", + " --- 0.3/3.1 GB 562.5 kB/s eta 1:21:56\n", + " --- 0.3/3.1 GB 562.5 kB/s eta 1:21:56\n", + " --- 0.3/3.1 GB 554.4 kB/s eta 1:23:07\n", + " --- 0.3/3.1 GB 554.4 kB/s eta 1:23:07\n", + " --- 0.3/3.1 GB 554.4 kB/s eta 1:23:07\n", + " --- 0.3/3.1 GB 554.4 kB/s eta 1:23:07\n", + " --- 0.3/3.1 GB 554.4 kB/s eta 1:23:07\n", + " --- 0.3/3.1 GB 547.0 kB/s eta 1:24:15\n", + " --- 0.3/3.1 GB 545.6 kB/s eta 1:24:28\n", + " --- 0.3/3.1 GB 545.6 kB/s eta 1:24:28\n", + " --- 0.3/3.1 GB 545.6 kB/s eta 1:24:28\n", + " --- 0.3/3.1 GB 545.6 kB/s eta 1:24:28\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 541.1 kB/s eta 1:25:10\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 520.8 kB/s eta 1:28:28\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 505.9 kB/s eta 1:31:05\n", + " --- 0.3/3.1 GB 396.5 kB/s eta 1:56:11\n", + " --- 0.3/3.1 GB 395.8 kB/s eta 1:56:24\n", + " --- 0.3/3.1 GB 395.8 kB/s eta 1:56:24\n", + " --- 0.3/3.1 GB 395.1 kB/s eta 1:56:37\n", + " --- 0.3/3.1 GB 394.4 kB/s eta 1:56:49\n", + " --- 0.3/3.1 GB 393.7 kB/s eta 1:57:02\n", + " --- 0.3/3.1 GB 393.2 kB/s eta 1:57:10\n", + " --- 0.3/3.1 GB 393.0 kB/s eta 1:57:14\n", + " --- 0.3/3.1 GB 393.0 kB/s eta 1:57:14\n", + " --- 0.3/3.1 GB 393.0 kB/s eta 1:57:14\n", + " --- 0.3/3.1 GB 390.9 kB/s eta 1:57:52\n", + " --- 0.3/3.1 GB 391.3 kB/s eta 1:57:43\n", + " --- 0.3/3.1 GB 395.6 kB/s eta 1:56:27\n", + " --- 0.3/3.1 GB 404.4 kB/s eta 1:53:55\n", + " --- 0.3/3.1 GB 404.6 kB/s eta 1:53:50\n", + " --- 0.3/3.1 GB 421.6 kB/s eta 1:49:15\n", + " --- 0.3/3.1 GB 421.6 kB/s eta 1:49:15\n", + " --- 0.3/3.1 GB 420.0 kB/s eta 1:49:40\n", + " --- 0.3/3.1 GB 428.5 kB/s eta 1:47:29\n", + " --- 0.3/3.1 GB 430.2 kB/s eta 1:47:04\n", + " --- 0.3/3.1 GB 430.7 kB/s eta 1:46:55\n", + " --- 0.3/3.1 GB 429.3 kB/s eta 1:47:16\n", + " --- 0.3/3.1 GB 429.3 kB/s eta 1:47:16\n", + " --- 0.3/3.1 GB 429.3 kB/s eta 1:47:16\n", + " --- 0.3/3.1 GB 431.6 kB/s eta 1:46:42\n", + " --- 0.3/3.1 GB 431.9 kB/s eta 1:46:37\n", + " --- 0.3/3.1 GB 431.9 kB/s eta 1:46:37\n", + " --- 0.3/3.1 GB 431.9 kB/s eta 1:46:37\n", + " --- 0.3/3.1 GB 430.5 kB/s eta 1:46:58\n", + " --- 0.3/3.1 GB 429.9 kB/s eta 1:47:06\n", + " --- 0.3/3.1 GB 429.6 kB/s eta 1:47:10\n", + " --- 0.3/3.1 GB 427.9 kB/s eta 1:47:35\n", + " --- 0.3/3.1 GB 427.6 kB/s eta 1:47:39\n", + " --- 0.3/3.1 GB 427.3 kB/s eta 1:47:43\n", + " --- 0.3/3.1 GB 426.2 kB/s eta 1:48:00\n", + " --- 0.3/3.1 GB 426.8 kB/s eta 1:47:51\n", + " --- 0.3/3.1 GB 426.8 kB/s eta 1:47:51\n", + " --- 0.3/3.1 GB 426.8 kB/s eta 1:47:51\n", + " --- 0.3/3.1 GB 426.0 kB/s eta 1:48:04\n", + " --- 0.3/3.1 GB 425.7 kB/s eta 1:48:07\n", + " --- 0.3/3.1 GB 427.9 kB/s eta 1:47:34\n", + " --- 0.3/3.1 GB 427.6 kB/s eta 1:47:38\n", + " --- 0.3/3.1 GB 427.6 kB/s eta 1:47:38\n", + " --- 0.3/3.1 GB 431.6 kB/s eta 1:46:38\n", + " --- 0.3/3.1 GB 430.7 kB/s eta 1:46:51\n", + " --- 0.3/3.1 GB 429.9 kB/s eta 1:47:03\n", + " --- 0.3/3.1 GB 429.3 kB/s eta 1:47:12\n", + " --- 0.3/3.1 GB 430.2 kB/s eta 1:46:58\n", + " --- 0.3/3.1 GB 430.2 kB/s eta 1:46:58\n", + " --- 0.3/3.1 GB 429.6 kB/s eta 1:47:07\n", + " --- 0.3/3.1 GB 429.9 kB/s eta 1:47:02\n", + " --- 0.3/3.1 GB 429.3 kB/s eta 1:47:10\n", + " --- 0.3/3.1 GB 429.0 kB/s eta 1:47:14\n", + " --- 0.3/3.1 GB 437.6 kB/s eta 1:45:07\n", + " --- 0.3/3.1 GB 437.6 kB/s eta 1:45:07\n", + " --- 0.3/3.1 GB 437.4 kB/s eta 1:45:11\n", + " --- 0.3/3.1 GB 437.6 kB/s eta 1:45:07\n", + " --- 0.3/3.1 GB 436.5 kB/s eta 1:45:23\n", + " --- 0.3/3.1 GB 437.6 kB/s eta 1:45:06\n", + " --- 0.3/3.1 GB 437.1 kB/s eta 1:45:14\n", + " --- 0.3/3.1 GB 436.5 kB/s eta 1:45:23\n", + " --- 0.3/3.1 GB 435.9 kB/s eta 1:45:31\n", + " --- 0.3/3.1 GB 434.7 kB/s eta 1:45:47\n", + " --- 0.3/3.1 GB 435.0 kB/s eta 1:45:43\n", + " --- 0.3/3.1 GB 435.0 kB/s eta 1:45:43\n", + " --- 0.3/3.1 GB 435.0 kB/s eta 1:45:43\n", + " --- 0.3/3.1 GB 435.0 kB/s eta 1:45:43\n", + " --- 0.3/3.1 GB 432.1 kB/s eta 1:46:25\n", + " --- 0.3/3.1 GB 432.1 kB/s eta 1:46:25\n", + " --- 0.3/3.1 GB 432.1 kB/s eta 1:46:25\n", + " --- 0.3/3.1 GB 429.6 kB/s eta 1:47:03\n", + " --- 0.3/3.1 GB 429.0 kB/s eta 1:47:11\n", + " --- 0.3/3.1 GB 428.2 kB/s eta 1:47:23\n", + " --- 0.3/3.1 GB 428.2 kB/s eta 1:47:23\n", + " --- 0.3/3.1 GB 427.6 kB/s eta 1:47:32\n", + " --- 0.3/3.1 GB 427.6 kB/s eta 1:47:32\n", + " --- 0.3/3.1 GB 454.3 kB/s eta 1:41:12\n", + " --- 0.3/3.1 GB 456.2 kB/s eta 1:40:46\n", + " --- 0.3/3.1 GB 456.2 kB/s eta 1:40:46\n", + " --- 0.3/3.1 GB 470.0 kB/s eta 1:37:49\n", + " --- 0.3/3.1 GB 470.0 kB/s eta 1:37:49\n", + " --- 0.3/3.1 GB 470.0 kB/s eta 1:37:49\n", + " --- 0.3/3.1 GB 470.0 kB/s eta 1:37:49\n", + " --- 0.3/3.1 GB 468.0 kB/s eta 1:38:14\n", + " --- 0.3/3.1 GB 468.0 kB/s eta 1:38:14\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:39\n", + " --- 0.3/3.1 GB 465.0 kB/s eta 1:38:52\n", + " --- 0.3/3.1 GB 465.0 kB/s eta 1:38:52\n", + " --- 0.3/3.1 GB 465.0 kB/s eta 1:38:52\n", + " --- 0.3/3.1 GB 465.0 kB/s eta 1:38:52\n", + " --- 0.3/3.1 GB 463.0 kB/s eta 1:39:17\n", + " --- 0.3/3.1 GB 463.0 kB/s eta 1:39:17\n", + " --- 0.3/3.1 GB 463.0 kB/s eta 1:39:17\n", + " --- 0.3/3.1 GB 460.1 kB/s eta 1:39:55\n", + " --- 0.3/3.1 GB 460.7 kB/s eta 1:39:46\n", + " --- 0.3/3.1 GB 460.4 kB/s eta 1:39:50\n", + " --- 0.3/3.1 GB 460.4 kB/s eta 1:39:49\n", + " --- 0.3/3.1 GB 460.4 kB/s eta 1:39:49\n", + " --- 0.3/3.1 GB 460.7 kB/s eta 1:39:45\n", + " --- 0.3/3.1 GB 461.0 kB/s eta 1:39:40\n", + " --- 0.3/3.1 GB 461.7 kB/s eta 1:39:31\n", + " --- 0.3/3.1 GB 461.4 kB/s eta 1:39:35\n", + " --- 0.3/3.1 GB 461.0 kB/s eta 1:39:39\n", + " --- 0.3/3.1 GB 461.4 kB/s eta 1:39:35\n", + " --- 0.3/3.1 GB 461.0 kB/s eta 1:39:39\n", + " --- 0.3/3.1 GB 460.7 kB/s eta 1:39:42\n", + " --- 0.3/3.1 GB 460.7 kB/s eta 1:39:42\n", + " --- 0.3/3.1 GB 458.5 kB/s eta 1:40:12\n", + " --- 0.3/3.1 GB 458.5 kB/s eta 1:40:12\n", + " --- 0.3/3.1 GB 456.5 kB/s eta 1:40:37\n", + " --- 0.3/3.1 GB 456.2 kB/s eta 1:40:41\n", + " --- 0.3/3.1 GB 455.3 kB/s eta 1:40:54\n", + " --- 0.3/3.1 GB 455.3 kB/s eta 1:40:54\n", + " --- 0.3/3.1 GB 454.0 kB/s eta 1:41:10\n", + " --- 0.3/3.1 GB 453.7 kB/s eta 1:41:14\n", + " --- 0.3/3.1 GB 453.7 kB/s eta 1:41:14\n", + " --- 0.3/3.1 GB 453.7 kB/s eta 1:41:14\n", + " --- 0.3/3.1 GB 451.8 kB/s eta 1:41:39\n", + " --- 0.3/3.1 GB 452.4 kB/s eta 1:41:31\n", + " --- 0.3/3.1 GB 452.8 kB/s eta 1:41:26\n", + " --- 0.3/3.1 GB 470.3 kB/s eta 1:37:39\n", + " --- 0.3/3.1 GB 471.0 kB/s eta 1:37:31\n", + " --- 0.3/3.1 GB 471.0 kB/s eta 1:37:31\n", + " --- 0.3/3.1 GB 471.0 kB/s eta 1:37:31\n", + " --- 0.3/3.1 GB 471.0 kB/s eta 1:37:31\n", + " --- 0.3/3.1 GB 468.0 kB/s eta 1:38:08\n", + " --- 0.3/3.1 GB 467.6 kB/s eta 1:38:12\n", + " --- 0.3/3.1 GB 467.6 kB/s eta 1:38:12\n", + " --- 0.3/3.1 GB 465.7 kB/s eta 1:38:37\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:34\n", + " --- 0.3/3.1 GB 447.5 kB/s eta 1:42:37\n", + " --- 0.3/3.1 GB 447.5 kB/s eta 1:42:37\n", + " --- 0.3/3.1 GB 445.4 kB/s eta 1:43:07\n", + " --- 0.3/3.1 GB 445.4 kB/s eta 1:43:07\n", + " --- 0.3/3.1 GB 444.5 kB/s eta 1:43:19\n", + " --- 0.3/3.1 GB 444.5 kB/s eta 1:43:19\n", + " --- 0.3/3.1 GB 442.7 kB/s eta 1:43:44\n", + " --- 0.3/3.1 GB 442.7 kB/s eta 1:43:44\n", + " --- 0.3/3.1 GB 442.4 kB/s eta 1:43:49\n", + " --- 0.3/3.1 GB 441.8 kB/s eta 1:43:57\n", + " --- 0.3/3.1 GB 440.3 kB/s eta 1:44:18\n", + " --- 0.3/3.1 GB 440.3 kB/s eta 1:44:18\n", + " --- 0.3/3.1 GB 439.1 kB/s eta 1:44:35\n", + " --- 0.3/3.1 GB 439.1 kB/s eta 1:44:35\n", + " --- 0.3/3.1 GB 439.1 kB/s eta 1:44:35\n", + " --- 0.3/3.1 GB 436.5 kB/s eta 1:45:13\n", + " --- 0.3/3.1 GB 435.9 kB/s eta 1:45:21\n", + " --- 0.3/3.1 GB 435.6 kB/s eta 1:45:25\n", + " --- 0.3/3.1 GB 435.6 kB/s eta 1:45:25\n", + " --- 0.3/3.1 GB 435.6 kB/s eta 1:45:25\n", + " --- 0.3/3.1 GB 435.6 kB/s eta 1:45:25\n", + " --- 0.3/3.1 GB 435.6 kB/s eta 1:45:25\n", + " --- 0.3/3.1 GB 431.3 kB/s eta 1:46:28\n", + " --- 0.3/3.1 GB 431.3 kB/s eta 1:46:28\n", + " --- 0.3/3.1 GB 433.6 kB/s eta 1:45:55\n", + " --- 0.3/3.1 GB 433.3 kB/s eta 1:45:59\n", + " --- 0.3/3.1 GB 433.3 kB/s eta 1:45:59\n", + " --- 0.3/3.1 GB 432.4 kB/s eta 1:46:11\n", + " --- 0.3/3.1 GB 432.4 kB/s eta 1:46:11\n", + " --- 0.3/3.1 GB 432.7 kB/s eta 1:46:07\n", + " --- 0.3/3.1 GB 432.7 kB/s eta 1:46:07\n", + " --- 0.3/3.1 GB 431.0 kB/s eta 1:46:32\n", + " --- 0.3/3.1 GB 432.4 kB/s eta 1:46:11\n", + " --- 0.3/3.1 GB 432.7 kB/s eta 1:46:07\n", + " --- 0.3/3.1 GB 469.6 kB/s eta 1:37:46\n", + " --- 0.3/3.1 GB 702.5 kB/s eta 1:05:21\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:40:15\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:21\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:33\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:41\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:42:47\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:42:47\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:42:17\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:42:12\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:42:12\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:42:12\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:42:12\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:42:59\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:42:59\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:42:59\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:28\n", + " --- 0.3/3.1 GB 1.1 MB/s eta 0:43:28\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:43:49\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:43:49\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:19\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:31\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:31\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:31\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:31\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:31\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:44:31\n", + " --- 0.3/3.1 GB 1.0 MB/s eta 0:45:47\n", + " --- 0.3/3.1 GB 998.0 kB/s eta 0:45:59\n", + " --- 0.3/3.1 GB 996.6 kB/s eta 0:46:03\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 992.0 kB/s eta 0:46:16\n", + " --- 0.3/3.1 GB 899.3 kB/s eta 0:51:02\n", + " --- 0.3/3.1 GB 899.3 kB/s eta 0:51:02\n", + " --- 0.3/3.1 GB 899.3 kB/s eta 0:51:02\n", + " --- 0.3/3.1 GB 899.3 kB/s eta 0:51:02\n", + " --- 0.3/3.1 GB 899.3 kB/s eta 0:51:02\n", + " --- 0.3/3.1 GB 899.3 kB/s eta 0:51:02\n", + " --- 0.3/3.1 GB 880.0 kB/s eta 0:52:09\n", + " --- 0.3/3.1 GB 880.0 kB/s eta 0:52:09\n", + " --- 0.3/3.1 GB 869.4 kB/s eta 0:52:47\n", + " --- 0.3/3.1 GB 869.4 kB/s eta 0:52:47\n", + " --- 0.3/3.1 GB 869.4 kB/s eta 0:52:47\n", + " --- 0.3/3.1 GB 869.4 kB/s eta 0:52:47\n", + " --- 0.3/3.1 GB 869.4 kB/s eta 0:52:47\n", + " --- 0.3/3.1 GB 869.4 kB/s eta 0:52:47\n", + " --- 0.3/3.1 GB 869.4 kB/s eta 0:52:47\n", + " --- 0.3/3.1 GB 847.0 kB/s eta 0:54:11\n", + " --- 0.3/3.1 GB 845.9 kB/s eta 0:54:16\n", + " --- 0.3/3.1 GB 845.9 kB/s eta 0:54:16\n", + " --- 0.3/3.1 GB 839.4 kB/s eta 0:54:41\n", + " --- 0.3/3.1 GB 836.2 kB/s eta 0:54:53\n", + " --- 0.3/3.1 GB 833.0 kB/s eta 0:55:06\n", + " --- 0.3/3.1 GB 829.8 kB/s eta 0:55:18\n", + " --- 0.3/3.1 GB 828.7 kB/s eta 0:55:23\n", + " --- 0.3/3.1 GB 828.7 kB/s eta 0:55:23\n", + " --- 0.3/3.1 GB 828.7 kB/s eta 0:55:23\n", + " --- 0.3/3.1 GB 828.7 kB/s eta 0:55:23\n", + " --- 0.3/3.1 GB 828.7 kB/s eta 0:55:23\n", + " --- 0.3/3.1 GB 828.7 kB/s eta 0:55:23\n", + " --- 0.3/3.1 GB 828.7 kB/s eta 0:55:23\n", + " --- 0.3/3.1 GB 828.7 kB/s eta 0:55:23\n", + " --- 0.3/3.1 GB 803.3 kB/s eta 0:57:08\n", + " --- 0.3/3.1 GB 802.3 kB/s eta 0:57:12\n", + " --- 0.3/3.1 GB 799.4 kB/s eta 0:57:24\n", + " --- 0.3/3.1 GB 803.3 kB/s eta 0:57:08\n", + " --- 0.3/3.1 GB 803.3 kB/s eta 0:57:08\n", + " --- 0.3/3.1 GB 797.5 kB/s eta 0:57:33\n", + " --- 0.3/3.1 GB 797.5 kB/s eta 0:57:33\n", + " --- 0.3/3.1 GB 797.5 kB/s eta 0:57:33\n", + " --- 0.3/3.1 GB 789.8 kB/s eta 0:58:06\n", + " --- 0.3/3.1 GB 789.8 kB/s eta 0:58:06\n", + " --- 0.3/3.1 GB 788.8 kB/s eta 0:58:10\n", + " --- 0.3/3.1 GB 794.5 kB/s eta 0:57:45\n", + " --- 0.3/3.1 GB 794.5 kB/s eta 0:57:45\n", + " --- 0.3/3.1 GB 794.5 kB/s eta 0:57:45\n", + " --- 0.3/3.1 GB 794.5 kB/s eta 0:57:45\n", + " --- 0.3/3.1 GB 794.5 kB/s eta 0:57:45\n", + " --- 0.3/3.1 GB 794.5 kB/s eta 0:57:45\n", + " --- 0.3/3.1 GB 794.5 kB/s eta 0:57:45\n", + " --- 0.3/3.1 GB 794.5 kB/s eta 0:57:45\n", + " --- 0.3/3.1 GB 794.5 kB/s eta 0:57:45\n", + " --- 0.3/3.1 GB 771.1 kB/s eta 0:59:30\n", + " --- 0.3/3.1 GB 769.3 kB/s eta 0:59:38\n", + " --- 0.3/3.1 GB 769.3 kB/s eta 0:59:38\n", + " --- 0.3/3.1 GB 769.3 kB/s eta 0:59:38\n", + " --- 0.3/3.1 GB 769.3 kB/s eta 0:59:38\n", + " --- 0.3/3.1 GB 769.3 kB/s eta 0:59:38\n", + " --- 0.3/3.1 GB 756.0 kB/s eta 1:00:41\n", + " --- 0.3/3.1 GB 754.3 kB/s eta 1:00:50\n", + " --- 0.3/3.1 GB 753.4 kB/s eta 1:00:54\n", + " --- 0.3/3.1 GB 751.7 kB/s eta 1:01:02\n", + " --- 0.3/3.1 GB 751.7 kB/s eta 1:01:02\n", + " --- 0.3/3.1 GB 748.3 kB/s eta 1:01:19\n", + " --- 0.3/3.1 GB 744.0 kB/s eta 1:01:40\n", + " --- 0.3/3.1 GB 744.0 kB/s eta 1:01:40\n", + " --- 0.3/3.1 GB 739.8 kB/s eta 1:02:01\n", + " --- 0.3/3.1 GB 738.1 kB/s eta 1:02:09\n", + " --- 0.3/3.1 GB 738.1 kB/s eta 1:02:09\n", + " --- 0.3/3.1 GB 738.1 kB/s eta 1:02:09\n", + " --- 0.3/3.1 GB 738.1 kB/s eta 1:02:09\n", + " --- 0.3/3.1 GB 738.1 kB/s eta 1:02:09\n", + " --- 0.3/3.1 GB 738.1 kB/s eta 1:02:09\n", + " --- 0.3/3.1 GB 738.1 kB/s eta 1:02:09\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 721.0 kB/s eta 1:03:38\n", + " --- 0.3/3.1 GB 686.3 kB/s eta 1:06:51\n", + " --- 0.3/3.1 GB 686.3 kB/s eta 1:06:51\n", + " --- 0.3/3.1 GB 686.3 kB/s eta 1:06:51\n", + " --- 0.3/3.1 GB 686.3 kB/s eta 1:06:51\n", + " --- 0.3/3.1 GB 686.3 kB/s eta 1:06:51\n", + " --- 0.3/3.1 GB 677.0 kB/s eta 1:07:46\n", + " --- 0.3/3.1 GB 675.0 kB/s eta 1:07:58\n", + " --- 0.3/3.1 GB 672.2 kB/s eta 1:08:15\n", + " --- 0.3/3.1 GB 670.8 kB/s eta 1:08:23\n", + " --- 0.3/3.1 GB 668.7 kB/s eta 1:08:36\n", + " --- 0.3/3.1 GB 668.7 kB/s eta 1:08:36\n", + " --- 0.3/3.1 GB 668.7 kB/s eta 1:08:36\n", + " --- 0.3/3.1 GB 663.3 kB/s eta 1:09:09\n", + " --- 0.3/3.1 GB 660.6 kB/s eta 1:09:26\n", + " --- 0.3/3.1 GB 662.6 kB/s eta 1:09:14\n", + " --- 0.3/3.1 GB 663.3 kB/s eta 1:09:09\n", + " --- 0.3/3.1 GB 663.3 kB/s eta 1:09:09\n", + " --- 0.3/3.1 GB 660.0 kB/s eta 1:09:30\n", + " --- 0.3/3.1 GB 660.0 kB/s eta 1:09:30\n", + " --- 0.3/3.1 GB 660.0 kB/s eta 1:09:30\n", + " --- 0.3/3.1 GB 660.0 kB/s eta 1:09:30\n", + " --- 0.3/3.1 GB 660.0 kB/s eta 1:09:30\n", + " --- 0.3/3.1 GB 660.0 kB/s eta 1:09:30\n", + " --- 0.3/3.1 GB 660.0 kB/s eta 1:09:30\n", + " --- 0.3/3.1 GB 660.0 kB/s eta 1:09:30\n", + " --- 0.3/3.1 GB 660.0 kB/s eta 1:09:30\n", + " --- 0.3/3.1 GB 660.0 kB/s eta 1:09:30\n", + " --- 0.3/3.1 GB 640.6 kB/s eta 1:11:36\n", + " --- 0.3/3.1 GB 640.6 kB/s eta 1:11:36\n", + " --- 0.3/3.1 GB 640.6 kB/s eta 1:11:36\n", + " --- 0.3/3.1 GB 640.6 kB/s eta 1:11:36\n", + " --- 0.3/3.1 GB 640.6 kB/s eta 1:11:36\n", + " --- 0.3/3.1 GB 640.6 kB/s eta 1:11:36\n", + " --- 0.3/3.1 GB 640.6 kB/s eta 1:11:36\n", + " --- 0.3/3.1 GB 640.6 kB/s eta 1:11:36\n", + " --- 0.3/3.1 GB 625.3 kB/s eta 1:13:21\n", + " --- 0.3/3.1 GB 623.5 kB/s eta 1:13:34\n", + " --- 0.3/3.1 GB 623.5 kB/s eta 1:13:34\n", + " --- 0.3/3.1 GB 621.2 kB/s eta 1:13:51\n", + " --- 0.3/3.1 GB 621.2 kB/s eta 1:13:51\n", + " --- 0.3/3.1 GB 621.2 kB/s eta 1:13:51\n", + " --- 0.3/3.1 GB 621.2 kB/s eta 1:13:51\n", + " --- 0.3/3.1 GB 621.2 kB/s eta 1:13:51\n", + " --- 0.3/3.1 GB 621.2 kB/s eta 1:13:51\n", + " --- 0.3/3.1 GB 621.2 kB/s eta 1:13:51\n", + " --- 0.3/3.1 GB 621.2 kB/s eta 1:13:51\n", + " --- 0.3/3.1 GB 606.8 kB/s eta 1:15:36\n", + " --- 0.3/3.1 GB 606.8 kB/s eta 1:15:36\n", + " --- 0.3/3.1 GB 606.8 kB/s eta 1:15:36\n", + " --- 0.3/3.1 GB 606.8 kB/s eta 1:15:36\n", + " --- 0.3/3.1 GB 600.1 kB/s eta 1:16:26\n", + " --- 0.3/3.1 GB 600.1 kB/s eta 1:16:26\n", + " --- 0.3/3.1 GB 600.1 kB/s eta 1:16:26\n", + " --- 0.3/3.1 GB 597.9 kB/s eta 1:16:43\n", + " --- 0.3/3.1 GB 597.9 kB/s eta 1:16:43\n", + " --- 0.3/3.1 GB 595.7 kB/s eta 1:17:00\n", + " --- 0.3/3.1 GB 595.7 kB/s eta 1:17:00\n", + " --- 0.3/3.1 GB 595.7 kB/s eta 1:17:00\n", + " --- 0.3/3.1 GB 595.7 kB/s eta 1:17:00\n", + " --- 0.3/3.1 GB 595.7 kB/s eta 1:17:00\n", + " --- 0.3/3.1 GB 588.8 kB/s eta 1:17:54\n", + " --- 0.3/3.1 GB 588.8 kB/s eta 1:17:54\n", + " --- 0.3/3.1 GB 588.8 kB/s eta 1:17:54\n", + " --- 0.3/3.1 GB 588.8 kB/s eta 1:17:54\n", + " --- 0.3/3.1 GB 582.0 kB/s eta 1:18:49\n", + " --- 0.3/3.1 GB 582.0 kB/s eta 1:18:49\n", + " --- 0.3/3.1 GB 578.9 kB/s eta 1:19:14\n", + " --- 0.3/3.1 GB 577.3 kB/s eta 1:19:27\n", + " --- 0.3/3.1 GB 577.4 kB/s eta 1:19:27\n", + " --- 0.3/3.1 GB 575.8 kB/s eta 1:19:39\n", + " --- 0.3/3.1 GB 574.3 kB/s eta 1:19:52\n", + " --- 0.3/3.1 GB 574.8 kB/s eta 1:19:48\n", + " --- 0.3/3.1 GB 572.8 kB/s eta 1:20:04\n", + " --- 0.3/3.1 GB 571.3 kB/s eta 1:20:17\n", + " --- 0.3/3.1 GB 571.3 kB/s eta 1:20:17\n", + " --- 0.3/3.1 GB 568.8 kB/s eta 1:20:38\n", + " --- 0.3/3.1 GB 568.8 kB/s eta 1:20:38\n", + " --- 0.3/3.1 GB 568.8 kB/s eta 1:20:38\n", + " --- 0.3/3.1 GB 565.9 kB/s eta 1:21:03\n", + " --- 0.3/3.1 GB 564.4 kB/s eta 1:21:16\n", + " --- 0.3/3.1 GB 564.4 kB/s eta 1:21:16\n", + " --- 0.3/3.1 GB 561.5 kB/s eta 1:21:41\n", + " --- 0.3/3.1 GB 561.5 kB/s eta 1:21:41\n", + " --- 0.3/3.1 GB 561.5 kB/s eta 1:21:41\n", + " --- 0.3/3.1 GB 561.5 kB/s eta 1:21:41\n", + " --- 0.3/3.1 GB 561.5 kB/s eta 1:21:41\n", + " --- 0.3/3.1 GB 561.5 kB/s eta 1:21:41\n", + " --- 0.3/3.1 GB 561.5 kB/s eta 1:21:41\n", + " --- 0.3/3.1 GB 561.5 kB/s eta 1:21:41\n", + " --- 0.3/3.1 GB 561.5 kB/s eta 1:21:41\n", + " --- 0.3/3.1 GB 561.5 kB/s eta 1:21:41\n", + " --- 0.3/3.1 GB 546.0 kB/s eta 1:24:00\n", + " --- 0.3/3.1 GB 546.9 kB/s eta 1:23:51\n", + " --- 0.3/3.1 GB 546.9 kB/s eta 1:23:51\n", + " --- 0.3/3.1 GB 546.5 kB/s eta 1:23:55\n", + " --- 0.3/3.1 GB 546.5 kB/s eta 1:23:55\n", + " --- 0.3/3.1 GB 546.5 kB/s eta 1:23:55\n", + " --- 0.3/3.1 GB 542.9 kB/s eta 1:24:29\n", + " --- 0.3/3.1 GB 542.9 kB/s eta 1:24:29\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 539.7 kB/s eta 1:24:58\n", + " --- 0.3/3.1 GB 493.0 kB/s eta 1:33:01\n", + " --- 0.3/3.1 GB 493.0 kB/s eta 1:33:01\n", + " --- 0.3/3.1 GB 493.0 kB/s eta 1:33:01\n", + " --- 0.3/3.1 GB 493.0 kB/s eta 1:33:01\n", + " --- 0.3/3.1 GB 488.6 kB/s eta 1:33:51\n", + " --- 0.3/3.1 GB 488.6 kB/s eta 1:33:51\n", + " --- 0.3/3.1 GB 488.6 kB/s eta 1:33:51\n", + " --- 0.3/3.1 GB 488.6 kB/s eta 1:33:51\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 484.2 kB/s eta 1:34:41\n", + " --- 0.3/3.1 GB 468.7 kB/s eta 1:37:50\n", + " --- 0.3/3.1 GB 468.7 kB/s eta 1:37:50\n", + " --- 0.3/3.1 GB 468.7 kB/s eta 1:37:50\n", + " --- 0.3/3.1 GB 466.0 kB/s eta 1:38:24\n", + " --- 0.3/3.1 GB 465.3 kB/s eta 1:38:32\n", + " --- 0.3/3.1 GB 465.0 kB/s eta 1:38:36\n", + " --- 0.3/3.1 GB 464.3 kB/s eta 1:38:45\n", + " --- 0.3/3.1 GB 464.3 kB/s eta 1:38:45\n", + " --- 0.3/3.1 GB 462.0 kB/s eta 1:39:14\n", + " --- 0.3/3.1 GB 462.0 kB/s eta 1:39:14\n", + " --- 0.3/3.1 GB 460.1 kB/s eta 1:39:39\n", + " --- 0.3/3.1 GB 460.1 kB/s eta 1:39:39\n", + " --- 0.3/3.1 GB 459.1 kB/s eta 1:39:52\n", + " --- 0.3/3.1 GB 459.1 kB/s eta 1:39:52\n", + " --- 0.3/3.1 GB 458.5 kB/s eta 1:40:00\n", + " --- 0.3/3.1 GB 457.2 kB/s eta 1:40:17\n", + " --- 0.3/3.1 GB 457.2 kB/s eta 1:40:17\n", + " --- 0.3/3.1 GB 455.6 kB/s eta 1:40:38\n", + " --- 0.3/3.1 GB 455.3 kB/s eta 1:40:42\n", + " --- 0.3/3.1 GB 453.7 kB/s eta 1:41:03\n", + " --- 0.3/3.1 GB 453.4 kB/s eta 1:41:07\n", + " --- 0.3/3.1 GB 452.5 kB/s eta 1:41:20\n", + " --- 0.3/3.1 GB 451.8 kB/s eta 1:41:28\n", + " --- 0.3/3.1 GB 450.6 kB/s eta 1:41:45\n", + " --- 0.3/3.1 GB 451.5 kB/s eta 1:41:32\n", + " --- 0.3/3.1 GB 450.9 kB/s eta 1:41:40\n", + " --- 0.3/3.1 GB 450.0 kB/s eta 1:41:53\n", + " --- 0.3/3.1 GB 449.7 kB/s eta 1:41:57\n", + " --- 0.3/3.1 GB 448.4 kB/s eta 1:42:14\n", + " --- 0.3/3.1 GB 447.8 kB/s eta 1:42:22\n", + " --- 0.3/3.1 GB 447.8 kB/s eta 1:42:22\n", + " --- 0.3/3.1 GB 446.6 kB/s eta 1:42:39\n", + " --- 0.3/3.1 GB 446.6 kB/s eta 1:42:39\n", + " --- 0.3/3.1 GB 446.6 kB/s eta 1:42:39\n", + " --- 0.3/3.1 GB 446.6 kB/s eta 1:42:39\n", + " --- 0.3/3.1 GB 446.6 kB/s eta 1:42:39\n", + " --- 0.3/3.1 GB 446.6 kB/s eta 1:42:39\n", + " --- 0.3/3.1 GB 446.6 kB/s eta 1:42:39\n", + " --- 0.3/3.1 GB 446.6 kB/s eta 1:42:39\n", + " --- 0.3/3.1 GB 446.6 kB/s eta 1:42:39\n", + " --- 0.3/3.1 GB 446.6 kB/s eta 1:42:39\n", + " --- 0.3/3.1 GB 437.3 kB/s eta 1:44:49\n", + " --- 0.3/3.1 GB 436.8 kB/s eta 1:44:57\n", + " --- 0.3/3.1 GB 436.8 kB/s eta 1:44:57\n", + " --- 0.3/3.1 GB 436.8 kB/s eta 1:44:57\n", + " --- 0.3/3.1 GB 436.8 kB/s eta 1:44:57\n", + " --- 0.3/3.1 GB 436.8 kB/s eta 1:44:57\n", + " --- 0.3/3.1 GB 433.0 kB/s eta 1:45:52\n", + " --- 0.3/3.1 GB 433.0 kB/s eta 1:45:52\n", + " --- 0.3/3.1 GB 433.0 kB/s eta 1:45:52\n", + " --- 0.3/3.1 GB 430.7 kB/s eta 1:46:25\n", + " --- 0.3/3.1 GB 430.7 kB/s eta 1:46:25\n", + " --- 0.3/3.1 GB 429.0 kB/s eta 1:46:50\n", + " --- 0.3/3.1 GB 428.2 kB/s eta 1:47:03\n", + " --- 0.3/3.1 GB 428.2 kB/s eta 1:47:03\n", + " --- 0.3/3.1 GB 426.8 kB/s eta 1:47:24\n", + " --- 0.3/3.1 GB 426.8 kB/s eta 1:47:24\n", + " --- 0.3/3.1 GB 425.4 kB/s eta 1:47:45\n", + " --- 0.3/3.1 GB 424.6 kB/s eta 1:47:57\n", + " ---- 0.3/3.1 GB 424.0 kB/s eta 1:48:06\n", + " ---- 0.3/3.1 GB 424.0 kB/s eta 1:48:06\n", + " ---- 0.3/3.1 GB 424.0 kB/s eta 1:48:06\n", + " ---- 0.3/3.1 GB 424.0 kB/s eta 1:48:06\n", + " ---- 0.3/3.1 GB 424.0 kB/s eta 1:48:06\n", + " ---- 0.3/3.1 GB 419.7 kB/s eta 1:49:13\n", + " ---- 0.3/3.1 GB 419.1 kB/s eta 1:49:22\n", + " ---- 0.3/3.1 GB 419.1 kB/s eta 1:49:22\n", + " ---- 0.3/3.1 GB 419.1 kB/s eta 1:49:22\n", + " ---- 0.3/3.1 GB 419.1 kB/s eta 1:49:22\n", + " ---- 0.3/3.1 GB 419.1 kB/s eta 1:49:22\n", + " ---- 0.3/3.1 GB 419.1 kB/s eta 1:49:22\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 414.9 kB/s eta 1:50:29\n", + " ---- 0.3/3.1 GB 402.9 kB/s eta 1:53:46\n", + " ---- 0.3/3.1 GB 402.9 kB/s eta 1:53:46\n", + " ---- 0.3/3.1 GB 402.9 kB/s eta 1:53:46\n", + " ---- 0.3/3.1 GB 402.9 kB/s eta 1:53:46\n", + " ---- 0.3/3.1 GB 400.2 kB/s eta 1:54:32\n", + " ---- 0.3/3.1 GB 400.2 kB/s eta 1:54:32\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 399.0 kB/s eta 1:54:53\n", + " ---- 0.3/3.1 GB 358.9 kB/s eta 2:07:42\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 358.7 kB/s eta 2:07:46\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 204.1 kB/s eta 3:44:30\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:32\n", + " ---- 0.3/3.1 GB 183.8 kB/s eta 4:09:16\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 183.6 kB/s eta 4:09:31\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 136.6 kB/s eta 5:35:26\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 128.7 kB/s eta 5:56:05\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 105.6 kB/s eta 7:13:46\n", + " ---- 0.3/3.1 GB 102.2 kB/s eta 7:28:26\n", + " ---- 0.3/3.1 GB 102.8 kB/s eta 7:25:40\n", + " ---- 0.3/3.1 GB 102.8 kB/s eta 7:25:40\n", + " ---- 0.3/3.1 GB 102.8 kB/s eta 7:25:40\n", + " ---- 0.3/3.1 GB 102.8 kB/s eta 7:25:40\n", + " ---- 0.3/3.1 GB 102.8 kB/s eta 7:25:40\n", + " ---- 0.3/3.1 GB 100.0 kB/s eta 7:38:05\n", + " ---- 0.3/3.1 GB 100.0 kB/s eta 7:38:05\n", + " ---- 0.3/3.1 GB 100.0 kB/s eta 7:38:05\n", + " ---- 0.3/3.1 GB 100.0 kB/s eta 7:38:05\n", + " ---- 0.3/3.1 GB 100.0 kB/s eta 7:38:05\n", + " ---- 0.3/3.1 GB 100.0 kB/s eta 7:38:05\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 98.0 kB/s eta 7:47:25\n", + " ---- 0.3/3.1 GB 76.4 kB/s eta 9:59:16\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 77.1 kB/s eta 9:54:29\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 75.1 kB/s eta 10:09:45\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 70.4 kB/s eta 10:51:10\n", + " ---- 0.3/3.1 GB 58.4 kB/s eta 13:04:51\n", + " ---- 0.3/3.1 GB 57.7 kB/s eta 13:14:07\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:26\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 55.7 kB/s eta 13:42:20\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 60.7 kB/s eta 12:34:35\n", + " ---- 0.3/3.1 GB 34.0 kB/s eta 22:28:37\n", + " ---- 0.3/3.1 GB 34.0 kB/s eta 22:28:37\n", + " ---- 0.3/3.1 GB 34.0 kB/s eta 22:28:37\n", + " ---- 0.3/3.1 GB 34.0 kB/s eta 22:28:37\n", + " ---- 0.3/3.1 GB 34.0 kB/s eta 22:28:37\n", + " ---- 0.3/3.1 GB 34.0 kB/s eta 22:28:37\n", + " ---- 0.3/3.1 GB 34.0 kB/s eta 22:28:37\n", + " ---- 0.3/3.1 GB 34.0 kB/s eta 22:28:37\n", + " ---- 0.3/3.1 GB 34.0 kB/s eta 22:28:37\n", + " ---- 0.3/3.1 GB 34.2 kB/s eta 22:19:37\n", + " ---- 0.3/3.1 GB 34.5 kB/s eta 22:08:43\n", + " ---- 0.3/3.1 GB 34.5 kB/s eta 22:08:43\n", + " ---- 0.3/3.1 GB 34.5 kB/s eta 22:08:43\n", + " ---- 0.3/3.1 GB 34.5 kB/s eta 22:08:43\n", + " ---- 0.3/3.1 GB 34.5 kB/s eta 22:08:43\n", + " ---- 0.3/3.1 GB 34.5 kB/s eta 22:08:43\n", + " ---- 0.3/3.1 GB 34.5 kB/s eta 22:08:43\n", + " ---- 0.3/3.1 GB 34.5 kB/s eta 22:08:43\n", + " ---- 0.3/3.1 GB 34.5 kB/s eta 22:08:43\n", + " ---- 0.3/3.1 GB 34.7 kB/s eta 21:59:40\n", + " ---- 0.3/3.1 GB 35.0 kB/s eta 21:48:37\n", + " ---- 0.3/3.1 GB 35.7 kB/s eta 21:22:47\n", + " ---- 0.3/3.1 GB 37.5 kB/s eta 20:20:38\n", + " ---- 0.3/3.1 GB 38.5 kB/s eta 19:48:07\n", + " ---- 0.3/3.1 GB 39.2 kB/s eta 19:27:00\n", + " ---- 0.3/3.1 GB 40.3 kB/s eta 18:57:27\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:48:59\n", + " ---- 0.3/3.1 GB 28.8 kB/s eta 26:30:56\n", + " ---- 0.3/3.1 GB 28.8 kB/s eta 26:30:56\n", + " ---- 0.3/3.1 GB 29.4 kB/s eta 25:55:58\n", + " ---- 0.3/3.1 GB 30.5 kB/s eta 25:01:36\n", + " ---- 0.3/3.1 GB 30.9 kB/s eta 24:44:18\n", + " ---- 0.3/3.1 GB 30.9 kB/s eta 24:44:18\n", + " ---- 0.3/3.1 GB 30.9 kB/s eta 24:44:18\n", + " ---- 0.3/3.1 GB 30.9 kB/s eta 24:44:18\n", + " ---- 0.3/3.1 GB 30.9 kB/s eta 24:44:18\n", + " ---- 0.3/3.1 GB 30.9 kB/s eta 24:44:18\n", + " ---- 0.3/3.1 GB 30.9 kB/s eta 24:44:18\n", + " ---- 0.3/3.1 GB 30.9 kB/s eta 24:44:18\n", + " ---- 0.3/3.1 GB 31.9 kB/s eta 23:56:58\n", + " ---- 0.3/3.1 GB 32.9 kB/s eta 23:11:23\n", + " ---- 0.3/3.1 GB 33.2 kB/s eta 22:58:21\n", + " ---- 0.3/3.1 GB 33.2 kB/s eta 22:58:21\n", + " ---- 0.3/3.1 GB 34.6 kB/s eta 22:04:43\n", + " ---- 0.3/3.1 GB 34.9 kB/s eta 21:52:22\n", + " ---- 0.3/3.1 GB 37.7 kB/s eta 20:14:05\n", + " ---- 0.3/3.1 GB 40.6 kB/s eta 18:49:12\n", + " ---- 0.3/3.1 GB 43.8 kB/s eta 17:26:20\n", + " ---- 0.3/3.1 GB 45.5 kB/s eta 16:46:27\n", + " ---- 0.3/3.1 GB 45.5 kB/s eta 16:46:27\n", + " ---- 0.3/3.1 GB 45.5 kB/s eta 16:46:27\n", + " ---- 0.3/3.1 GB 46.7 kB/s eta 16:20:19\n", + " ---- 0.3/3.1 GB 48.8 kB/s eta 15:38:34\n", + " ---- 0.3/3.1 GB 51.9 kB/s eta 14:41:44\n", + " ---- 0.3/3.1 GB 55.8 kB/s eta 13:40:52\n", + " ---- 0.3/3.1 GB 58.5 kB/s eta 13:02:05\n", + " ---- 0.3/3.1 GB 59.3 kB/s eta 12:52:39\n", + " ---- 0.3/3.1 GB 59.3 kB/s eta 12:52:39\n", + " ---- 0.3/3.1 GB 59.3 kB/s eta 12:52:39\n", + " ---- 0.3/3.1 GB 59.3 kB/s eta 12:52:39\n", + " ---- 0.3/3.1 GB 60.9 kB/s eta 12:31:23\n", + " ---- 0.3/3.1 GB 60.9 kB/s eta 12:31:23\n", + " ---- 0.3/3.1 GB 60.9 kB/s eta 12:31:23\n", + " ---- 0.3/3.1 GB 61.4 kB/s eta 12:25:57\n", + " ---- 0.3/3.1 GB 62.0 kB/s eta 12:18:15\n", + " ---- 0.3/3.1 GB 62.0 kB/s eta 12:18:15\n", + " ---- 0.3/3.1 GB 62.0 kB/s eta 12:18:15\n", + " ---- 0.3/3.1 GB 62.0 kB/s eta 12:18:15\n", + " ---- 0.3/3.1 GB 62.0 kB/s eta 12:18:15\n", + " ---- 0.3/3.1 GB 61.9 kB/s eta 12:20:00\n", + " ---- 0.3/3.1 GB 61.9 kB/s eta 12:20:00\n", + " ---- 0.3/3.1 GB 61.9 kB/s eta 12:20:00\n", + " ---- 0.3/3.1 GB 61.9 kB/s eta 12:20:00\n", + " ---- 0.3/3.1 GB 61.9 kB/s eta 12:20:00\n", + " ---- 0.3/3.1 GB 61.9 kB/s eta 12:20:00\n", + " ---- 0.3/3.1 GB 61.9 kB/s eta 12:20:00\n", + " ---- 0.3/3.1 GB 61.9 kB/s eta 12:20:00\n", + " ---- 0.3/3.1 GB 61.9 kB/s eta 12:20:00\n", + " ---- 0.3/3.1 GB 61.9 kB/s eta 12:20:00\n", + " ---- 0.3/3.1 GB 61.9 kB/s eta 12:20:00\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:24:36\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:24:36\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:24:36\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:24:36\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:24:36\n", + " ---- 0.3/3.1 GB 61.4 kB/s eta 12:25:08\n", + " ---- 0.3/3.1 GB 61.5 kB/s eta 12:25:00\n", + " ---- 0.3/3.1 GB 62.0 kB/s eta 12:18:11\n", + " ---- 0.3/3.1 GB 62.3 kB/s eta 12:14:27\n", + " ---- 0.3/3.1 GB 62.9 kB/s eta 12:08:15\n", + " ---- 0.3/3.1 GB 62.9 kB/s eta 12:08:15\n", + " ---- 0.3/3.1 GB 63.7 kB/s eta 11:58:40\n", + " ---- 0.3/3.1 GB 64.3 kB/s eta 11:51:40\n", + " ---- 0.3/3.1 GB 65.6 kB/s eta 11:37:47\n", + " ---- 0.3/3.1 GB 66.2 kB/s eta 11:31:14\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 67.2 kB/s eta 11:21:40\n", + " ---- 0.3/3.1 GB 63.0 kB/s eta 12:06:39\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 65.1 kB/s eta 11:43:19\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:58\n", + " ---- 0.3/3.1 GB 83.0 kB/s eta 9:11:35\n", + " ---- 0.3/3.1 GB 83.0 kB/s eta 9:11:35\n", + " ---- 0.3/3.1 GB 83.0 kB/s eta 9:11:35\n", + " ---- 0.3/3.1 GB 83.0 kB/s eta 9:11:35\n", + " ---- 0.3/3.1 GB 83.0 kB/s eta 9:11:35\n", + " ---- 0.3/3.1 GB 83.0 kB/s eta 9:11:35\n", + " ---- 0.3/3.1 GB 82.8 kB/s eta 9:12:30\n", + " ---- 0.3/3.1 GB 83.2 kB/s eta 9:10:02\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 85.0 kB/s eta 8:58:27\n", + " ---- 0.3/3.1 GB 82.4 kB/s eta 9:15:31\n", + " ---- 0.3/3.1 GB 82.4 kB/s eta 9:15:31\n", + " ---- 0.3/3.1 GB 82.4 kB/s eta 9:15:31\n", + " ---- 0.3/3.1 GB 82.9 kB/s eta 9:12:21\n", + " ---- 0.3/3.1 GB 83.2 kB/s eta 9:10:25\n", + " ---- 0.3/3.1 GB 83.2 kB/s eta 9:10:25\n", + " ---- 0.3/3.1 GB 83.8 kB/s eta 9:06:11\n", + " ---- 0.3/3.1 GB 83.8 kB/s eta 9:06:11\n", + " ---- 0.3/3.1 GB 84.7 kB/s eta 9:00:12\n", + " ---- 0.3/3.1 GB 86.9 kB/s eta 8:46:25\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 89.6 kB/s eta 8:31:03\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 80.3 kB/s eta 9:30:13\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 79.2 kB/s eta 9:37:57\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 73.3 kB/s eta 10:24:38\n", + " ---- 0.3/3.1 GB 72.0 kB/s eta 10:35:54\n", + " ---- 0.3/3.1 GB 72.0 kB/s eta 10:35:54\n", + " ---- 0.3/3.1 GB 72.0 kB/s eta 10:35:54\n", + " ---- 0.3/3.1 GB 72.0 kB/s eta 10:35:54\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.9 kB/s eta 10:36:34\n", + " ---- 0.3/3.1 GB 71.2 kB/s eta 10:42:42\n", + " ---- 0.3/3.1 GB 71.2 kB/s eta 10:42:42\n", + " ---- 0.3/3.1 GB 71.8 kB/s eta 10:37:46\n", + " ---- 0.3/3.1 GB 71.8 kB/s eta 10:37:46\n", + " ---- 0.3/3.1 GB 71.8 kB/s eta 10:37:02\n", + " ---- 0.3/3.1 GB 71.8 kB/s eta 10:37:02\n", + " ---- 0.3/3.1 GB 72.3 kB/s eta 10:33:14\n", + " ---- 0.3/3.1 GB 72.3 kB/s eta 10:33:14\n", + " ---- 0.3/3.1 GB 72.3 kB/s eta 10:33:14\n", + " ---- 0.3/3.1 GB 72.3 kB/s eta 10:33:14\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 72.2 kB/s eta 10:33:33\n", + " ---- 0.3/3.1 GB 64.0 kB/s eta 11:55:14\n", + " ---- 0.3/3.1 GB 64.0 kB/s eta 11:55:14\n", + " ---- 0.3/3.1 GB 64.0 kB/s eta 11:55:14\n", + " ---- 0.3/3.1 GB 64.0 kB/s eta 11:55:14\n", + " ---- 0.3/3.1 GB 64.0 kB/s eta 11:55:14\n", + " ---- 0.3/3.1 GB 64.0 kB/s eta 11:55:14\n", + " ---- 0.3/3.1 GB 64.0 kB/s eta 11:55:14\n", + " ---- 0.3/3.1 GB 64.0 kB/s eta 11:55:14\n", + " ---- 0.3/3.1 GB 64.0 kB/s eta 11:55:14\n", + " ---- 0.3/3.1 GB 64.0 kB/s eta 11:55:14\n", + " ---- 0.3/3.1 GB 64.0 kB/s eta 11:55:14\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 58.7 kB/s eta 12:59:32\n", + " ---- 0.3/3.1 GB 33.5 kB/s eta 22:47:25\n", + " ---- 0.3/3.1 GB 33.5 kB/s eta 22:47:25\n", + " ---- 0.3/3.1 GB 33.5 kB/s eta 22:47:25\n", + " ---- 0.3/3.1 GB 33.5 kB/s eta 22:47:25\n", + " ---- 0.3/3.1 GB 33.8 kB/s eta 22:32:14\n", + " ---- 0.3/3.1 GB 33.8 kB/s eta 22:32:14\n", + " ---- 0.3/3.1 GB 33.8 kB/s eta 22:32:14\n", + " ---- 0.3/3.1 GB 33.8 kB/s eta 22:32:14\n", + " ---- 0.3/3.1 GB 33.8 kB/s eta 22:32:14\n", + " ---- 0.3/3.1 GB 33.8 kB/s eta 22:32:14\n", + " ---- 0.3/3.1 GB 33.8 kB/s eta 22:32:14\n", + " ---- 0.3/3.1 GB 33.8 kB/s eta 22:32:14\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 34.4 kB/s eta 22:11:41\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 33.3 kB/s eta 22:55:07\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 32.1 kB/s eta 23:46:37\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 30.0 kB/s eta 25:26:43\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:11:35\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 29.6 kB/s eta 25:44:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 28.5 kB/s eta 26:46:03\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 27.3 kB/s eta 27:59:02\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 26.6 kB/s eta 28:39:37\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:50:12\n", + " ---- 0.3/3.1 GB 25.6 kB/s eta 29:47:27\n", + " ---- 0.3/3.1 GB 25.6 kB/s eta 29:47:27\n", + " ---- 0.3/3.1 GB 25.6 kB/s eta 29:47:27\n", + " ---- 0.3/3.1 GB 25.6 kB/s eta 29:47:27\n", + " ---- 0.3/3.1 GB 25.6 kB/s eta 29:47:27\n", + " ---- 0.3/3.1 GB 25.6 kB/s eta 29:47:27\n", + " ---- 0.3/3.1 GB 25.6 kB/s eta 29:47:27\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:43:06\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:43:06\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:43:06\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:43:06\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:43:06\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:43:06\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:43:06\n", + " ---- 0.3/3.1 GB 26.1 kB/s eta 29:13:37\n", + " ---- 0.3/3.1 GB 26.1 kB/s eta 29:13:37\n", + " ---- 0.3/3.1 GB 26.1 kB/s eta 29:13:37\n", + " ---- 0.3/3.1 GB 26.1 kB/s eta 29:13:37\n", + " ---- 0.3/3.1 GB 26.1 kB/s eta 29:13:37\n", + " ---- 0.3/3.1 GB 26.1 kB/s eta 29:13:37\n", + " ---- 0.3/3.1 GB 26.1 kB/s eta 29:13:37\n", + " ---- 0.3/3.1 GB 26.1 kB/s eta 29:13:37\n", + " ---- 0.3/3.1 GB 26.0 kB/s eta 29:22:44\n", + " ---- 0.3/3.1 GB 26.0 kB/s eta 29:22:44\n", + " ---- 0.3/3.1 GB 26.0 kB/s eta 29:22:44\n", + " ---- 0.3/3.1 GB 26.0 kB/s eta 29:22:44\n", + " ---- 0.3/3.1 GB 26.0 kB/s eta 29:22:44\n", + " ---- 0.3/3.1 GB 26.0 kB/s eta 29:22:44\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:41:34\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:41:34\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:41:34\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:41:34\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:41:34\n", + " ---- 0.3/3.1 GB 25.7 kB/s eta 29:41:34\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.0 kB/s eta 27:15:07\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:49:01\n", + " ---- 0.3/3.1 GB 28.4 kB/s eta 26:49:01\n", + " ---- 0.3/3.1 GB 30.1 kB/s eta 25:18:43\n", + " ---- 0.3/3.1 GB 30.4 kB/s eta 25:05:15\n", + " ---- 0.3/3.1 GB 33.8 kB/s eta 22:32:11\n", + " ---- 0.3/3.1 GB 37.6 kB/s eta 20:16:22\n", + " ---- 0.3/3.1 GB 43.5 kB/s eta 17:32:33\n", + " ---- 0.3/3.1 GB 45.8 kB/s eta 16:38:18\n", + " ---- 0.3/3.1 GB 50.6 kB/s eta 15:03:56\n", + " ---- 0.3/3.1 GB 52.2 kB/s eta 14:35:23\n", + " ---- 0.3/3.1 GB 57.7 kB/s eta 13:12:43\n", + " ---- 0.3/3.1 GB 64.2 kB/s eta 11:52:49\n", + " ---- 0.3/3.1 GB 68.2 kB/s eta 11:10:39\n", + " ---- 0.3/3.1 GB 73.6 kB/s eta 10:21:27\n", + " ---- 0.3/3.1 GB 79.6 kB/s eta 9:34:06\n", + " ---- 0.3/3.1 GB 85.3 kB/s eta 8:55:43\n", + " ---- 0.3/3.1 GB 91.7 kB/s eta 8:18:28\n", + " ---- 0.3/3.1 GB 96.7 kB/s eta 7:52:46\n", + " ---- 0.3/3.1 GB 103.4 kB/s eta 7:22:02\n", + " ---- 0.3/3.1 GB 106.6 kB/s eta 7:08:59\n", + " ---- 0.3/3.1 GB 108.8 kB/s eta 7:00:06\n", + " ---- 0.3/3.1 GB 115.4 kB/s eta 6:36:14\n", + " ---- 0.3/3.1 GB 118.7 kB/s eta 6:25:03\n", + " ---- 0.3/3.1 GB 122.5 kB/s eta 6:13:14\n", + " ---- 0.3/3.1 GB 124.4 kB/s eta 6:07:28\n", + " ---- 0.3/3.1 GB 129.0 kB/s eta 5:54:11\n", + " ---- 0.3/3.1 GB 135.8 kB/s eta 5:36:24\n", + " ---- 0.3/3.1 GB 142.3 kB/s eta 5:21:09\n", + " ---- 0.3/3.1 GB 142.9 kB/s eta 5:19:45\n", + " ---- 0.3/3.1 GB 146.1 kB/s eta 5:12:45\n", + " ---- 0.3/3.1 GB 146.1 kB/s eta 5:12:45\n", + " ---- 0.3/3.1 GB 149.8 kB/s eta 5:04:59\n", + " ---- 0.3/3.1 GB 153.1 kB/s eta 4:58:31\n", + " ---- 0.3/3.1 GB 156.3 kB/s eta 4:52:21\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n", + " ---- 0.3/3.1 GB 159.2 kB/s eta 4:47:03\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "ERROR: Exception:\n", + "Traceback (most recent call last):\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_vendor\\urllib3\\response.py\", line 438, in _error_catcher\n", + " yield\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_vendor\\urllib3\\response.py\", line 561, in read\n", + " data = self._fp_read(amt) if not fp_closed else b\"\"\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_vendor\\urllib3\\response.py\", line 519, in _fp_read\n", + " data = self._fp.read(chunk_amt)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_vendor\\cachecontrol\\filewrapper.py\", line 90, in read\n", + " data = self.__fp.read(amt)\n", + " File \"C:\\Users\\SAURAV\\anaconda3\\lib\\http\\client.py\", line 463, in read\n", + " n = self.readinto(b)\n", + " File \"C:\\Users\\SAURAV\\anaconda3\\lib\\http\\client.py\", line 507, in readinto\n", + " n = self.fp.readinto(b)\n", + " File \"C:\\Users\\SAURAV\\anaconda3\\lib\\socket.py\", line 704, in readinto\n", + " return self._sock.recv_into(b)\n", + " File \"C:\\Users\\SAURAV\\anaconda3\\lib\\ssl.py\", line 1242, in recv_into\n", + " return self.read(nbytes, buffer)\n", + " File \"C:\\Users\\SAURAV\\anaconda3\\lib\\ssl.py\", line 1100, in read\n", + " return self._sslobj.read(len, buffer)\n", + "ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host\n", + "\n", + "During handling of the above exception, another exception occurred:\n", + "\n", + "Traceback (most recent call last):\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\cli\\base_command.py\", line 169, in exc_logging_wrapper\n", + " status = run_func(*args)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\cli\\req_command.py\", line 248, in wrapper\n", + " return func(self, options, args)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\commands\\install.py\", line 377, in run\n", + " requirement_set = resolver.resolve(\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\resolution\\resolvelib\\resolver.py\", line 92, in resolve\n", + " result = self._result = resolver.resolve(\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_vendor\\resolvelib\\resolvers.py\", line 546, in resolve\n", + " state = resolution.resolve(requirements, max_rounds=max_rounds)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_vendor\\resolvelib\\resolvers.py\", line 397, in resolve\n", + " self._add_to_criteria(self.state.criteria, r, parent=None)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_vendor\\resolvelib\\resolvers.py\", line 173, in _add_to_criteria\n", + " if not criterion.candidates:\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_vendor\\resolvelib\\structs.py\", line 156, in __bool__\n", + " return bool(self._sequence)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\resolution\\resolvelib\\found_candidates.py\", line 155, in __bool__\n", + " return any(self)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\resolution\\resolvelib\\found_candidates.py\", line 143, in \n", + " return (c for c in iterator if id(c) not in self._incompatible_ids)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\resolution\\resolvelib\\found_candidates.py\", line 47, in _iter_built\n", + " candidate = func()\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\resolution\\resolvelib\\factory.py\", line 206, in _make_candidate_from_link\n", + " self._link_candidate_cache[link] = LinkCandidate(\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\resolution\\resolvelib\\candidates.py\", line 293, in __init__\n", + " super().__init__(\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\resolution\\resolvelib\\candidates.py\", line 156, in __init__\n", + " self.dist = self._prepare()\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\resolution\\resolvelib\\candidates.py\", line 225, in _prepare\n", + " dist = self._prepare_distribution()\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\resolution\\resolvelib\\candidates.py\", line 304, in _prepare_distribution\n", + " return preparer.prepare_linked_requirement(self._ireq, parallel_builds=True)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\operations\\prepare.py\", line 516, in prepare_linked_requirement\n", + " return self._prepare_linked_requirement(req, parallel_builds)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\operations\\prepare.py\", line 587, in _prepare_linked_requirement\n", + " local_file = unpack_url(\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\operations\\prepare.py\", line 166, in unpack_url\n", + " file = get_http_url(\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\operations\\prepare.py\", line 107, in get_http_url\n", + " from_path, content_type = download(link, temp_dir.path)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\network\\download.py\", line 147, in __call__\n", + " for chunk in chunks:\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\cli\\progress_bars.py\", line 53, in _rich_progress_bar\n", + " for chunk in iterable:\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_internal\\network\\utils.py\", line 63, in response_chunks\n", + " for chunk in response.raw.stream(\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_vendor\\urllib3\\response.py\", line 622, in stream\n", + " data = self.read(amt=amt, decode_content=decode_content)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_vendor\\urllib3\\response.py\", line 587, in read\n", + " raise IncompleteRead(self._fp_bytes_read, self.length_remaining)\n", + " File \"C:\\Users\\SAURAV\\anaconda3\\lib\\contextlib.py\", line 137, in __exit__\n", + " self.gen.throw(typ, value, traceback)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\pip\\_vendor\\urllib3\\response.py\", line 455, in _error_catcher\n", + " raise ProtocolError(\"Connection broken: %r\" % e, e)\n", + "pip._vendor.urllib3.exceptions.ProtocolError: (\"Connection broken: ConnectionResetError(10054, 'An existing connection was forcibly closed by the remote host', None, 10054, None)\", ConnectionResetError(10054, 'An existing connection was forcibly closed by the remote host', None, 10054, None))\n" + ] + } + ], + "source": [ + "!pip install torch==1.8.1+cu111 torchvision==0.9.1+cu111 torchaudio===0.8.1 -f https://download.pytorch.org/whl/torch_stable.html" + ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": {}, + "outputs": [], + "source": [ + "import easyocr" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": {}, + "outputs": [], + "source": [ + "detection_threshold = 0.7" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": {}, + "outputs": [], + "source": [ + "image = image_np_with_detections\n", + "scores = list(filter(lambda x: x> detection_threshold, detections['detection_scores']))\n", + "boxes = detections['detection_boxes'][:len(scores)]\n", + "classes = detections['detection_classes'][:len(scores)]" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": {}, + "outputs": [], + "source": [ + "width = image.shape[1]\n", + "height = image.shape[0]" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0.56601626 0.20935276 0.6988997 0.36206636]\n", + "[426.21024138 281.57946423 526.27146381 486.97925195]\n", + "[([[22, 12], [46, 12], [46, 48], [22, 48]], '', 0.0), ([[62.013606076167854, 7.0816364570071375], [203.91492701870476, 29.993203911709827], [192.98639392383214, 78.91836354299286], [51.08507298129524, 56.00679608829017]], 'Go4o20', 0.2872526183101113)]\n" + ] + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAiEAAAEhCAYAAACp/3AaAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOz9WaxtWXaeB36zWc1uTnP7G5kR4WRjkbQokxZFUU3BpVKxZKAawLAe/GZb0CNJwKJfRAMlgC9F6El6MCW9CDJQgGBBgAQBEkC5zLJMyEXbUrpcMk1mYzmbiIyI255mN6ubTT2MOdda+9xzb9zIaDJCPDNw4tyz9tqrX3P+8x//+IeKMUZu2k27aTftpt20m3bTPuOmf9AHcNNu2k27aTftpt2035/tBoTctJt2027aTbtpN+0H0m5AyE27aTftpt20m3bTfiDtBoTctJt2027aTbtpN+0H0m5AyE27aTftpt20m3bTfiDtBoTctJt2027aTbtpN+0H0m5AyE27aTftpt20m3bTfiDtBoTctJt2027aTbtpN+0H0m5AyE27aTftpt20m3bTfiDtBoTctJt2027aTbtpN+0H0j41EPLrv/7rfOUrX6Gua37u536O/+F/+B8+rV3dtJt2027aTbtpN+0L2NSnUTvm7/ydv8N/8B/8B/yNv/E3+Lmf+zn+6l/9q/zdv/t3+frXv879+/df+d0QAu+99x5HR0copT7pQ7tpN+2m3bSbdtNu2qfQYoxsNhu+9KUvofXrcRyfCgj5uZ/7OX72Z3+W/+w/+88AARZvvfUWv/RLv8Rf/It/8ZXffffdd3nrrbc+6UO6aTftpt20m3bTbtpn0N555x3efPPN11rXftI77/uer371q/zKr/zKuExrzc///M/z27/92y+s33UdXdeNf4+Y6J2/AMfVJ314N+2m3bSbdtNu2k37NNplB2/9FY6Ojl77K584CHn69Cneex48eHCw/MGDB3zta197Yf1f+7Vf41d/9Vdf3NBxdQNCbtpNu2k37abdtC9Y+yhSih94dsyv/MqvcHFxMf688847P+hDumk37abdtJt2027aZ9A+cSbk7t27GGN49OjRwfJHjx7x8OHDF9avqoqqej3Go+g8P/S1C+482hNDJISAUmCVQSsFMUKMKAVGK1DgYsTHiNeKwRh0UXB8/wH1ekUXAm0IuBjZO4ePkaKqsGWJNhpbFGitsdZgjCGGQPSBGAJ+GIg+4L3HO48Pnq7r8CHQdR1DP8jxhECMEe8cMQRCDPjgIUIMnhgjBoVBoZXGGoMmnwsohZwbioCEqrRSaK1QgNUKhUIDWgkCNUqn37JNrRRGyzKr5VrFGCHI9pRcKlRWB8VIDBGQa0xkPB7yumk9WT+F0dI6McZ0jIJxYwjTduPs+0z7jbP18vlCHMNzMW+byIGKSYFCkYH3eA7I9YkxEmOY7e1Km2/sqjwq/XkV1Kur24mzla+0V84HPo7u+lVSrvl2P3HF1w+ofeoa9XjtPz+z9jrnd/XBf3GFT+hg5u2jXPhP88J9nG2/3jlcXevz9Op8Ho+tWRp+5ydPeHrv40UsPnEQUpYlP/MzP8Nv/uZv8u/+u/8uIMLU3/zN3+QXf/EXP9a2l9uB/9v/85v8iX/8Ln5wDEOPQbMuKgptIHhU8BitqEqF0rDxniZ6Gltwsagpj0/4Q/+nL3P/h9/kqRt4r+/YOcc72y1N8Bzfu8v69h3KumJ9ekxRFBwfrVkuKnw/MDQdYRhonl8ytB3dvqHZ72nalkdPn9B0Lc+eXHJ+fg4uELuB6D373Y6h7+hdT9e3hODxfUf0gQWaKhoqazmul1ilUT6gQsQojTWWqMDHQIhQWk1VWKxWrKzBakWpwCootGFRVBitqW1JoQ1VYVkUJdYY1tUCqw04T3QeBRgZxjFEVIwCroaBGCK+Hwg+QJAfhcKqNOj7AEEG+egEbEXnIUSsMVS2kPufAFj0kRgCKuZ9gokyqEfvCc5BBGMMWmlCCIQE4oL3CVBEwggqAARgaaUPgJROnwXv8M6nv67pjjLACjGBpEiIcQa0BNhlylCl41ZMYORl2u75NqaFcVzwaspyWu/aT18BfGZIbP7PL3SLnwkISffls75m6tX3emwJhMvFuO6ChGuWfdz2sn1dba95Dtdt/rW/e7jOwcTpw3fykdd63U1fd/Svf2yv176fY4vq0wUr77655P/+//hJfut//+qM1w9rnzgIAfjlX/5l/sP/8D/kj/yRP8If/aN/lL/6V/8qu92OP/fn/tzH2q72kZNnLQ/e2eGGgaHvMUpzVAwUyqBjQEWP1lAVgIZF8OxjoKtrVsclpY88OIf7F4qhcTzbtQxuoNi1OO8pfEc5dJQLRTU4ilKzcIFlGwkDuBbioCgvNb4z9I2la0raNhDbmrYD0y6o2l4G+s4SnGO3G+i7QDd49p0ieIVrZcCvQ6QKkdJEjsoeqzQMHrxHK43RBgBHAiGFpp6BkEIrSqBQUBjDoghYrVlYT2EE3CxLj9WGdQ2ltgIWXEAr5NopMAgoiCEQBi8gZPCEBIjwQdgXpdBzEBImEILzxBCwOlJZhSLiB0dIDJJsQ2FjYm+iAIbgA2EYICJskBYQ4n0gxjCCkBBmICQxRUaba0GIAmGpEgi5GntUM3YFP4GQDCoOtqXUrDtW4/aJVzDGfAfxuu5vDkLm37hu5Zd0Ia9MaLvSJc43+znJeP9YHeOncg5x+p3Zr09jN6/c/7UPy7TGjHWUdhUcfJ8g4LXahwGRj7PvDz/3g/szWzRnU1/dXhdIHbyNr9XGM79yK15/j6/fPpFj+wRb0Iq6+fjA91MBIf/+v//v8+TJE/7SX/pLfPDBB/z0T/80v/Ebv/GCWPWjtogMKkM/EIMMLDFGhsER8FSlpSxLfBh43l7io2NvLb0xLO884Ed++g+jVmse+4F33/kO/+xb3+a//r2v0YTApSlwWmPrCluV2KqkPjnGlgW3To9ZLRfCMtiCQltuVysWtmBR1ayqGnO85K033kRbw4+nux+9J3QDwTm2m3O6rmGzv+T88jnODXS7LX4YCJs9ftvIAL7vCM7TXG7p9g3ee4Z+TwSCUUSlME5hQ49RkQVgiBRELBGrDZUpMEphlcaghSnRGo2iMhajNKU2FNpQGMu6FnZkWRRUVj4vtEYZhS1qCY+EiArCEMTEDKgoy+TGCMOBD+gAMQY67yEEHJGogahQ0aRQjQWlCC6gEkCJNvEXShOVEibEz5mQICAkTCBE1lfji5YnlT4xLspqjDVACjHF+Y9KISlFJKRQEuOEcgwBJcZC1pSfgICTVxHkUU144bpZUYzqhVDPYVNX/nrd7id9b1z9XxE65FNHBhIC/Hy21zn5jzpM3bSb9oNvnwoIAfjFX/zFjx1+ua4FH/DOAWnwieC8J6IoMGhrGIaB3dAw+IFO1zhbcrRecO8rbxPqBR9sdzw5e8b//O1v8U/+x/8vbQS/PiYUVmbCRHRZYI+PsIUdQciqXnC6XLOoan7o/hucLNfcOb2FWaxYLVbc+tKXqRcLjtZrlvVCwhp9j3eOzeaMrt1zsTnjydkj3NDTbC5xfU/z9Iz2+QVD07F/do7renzf0w89fXDs/UAgEpUBowUMRDAxUgWHiREbI4aIUYpSWzRKBmFkPYMMmhaFRlEXJYuipCpKTt0RpbUc1QsWsaQ0lkVZYlQO+xjZVmIt8uCrYwIiEVQAYkQFUCESncN1LTEonNdEFcfjsUoRbUFUiqgdOEUMCpLOJaCTRkRAV4yRoGTQDiESo2bUqJAwgwhApvBKlEHb6IlJ8s4fhF4mTUsErYhRSdhJp2VJAJO7dHUFBoQrg5b8NRssYhTmPKMX8urTOnG2jXFmdx0yeW07n6sAZNrTZzE2fZIzr4NJ/4es+Nq7vHbFz2PE/VXtupP4OADkumDCh63zCbfP+yX/sPZ5Pv7P87HxKYKQT6fJNDcPBVoptFIUSgbW4D1N2+DigDIWYzTFcoleLKCu2cVI2/d88733+fbZOY+3e5Z37lEogz86JtqCkDQBUWtCYUArmi7gfEPbOPb7gdJYmk3Hwpasq5qjqqasKk5v36YoS+rlkqqqk55DZv5lqbBWEZWTd7woWJyeoGLk9OgE84YjDo6wb4UJ2e7om46mbbi8vMR5zz4MuBhww4AbRJsybDbEYSD2PQwDPkbakK5RmECCjlFAiBJGpNPQELB+YNfuhEFpGwqtsUpTaYvWitoWGGOwSpYbpVkUBVZrLPK3mW3XKhHZKh3RhUXFiLEGHRGhLCmUgxF2p+sJg5Pj9AIAY8yhkhlg8AEVIzppRCbxLIfsRl6m03pay0/MoFXWmW9fATHESVybmZYs3J0Pci+IVyeUEjmUrAoemmh0FaOwKjFOrMosVhJ5mU4kglKy/Sj//lBQkkHZZ9gOiJfPKp4xXd7PS7Tpc9A+CqPzOR+hbtrntr0g0P8+2xcLhMj0GGJAa01hZOArMRgUnWtpuhYM6KpAW40+OSEerWG94jIGztuGf/6N/5V/8Z136NYnHH3pbWJRwtEp0Za4EPEBBj+w6xq8d2z2G3y/A5RoA0JEDx7lI6rrUe0gy61FaYWpanRRUNc1JycnLOqaH/rhN7l955R790748pu3qcuSk+Pb1GXBnWrNrXpFoTTLxGKIEDSy2W558uwZ7dDzZHvOvuvY7zZsLi9pdzsev/MO3a6h227p93u8G+ibVsIbIRBTGIUQBSRoyZbRRDQO5R1q10qGSj8QByeAIUhXVhdFErkWLIqSwhacrNaU1lKagtJYCi3AxGhNbSylkXDOorIYrVmXFVYbAThai47EiejUty2+6wWspH3GJGQV1iUNvAmM6JBAQkTOL0ZIoRqSbkXQTQoPaZVASER7ARqZSVIz1iTGMAKZMWxzFeSkf8f0LOZwDVFdO+ZHpoUxTt8dwc4YtZ2i2y+82C8I92Yz3tcCGVe/98VqH5H/+Uy39vkewD9Mw/Gyvz97FuSL9WR+sY72uvZJncHvTxCSWhyzF9JlmA0M+RKP+Q3agLUErelipPMhpeZGnNJQlKiyQlULKCqIEmbAOUptcD5ldig97juGiA8ORUjKSpk5SxaJQqsBHWBAEW1D6zxHZxf4GIjKYcpAVRa0zZ66LGirHU21wirNMmk2KmuxxtL0HU5BNBpb1VTWELX8XdaSsdO3LcNuz9C2+GGgbxsZ4AdH8J7gPH5wI6NAjKJX8W42cEeCk/CHQkI7SilC9JgQcV7hlMLGAJ2l8JbKeEpjsVrTBY/RmoURsFFqQ6/lswCUJmlQEiuRs2hC8EQVMQrRoURAGUREoqYxeBZCUZm1SOxI9EpEryHdixhRIe1HQRiZg7QNlYFHRGXhRhCgEmefKzX7ToSYQhoqrxfVqEGJjF+78qzKbzXHHdNj+pL15xqUTMPIvmJCO7LoNQaamN+Fz669bibLh2YPvGaE4WMDkIOPXhbOmq/y4ocfZ5ieWLaPsZEXt/aS9vkETl+8of2Ld8Tz9okcffxktvOFAyExzYSV0hgjHXNwTjxDNJS2wutAHwd8CGhj0GVFpwy7znHmPF21JB6d4lcndNURul5QndzHVDWlMShtCCGy9LLdpt3RD8IuBO9k8Oo9+IjyHuU8wXv6riMGP2Y9hBA4HzzKdVx+/V9SqEBZK6qlRmsorIQoVhiWGEyEKkqa7ZfeeIPbt05Zrlec3rmNLUsWp0fYxYLjk2PuVwUGTa1M8hmRAEfwnqHvCN6z2Wxo25b9dsfF2Rl933P27Blt07LdbNhsLiQrpRfPk5hDIz6O2SKDdyMrw9CgB0XRt8JAaUOhDEYrSpvCTkpjlKJSmqUxGKVZFVUSzFoqKz4oJmXHVNZSGkNpC46qEqM1RfI2sUpBynrROcQUZWBWQYBUjJHYD3jnUCGA9yl8IiDUOUfvBvkrMRvaZ0YlSir0DOSotP3pBVMT+BnZj8zMhCRklfXDdbqLmT5l/CxmJUhKiSZ7n8Q5RhqBjc6j+uGvF9o4Nk7/GP//WaWdvm5a4Ot2XnP1zA+ifXZqkde4It/Xzj8KI3LTbtpn375wIGScdsbMhMQ0CxZgoowmKJK2I8XYjcGjaFyg9RGnLbGsCLbE2wqsMCG6XmBMgTGWiIg9QwzEqkS7nuA93iUTst4LrR9Ep+CdI+53BO8hBlQM9P1A3zeiVdlfwtCCdmCGNNI4ILDwUHkRkBYuUFrLD1+c8+D+fW7duc2bWlMvF+ijpQzOVcni6Ii6KLi9PqGyBZU1lNYSvccNA947zs/P2e/3bC4vWTx5QtM0BGOwux3OahpS+mrbC9tjLHoY5LycAA/f94Tg8IPDOwl16CQMLpSmQKO1okhhHgsTCNFG2BHbUShJFa6thJsEaGhWdcVCldRRY42Yr0VjxMtEKZTSklqbBm5NZr0iOLnWQUE0woYolxJxlTApYQCv/MhwKQAdiT6FZVQaoBPo0pm5GJ83NQKJAxZGBabsmlmYhRnZMRPPZnpAZcErmV2ZQM74aCe2Q7b8Iul53dCh8mbnVEteOH726bcrp3ttuw4QXdXSHKz3GSGoq4esuP64XqW5+Ch+JnNjvddr3+91eI0Qy8EpXd3P6xzf5x3QfNzjUy/59037uO0LB0J0EkcapZLoMvewmUZNXbfSKDRFUWMXa1pTcr7vOHOBjYN9tIRyiVqfohZLWJ8QqwVdEC8KpRRKSx5I0Bb8kHQLHoLMplUAlQCH9o6w2hO8IwwDwQ9UPlIeBaL30N0iuh5tArrwhOAYmi3RO+6UNXeqGh0C1jlhNcqSzb5l3z/i0fPnaKPRdYmyhrIsqOuKqii4sz6hKgpWiwWLqqIoLMvFAq01eUjUWqHrikVV8uZ6NRqAxRSW8YkJGfYNvuuILqUWe89uu2MYeraXGy7Pz4Vp6YRpiS6dW5S02RAjzom/SQs0MaLxmKEV1sNbal8ImPACKhZdRV0U4m9yeYnWmsrYJIJVFFphFNTGYJSAFKtFkFzqZLMWI0qDMYqiLJLniU6pxQZ8mdiA9Iz4KCk1PhCHxPQMXlKFE7ORPUkyA5LjKmNK8kwnkoWrYS6aTQLnUcuiRN8SZ8/o3CBtWs7h9iP4kBkTWa60ntxox/3NjymFpK6kAF+bJgzjc3K1fT9d7QtE0EvWmx/LdYN/PPgkL/koA8k1A6m6bvmLx6CuWXbd3/FVH75Ouzbc9Cr0pqZn5DU2O+8XX/qteSzoEyZNPjrb9XG39Nm3l7KSn+lRXN9efmyfnCrkkzjTLxQIUcjgYlImxoHAEDX2v2RPCjS2XFAtj4i64Gzf8XzwbDzssJhigT06RS1WsD4lVjV929N2HVobyqIApQhFBTGkGXk6jqCkkyegSGGaXkCIaxtc32HR1KpAEQl9D95hiogpI2Ho2T9/gh86Hty6xZsnp5gYMH1P9I6LZ0+53F6y2295dvaUwQ1c7Ld0wyBW7lpRFQW3j04kzfb4iKP1mtV6xcMHDyRb59Ypi+WSW7dOefjwIVVVcnr7FnVVcXJywsnJqbAdTkBId7kVIDIMDPsWNzien5/RNA1PHz/m/ffeY+h7dttLhmGga1v6rsc7T5uAiWs6/DCgQkA5GeDz9itbUIdCrOx7hwpQWRG3KhhDNKIzMRgiVoE1iqOqxBpNZTWlURTGsqoXGK0pbYE1wgStCjsCVZ2s661WYwhIoZJYF2FS2p7oA6odwDkJ9yVWJAyiB8rhDBVTWGg+gKYMLUDCQ0kMHIIXTJBAGlqNhmdkgJLN3phYlLGFKOGlCDHreKKAJ2UMylohOTLwSeGlvI4kOid90yv6ifzKXPu+fQKT25dtYj51uG5wnwJJ39/2X/j0mk1dt/UP61bVlX/F2UX6qK6ukTmD9Tp7n33xFcd3HQiZvqaQh0gB/lMbLcc9f6IEyfdxsJ/kQbzEqfbzADhe1q4/2k/miH//ClMVYxpjzk4wSTcQlPhJ5AsdlSKN2ASl8YBD4dF4pTHWossKbEEfQfnAAMJ8aMUAI2WehamjbbdSqOkvEYvaArRGE7FGYzFYJWmqQRsRghpPNDJA6WqBNob1yS3uPnhAqRVro9DBc37rhN12w77ZcefiDv3Qc77d0PadWL57h1GKhS2x2mALSS/u+4GziwustezbhqIsObs452KzoSwLjk9PKBMIOT05lWuaBjn6AeVcGrCRwdoaikXN+tYp95AaOF17G+8dQ98z9IP4suz3YiTXCgiJgxNWxXv6RtKOLQqLEv+UboAQCFExoISNcDLgexWxKiYQEjFREVyL8YrCK0qtsMawT2LYMoVvCm2obYlWmkKbMUxUGNHNlIkdKTESDooRo+We2tKgk8ZIZ/dUaxh1Hzlc4uW3GhWnakq79SoJlwPR68Q0yWeB1O/n78aUrhsyDxHHvlJBAhUils1+OKM2RWuwOj136bPsRhujDIxJNDvVAzp8jeJ8wcgmXlnn1WP4S1pkdiqyZDbjH1/P2TovCxaogw+vP4LrtbnXnc8r9nZNzOXVAYw4hc1QB+DjOiBysOjqNb1m39cdgXrl1bq+jWUFRkg3bSNefSA+bLvXXOir8OagTa/Hax3pp9euObbX2N2190y9dI3PtH2sPY+X45M4/t+PIETJbFJr6bzzQGxNiVWaQUUcEYVP/ymCtkRT4LWhU5pWRXpj6W2BrZcUx6d4U3A5BJzrpW5JVeGSM2ckoLVJRd4m2KG1SmxLosptgMKAClhWaCJF1NRRQwDXt3jn8KGndw1YR6k1Ngbe+gP/Bj/143+A09WSH314h8pqLs/O2G+3DK6n7XYMbuD52XOatmW73bC5OKfvOs6fnjF0HW3T0HUdbdfx+FvfZnAD+2ZPP/RoYwRwGU29qDHWcnxyzMnJiaQ6a/FUuXtyyslqxcnRMW/cf0BVVZyenlIfrzh5eJ8frWtZvxBbdR9k5t+2LWfPzxiGgb7tGNxAt2vYXVzg+oHd5Ya+6+ibjr5p8M7R7+R67Lc7ATD9QL9vUBEW1opoF/mJweH2O4JzIzjRSo3F/rJHiYkCcrRSVLbEGE1dFNRlgVGSZmyV5qResS5rSm1YFSVWKZaLWlxlQ0pPjtJVK0iMRZDscDelB2ffjwwuvPfyzKTChiTxLDEJhoPU6tEhT9DiGGUYa9Pkzjs71CZwPA8JRSDquQl9WneW+UQMY2r29ZPBHLqJs6yeeG2ffZ184NoWM5hKW0vbj3kbatpWnP37ZUzMi1DiZcDiZe1qvOPq3x+9ZZAxByB5QH/trKCPsPRw56+79otz1I9/5l/k9vv77D/v7YsFQriKUOemT5mhkLVS3y6dhBJXDI90eEEpglLSkWtD1BoXI0OaESptiAR8CONsUCstmQtKj+EfVDaPkimeMgaUBp0FjwqCSYOJCGejj4Q4SCin8Ggi1WrF+uSUk+M19x48oC4ty0VNs9vj/cDgGgbnODo+omlbLi8vuFivaJsGix6zXcxuJ+e8ucSHQNuJ2VkkFWVTGltatDFsdjsut5uxcq/Rhm7fsD8+ou06qrqirhcUdYUyBlslO3trqRYVxuhRj2C7GgdSz2eQTJV21VBUJa4fsFXF0He0u0bOyTmKqsE5h9cKr4GuR2Wvj7IEY4lI1eHgoesinoCOAROl/oxOg7pJPh06SO0brRRVMWC1oXYSArJKCvrZfM+VMCgYYUuU0gSlMHoqrqfzM6U1ysttHrVIYuEqz52SmWVwSoTMPhBdYkecEjZFAz49tsnK5CDrBkamQJ4zGFOFUdMK6bOorpi4q6nasWTiKJKNbdrp1S44ynGhDiiPq1Gha7Wt8SWD4AHDkf+froOahR7yOjMg8orNvWQ6/aoB5Tp6YT4QZUrq5efzKkAx2vjP0N0rAch1k/FrD1+94rPpEThc+1XtKgMybWe6lx9yEz6n7fWP+Jr7ftN+gDzOi+2LBUJStkoIXmzIjcT6XXASgzeSHQPgY8QT8VoRrMIBQwz0RJyKBA2tG4j7LRQVZn2CtmWqQ6JAabSy40AjTdgPGQCSMFAxzoiDQByGEIGACYoiCTCNtWhriVFjggLvCK3HxcBgFJ2CjkhHYgCqioXw8hAXhBg4Pj7CeYcbevpOmIR2J8xCs9/TNS1t13J2ccHgBnb7LV0v7Mhmt8X7QNd3+BAYnMN5R9/3bC4u6Ieeb33n23xz6KnLiqP1CmsMi8WS0lqWqxXHR0cYa6nrGmMMxohAsixLjk6OKWzB0dGauqqpyoq7b31JBvKMCBNzQkzuqD5weX7OdrOhbzt2F5dScK4XUWwYelzXMQw9l2fP6LuWMAxSb8d7+r4jhkDXDwTnxWQtDdqd0mgFVjus95KR4zsMisfdnlJLSnSJCEZrbbCImVqpbNLcpJRhrUePk6Upxto7VhusMRRFIc/IgetqHGvriK19YiYSK6KiGLbl9eK4XgIlicUgiP/MmGmTBvTMHoxhIa8TEIngVfIyAezhIHxAoccU/kqpzi+McrNVX2BTXtaXZ7H47GcUz6rp+HWcwNa1s/aMo17JfrzuyH/dTPj68MKHDVFx/B1n/375cRy67b5szy9Z/2U7/5BtvLzF6bsjCkQmTh97cP7BDGsfftRX1/g8Db+ffVOv85B/xu2LBUKAGKWqalRqrJzqvZd0XGNRSbsRIngEbAStxOYiRlwMeCXL+iQiNSgqYzBlMXXGEbQ209+S74tYZydTr5hnRJGgIl4lmWqcnDm1lxn1oiwoTDbgUuAHgm/BDzitGYgMCgYiTil0WWCkVAwm4aLMwGuVQwXiD0KEru0k5DH0bHc7nHM0XcPgei43G54+f0Y/DFxcXND1PWfn55ydn7Hb7theXuLcwPuPPuD5s2dIt5o6rNQpLpdL1us1xhgWiwUmDb7WWk5PT/mRf/1HWa3XfOmNN7h16xbFoubk3h3KsmS1WFJYi7WGwop3SGnk0bt4fsb28pKubbk8uxB9yYX83bctzXZL33fYJzVt20i4p+1Ej7LdEJxjaBpc1ydWhOStkWeUQQBAlDCLjhK20NlTZBDDtgKxmy+MpUpW9ct6QWGthHSKgsoWnFZLCmNY6opKRwqrWFR6Yk3S9cr/NtnPLh9PjDAMIkxNlZKzGFZFeV5UiDMQEkcB6whCmHiGmAf9RDOMoGQWuslMwtXBMD/ocWAsCpiP+4VV87ldB0gO1pmBjzC50E4pyHK8QU2Dfr5ehxsaiaAXP3jlsP9h7eW98OvOlaeh/EVlxTUrytqv0fF/GAD5eMPnDIBweA4jIPmszGQ+ofZ6R3vljv7+xiCHLNjnpH2hQMg484gRUX4EdMqoGJfHICXvk0g1Sq13YpDiZz4tDwqsSeJUaxKTIZ1xyBkRwomP4ZcsQlUqZ8ao2YRC4UOaH6UUyjEkA0RtCFoTYwJMkESsBqxkOyhjUEamiS44ohvESdTIsZgoepgQ49RxjyNSxBiNjZa6rvChwBQGHxxlVVEvFwzOcXp6i37oubffs2/2tE3LW2+9Sdd1PH38hIuL89EPJcQ4uq7qdE4hBIZhGNNRQ4zsu5bvffA+VVlyeXnJcrVivV7xv337WxhjhFEwWsS6xlBYy9FSAI1hGvh0FKFlsVxgqoLFesnxrRO8d5zeu40bxB22b3vc0LPbbZNQtsV14uMS+kGyU/qBGKTOztB3EiIZBvCB0PeEfkgDvNStGcdLpQnp3nWhRw0DVRgovaHUhm3fSWjHFBTaYI2lKsuUiSPfM6nOjlYKG4WRqbSl1CJS1kEM1TRRStsohdEKHRWmMCnzK0hZgJi1HowD+XjTIxLCikj1YhcTy5SzacIIWq4W3xsHnxiIKgOGw/cMroCOaer/Ykc2fhYm2/tZrZ6rzMgcgFwNAcW033gwYuZhczZofmiL14RyrumGZ9GZ19V1TPBDzY7xxTYHdR9ljH/xqF9kcz7aYHIoRlUv/Cu+/slfs+0fSPsou/04h/h5G7U/ajt47j5/J/OFAiHAmMoYQsAhnWuRsh5c9Hgf6FXEGWGoo9FgDcFHBh8ZiPjEjlBY7KJClSVBAzGkcIeTzApjk9ZEo67+NwMhASXgJwQCntKWFKWV2H9KFw5W47XCeccQJJhTWItBQ1miqhJdWSgU0ULnerpmR2EUtZXzK6zFaNmrjhNTIR2ogBBtSsqqkGsEoBBhamEJIbBvRYuRRb4hBpwbCMGz3W5pmoa+79lvZYDfbLd0Xc92s+Hi/Jz9bsd3v/sOu92WzW7LbrfnfHvJux+8h/d+BGpoRu4vpOq1WmusVizqBQ8fPmS5WPKVt9/mS2+8wenxCW99+ctUZcliJaGdxaLiaLXCGD2GRvqup2t7nBto9lu8d/RthxsGuqZle3GJGxz7zZah79httlIAcBjYbza4YaDdbOn2uzF0EGPE+VxrJxCcCEybZod3EvozSiIbtZenoYjCnEzgI98fLanIhVQhro3U1DmqlxzVS6lynFKHKy3W/IXSVNpglcEWFdZYYUZy/ZsDECI3XAbjSEZP2kX0IMt0Wua9w3s3DrAHc8I86MZIGLSY7PHiQJlZpemBmr4/384YQknXUMJC4eAYx2Xzr8crx5UWjscRxgOV5SiUCi+dBV9lcl63fRrSiDlj9EqW41Np1+3t6kl+/gakj9Q+j9P6z217NVj+/rZ3LYf5kdsXDoQAh1QzMiuRPkpYgqByCl1KYVSkiIoIHeUzUFoMyVQy9hone4nZiJGps591upBEi1HU8SqHaeYHlW9OGuxzKmcWFIZ0DBH5TGktsdnxWZnT7rI5ld+6HGcnHgwMmb0RIyupVhsBU1iKspTvaEUIHpSezNiiFICrFzVd19H3Pc1qhXOO5XpN1/cslwuKomC/XNK0LcvdkmqzoF7saLsWpcQi3Xu5xt57hmR774Ze6uok0eQwOOpa9nV8dERZVrKvxUJASAqDLNoF/TBgrWG9WGKNTfvwhBggVSi2FShjQelEbjiMtbhhwBQlylqcG0QoOwyUdUW3W6TBLg3Yw0Dw4nzrenGc1QpJN06Mj4uRfhBXVe8FCMogHVBKUQbxscl1dozS9CFgkgg6aI1VikpLNk9lPFY5CmWok0GbUkq+E2LKokkurnMmZBbz0UonkJDgcAS82KJFLSB4BAjj+zO9R/IcFWORvxinlWPad0hAJAsyR+piDiAO/p3/kOdLKSZjtisD4agXYtovqJRmDOjrwkM6vSbX9KgHA9MV9kDl/836j/GjzBOoF8mTV7QPAzwHoOg11n11Oxx1X388eQ026IvaPvRU8rP6r8j5fuz2+bsOX0wQwgQYFCJAjURchD6Ci8KCBKMIGrxR9M6z7zuaweMJYJRkfRQF0RiGKAZTxsqAjQ+EwRFymmUyuNJByWy3LrBWzMzQMHiFD62wMz7ie4dWBquLNHvLxy1ZGEopPApHJBqDLgowFo/CA8paiqKgtJqqTMZbWggG7yIu2cdrcgVX6bSlunABCkLwok8ZghTc05qqLNCmpB8cg3MptCWDQ71YUC0WBOdxR8fMnTzbpmW/2yVBqAzY+66l7Tr6vmO72QjLM/Q459ntdpyfnTH0A5vNhr7v2W2k+m8IAZf2/a1vf4d/+b99a2QQlFKjAZfRGmMN1lpO1sdUZcnR+oj1ek1dV9y+dYuyKFnUlfyuao7WaypjufPwy1hrCd7hnWMitCNd19L3Er5xqc7OdrOl61qapmG72TIMA5vtRs6n6/F9L+Zm+16K/7U9oRdzs+g9EXDGEJRi8IGdCwQfcG1D9IG62YqYNTEgGmDwRB8EhGiLUYqllkyeUluqZHtfFVYqH2uxujdGxMDGGFbVgqosKIKismJxXyDARCnQKgH0bC8/simMYlcVAjZGvPdSfiAVPxxrBsUgPivKyKDq59sQNjJXPPbO4VwafA3jfsZ50wGgiCmNOcgzOIZtmJiTrIVJAGXaRtYtTcvz8YxRmGkekHaY6/SkUBWIviyDnyBYzGh7fVd9ACYm9CTbOnS9HY/nuu1c215nzevW+YTpm3/l2lX25+Z6fd6AyBcShFx9jCJiBuXJglSZhEWVRKlKiosN3jF4GZhTD402Omk1UqzaaKy1RDyhd5PXw5ipIIJVg5IUT6WEUSFglBamJSQmQ4O2ejJXIyYmRHrIiQnRKG0gMTKigZUB2BiNtTrZfk98TQiJPs9dcbYYT52v+FsJy0Gu7msNxtTYwuJDoB/CyLigFNYWwqKUkRhqAMqyRGvN0Pf0bYdWmrKs0FrTDQO9GxiGnv1ui/eetmtxznFxfsHjDx7RdR1nZ2d0bcfzZ894+uSJLDuXgnrnF8+5OL+QQnPJdbXvOhkMY8THSGEtt45PqauKe/fucffuXY6Ojnj7zbdYLBacHh+zWi4Jx4rj01vYquLo1m0Wi4VYuBuVsngKlFYMw8CQwEnXSXbR+dkZ+92e3W7H2fk5w9BTbi7ph55+39A3LbF3uG0jYthdi2s70RClCsVBa1AK1w+4tsPHSON7/OCwfcRG0YvUaZBzTUcYnGhMtACNGjNqTha2lAylWjQ1JoGSoiioVaAIllCVOF1QKXmeDIqYihpaI88mkdkAL8LuDFxV0lSpiDjGJnAWiMSgwHsxTVOKoEwyI86CWNIzKM+h5IZpQpQKxtkILj+niskPJb/H0fux8rEUJGQ0cFMpy+y6MUQEuOFKyCN9L7GTqPR2zKmg9L0MGMZFKR4TU5hVzX1YXmBq5tPvCdzJFsaA5AvtZcPftKWPOjhMx/F6Q+t1tEH+5qc/MH1qe/jQk89A5CMwQJ+vcfpTaJ+fE/xCgpCrLaRXPyQwElMqiZJekAj4EHBeNCM5/CHi0Ww2lTMSkpV2CBADWitu373NarGkb1qayx1GGY6PVtRFTVEWFGXBtt2zfbTBeS+pvUo6YjcMCG8unWOIY3IlShm0imht5EfppDWB/GaF4Ol7JwJVK8XixDFD0k6NFabFOykwF0Lapxq7WkLSyiiv2aqINgYfxAcFGFMhD/Q2gxSpiyFIHZoQUscOPkg4JCYmxhrLoq4JIVCVJT4E6rJitVhKlk7T4IZBMnE2G5xz7PaSwXNxds52s8W5gbZp8d6x2WwkLNT1NE07zYiBuq5Ba5qu47vvvisDsxGGoKpKVqslxlhWyyVFUbBOqcXWWvnMWhH/msQumUTt5yyTsuTo9m0ikZMH94QjSlk1YXAM2z1h8Az7VtxhnaPvekII+BR26pqWdit+KO12hx9kcI+DQwM2ShZL33T4fhBxbqKLnZdaMVEbvJJqy3vlhG0IDhUUyneYYS/nfHlGoTU1hlUCMIsU2snZSCqBE5UFsFoyy2xi5EpjRddSgLIlADrUck2SfbxBUSiDikitITdP65VwmFaKODiMSzqUHIIZa+RIYUnS9QZkAqBlWyGFhA4qGkdhO1/Iyol58CcZyWVWRH4riV+m90zARWYGM/hAAcZMTEqUSYJXWQM2vqop+Ugh8U81Hj9k8DCWVvxQsHHYpjDQy9b/fufur/e9DCH/VWQI5ueUoeHrnue/itcDPlnw8cls6wsPQiLCfMjQnNgQhcxkjGS9SDEy8cYYfABl0NZMICQNwDGK9TUqJDFdQBvLw4cP+NKDB1w8P+Pxex+go+LO0TF1uWC5WrJar3h+ccb7T75H4xzaSqfufaQfegmRZ22K8RIKUiqBjygurdqitZlOKv3DBylFrzVoXaKUIcZAiA6lDcbKDDkGCTOFxHCgRJCqtIgO5TgiTdeAAlsUFEWR3s1kPR4MaCMDaddBjLh0jayRsAggRepS00phrKW0q9EobvJVkZZf/5CcREVjIce63+1p9w3DMLDf7xiGgSdPn7Lb7thsNpw/P6NtOx4/ekzbNLQpBLRrGt5993sM/cDlZkvTtDg/0A8tWXmglOLh/Ye8+aU3xf311i3KqqReL6mXNVVdc3pyQlmW3Ltzm/VqRV3XnKxX2KLg+PSYoipZ1QtWKUzVb3YCPPaSkdP3Pfv9Hjc4tpeX9G3Lfrtjc34hTEvycem2O7r9XsJ6TvxS7L5hSPb1OGHb+q4nukAfweRCejGFzZJ4VjKUBPD4fUscHEtdcKIrrNYclRWFlkKHZVlI+KYQUXNdVZIubQy1FdHsoqoprKUqSupSygAUVhgwnXxMTFSUUQtA3+8J3SChjCDutaqQ9XEp7TlGwiD3Ojo/HbtPBmoJwMiyxES6qQ6OCmJIl0sy6JjFuLP3I/0OTqo8pw1y3QASVWTwAZ8M7rLJnNFz0blADDeCn6mb1eP4lf6RM39QZL3BXO/y4pz7o4ZS5pl317UPHyTjC/941bF8ujPjH8y8e/6w5PY6R/KvIlD5pO/Ay/i+j96+cCAkKxjm7QDfzgfC5N0glGuc0m8TXa3VzIY9hzUyLZzSdDVgtBJK32RtR8RHjw8Dzg+4QbJLjFEUhaVe1JSLBV3n8L6RKqhpsM/Ho6LMRg2gkYqxetYZjuulsybOgBJSGXc+2BujobCMsRgF2pokeBVWJOYwlFISJtLy73ztgtAoYqY1u6ZySdVUwyTPQOfHmbQH+ZhyJ69gLPBmtAAZGX9CorAVhS0YhoGisAzOEWJksViyXK5YLlb0XcdisaBrO5qmoWka2rZlvVyL2dpmS9N09EPLrtkKK5Hs0hfLpQAxoO17XAh0wbNtG4qyYL9vKApLs99LJeJFzXq9pigLTranVHXFcrFguViIf0cK0flkkBa8l/Cf0diqkpCa0ihjid4zHA1SP2e/p2+alCosuotu3+L6flwWvKffNzKgulSlOAScF3FsLo4XvUf1FuW93L9uICqLVwVKaTqj8CrilGdAoYOi8B4dFe0QsEGM1kon2TyL4LDGUNmCqpcspEVRiSYHqSNklaZWVpiQ4Aip+JkykuljTBLfxpjCMXF8n1CkGjd6LMY3PkchpDS2KKYqiX0hZMYhPeNJz0ECCPIOja/72DcQ/QFLkXsM2acZ3438HqDN+F5K1lsEHw+ydhJRCkj4ahT0hnQw6ImZmTEoVwMd88+mNQ61JAdt9n7ny3AYfHn1IDBqXeaUzvUrfqrt4zI6H9au3+7HCTO9TtjmiwRApqauPEEfvv6n375wIAQmAnP6W1rIY6QCbTTRJBeKIKK7oWtxHmxZUlubCpvJu14qjUfLbNdJpVqrpXQ8yhNwBOUI2hF9ZLu/oFWGpt2x321oh45FXVKUmvtf+hK3797j2fNzvvWtd+j6YWRChAEQ8FGpgkorKlNSmUIKsTGrI4IAk2xOFrzDAahIURQCohRAYLGosdaOgEFGf4kBeS+hKJRCa0k77v3A4MULxKXqsX3X4pO7qM4zxaR5sVpjtUnrD1Lmfn4HMg2eQY5SwsTAKMRViD260og/CrBcWRbLdH/6I2KM3L33QAYnUgZSjEQvbMB+39A0bQIfko7bth1979jttjx9/lRCP7st/TDQ7Pfstjucd+yahl3fcfbsMZd7CZN0bStmZUos2atSQEdZFty6d0cAZVlSliJ8vXfrNlVZUpcVRVmyqGuOT06wxrKsa+r1mpOHFct6gU5iW600wQ1E7wjO0TfiWzJ0HX6QWfzQ9QxDz9OnT2n2wg41uz3OObqunbxrUGmZbCPsRatSeqgGUN7TdS2tdwQcPvaQrORxEdqcNithJgUigM1VhxH9TF1UWG1YFAW1EaO2k2qJ1YZKW3GRtQV1WQnDUiishmgVeAMxooOEOnQGFhERqWaWISaQkurwjOvkmjcxChiLCPhOj1ycfZ8IOCc/MRCDH0FC/hlTyGKUp05NlY+1McJKpncN74XlSenR6spjPj7rIaQaPSTWNH+WX4UcZHlVNz7N1Mc6O3k747LDAUN9GKCYfeNaJuW60UcxhgOvay+kbX/I3q8/mi9S+yQcZD+/7XW0R58lc/WFAyEvMCEHV2uaLhwwISkuHXwgpIJeRs9cLpkeu8yYaC1UrdEyCPrgJJWVQCAwuJ4Q9ThDHYKTbZqC1XLJ8fERbdslQSETMCB3oioxIPknMyF5hpfBh3QQSon8NgTGY5tn3RijKVK4JGYwhogVtZHtQxKfKi0Or1HCTpmfCUFSVNEaY+w0YSRPHtXY8ceZw6bsK2cbCBDJwCMfYIyJvSHNONNyq6UkvYSkBH5plUNAVsICSkCQUtA0LU3TMgwD2+0W7yRbxznP5eaS20+eJIByQdd1PH/+nCdPntB2Ha1zYpPvHLv9nr7r2Jxfyjk7B95LSCJl25xvLqkTuLNFwWqxpH3YUNc1q+WSuhbWRBcFZVlSJBGvKUvq9Vp0KIsl1hhRNMeQQEgroZTEpjjnGNqOru8ZrKbY7TDbHbGu5NjaRgzj0nVxzqFa2UasO+LgsH2g6DzBOZyWOjaDj6mkQcS79OwGJ0yfl/CHAoo0AGeAICCkxGjDqqhYFCW1LRlCoNCGVVkLa2IUQVmsAlRIA7xU/xsxMFLbZ6xQnAa7UQybs2DilIqcQQghSH2nDCbiYTG+OCMi5AWO4CfGMGbzwJFGmFg6MoAfmRD5OzqdhOiKGKYBWObGGWGQ1O9X6MDM8MxAyLxfepERyC9TBg2KrHDL+pQ4W3NMI35lDvGL+736WbyySJErAb+43bHez8t28Rptzqp+mm3iPl6HyXjZKt8/g3L1HD/Lgfy12sEBfn6O7gsHQubt6k0fM2RQiOfG9BOJIkwNMcWCjQz8aVYYU3Wx49WaZb3EaEVRGJSKnF8859n5I7zzuK6Xcu6t7ExlOGENxarCWitZIm1LP/TS6QcHWqWaII4YBnlNTEyW3oGxGm/IfaacnTaGoigRkNDjg6e2JXVdoxAXVSK0bcfmcst+v+fJs6cMw0DTdTJgaY22Vmbm9RJrLcenJ5zcOkFrI9tSohcIWbORhIe5MqxSmjJJSLIQcNKAQLbLz0LfUdiXZ7uIQHa0mRoHhGm2mH9nFoZIytSY7FByaq/WmuVymbYt3zu5dcLtu7eFVRkky2O327PdbnHese9anHdc7ndsmwmEuMHRbrcMbSshDy9J3z4GApGmbWlaCat9+7vfZRQ2orDWUKV02aqusUkMe3J0TFmUnBwfUxYFdVmOzqo2gcij9RGLxJgYrcEqTt54wPEsdJhBcZ5lE0V43LathIL2U9bOcLYlDAPtdoMfepp+T9Pv0zaSrsQ50WWECCnc45PbbK7cSxQBaQR2UdHGiPYdzy5bdBRhrQYJ6ZgiMSGiJZFqxgIky2TRX9mCMumkSmPRSqobW23SuUtostTi+zIeR4hibZ8AigDy/O9pWQxlYlMC0aW6PKNBWiA7xx72G+kO5scxMzQKCFZCbzPMMU4OEhBS0UrfEeNoyhbmzrAzm/2Xj8BTKCak8GSchXtGJmR+EK9orzWszBFBhByOvfrdEXx9nxGc78cw7nWh1cs+vwZCfcStvM6RvHz/4zv6WmzV623xE2vX0mIft30y2/vCgpCrtyhPQKS7VkSV0lHST4xIcbSE/I2ZQEgMaeakFEfLFffu3hcQUmqcG/j6t36P9598j0VVs14sISqGvSMMATd4XO+plwseLB9I5okP9H3P0PcCOqKX2mIKCELLo4TRED4jjp1b6jfHE9RaU5QGCDRthw8ebTRVXcl3PcQQ2V5uuTi74NmzZ3ztm99g3+y5vLykaVuKsqCsa4y1rNZiDvbDP/LDLFZLqkpTV1KQjtRZuyFnqnj6vsc5R2EL0c3EnEWUemwloC4Dh6ui1GmWxzgzHf1HmBgWnZiP+bYEeAkd70YXUAGLxhjKUgoO5ho2cv/jeN0UUlfIOTd+Fon0wTMEP4KQoR+4ePqMZrejbfbsNhu6vufxsyfsm4Ynz57y5OlTttst7773PZp9w37f0HU5O6aVvsdalNasl0uOj46oqoq7t+5QVRUnR8ccHR1RlgXH6yVlWfLWm29x+84d6qpmtV5RliW3b9+mrmvKqpJ7rCVlXCkl4ZdkRd82wo64fYvvB/bPz7l4/ymu72k2G1zfs91fsm02AkKQwTwkgSghoFwQoHa5oe96sYlPn/edpB/33UDoHd71dJstwXl8N6TBXkzMxMtEKhQX2lAoKey3rCTFeLVYsqgqCmNZVjVGG470kkqXIqC1AmQWZYFNYlidnzGXHGHJDCFJtErKKiKlr5NEv256PqOIywl+GshHPUd6GpJ2SJCuVEe20YwFAMfxP+071wAS4CSAASf1f1RIYa/IGGIa6//kl0BN/xyPh5TVN9OaxLFfmo77dTiF1xkWDniZl21OHbJA8xZnn72sxZHF/WjD6XXHH6/8fuk+X/L9T6e9yGtN+qUrq3zf2/+EgMinBkA+amDu+vaFBCEveygjJFdS+a1y1ocSDwMfPD7MtA6Q7CBTNoyS9MXSmnEQjORBNukZjEFFhSk1SkcCDoIjGoOLij5ENvs9fQjsm4aiMGhVEKPMrh0yyzRK/CuMgcIqCiu+DlpJpxrysBlVcq6OabAV8d9ut6NrO568/5h23/Dk0VPOnj3n4nLDu++9S9d1bHY7uq5LjqkFxljq5YqiKLjcbHjy9CmL5ZL79+9RVxUnx8csl8sREGhtUiaMQimN815me1n3YdIMHkbeVqWQwXwmd1UoqBLaymzCKGIMIlII5MrF6SezKSOJcgh2Ygx470YgmqbHKNQBi6BSz2mUAmNQRUFYLvGlw4RAv1zQ9z3dyTHDMLA6XtN2HXfu3uXhw3P2+z0P792n67oRhEhqcUMIUWz7Y6SwUh8nF8EzxuJjYLvdoo1mv99ijaXrB46ePKEoCqqqpigsJyen1HVFVVVUi3oEW1pL3Z0pmyNdnVRh1ytFdbyi9AuqVU3wgWV/wvHQItlUM4YrWdPHQbxSFpcbhq5P/iY9MXiq5CAbeycgpB+o1mthXxIIIQ26CjXWytHpyKLSDNbglSKqQOcHTHBc+gGjNOddI4DFWGFJxhCQFhCjxXBNJ92KVeIya5SS1GKEUdKIjsVqle6vGusVxKgAjQpjdakZO5F1KEHCOgks6BjRLn3mZ+nFCVTIBCGO/QwxWbWFxGIYCR/poCeWZG64NvZT+XAmwa28RtmDRb6rDt6f8QmfvU6TiDbvQ12HENI7ltkcWVVN331hfV4+vlz72dXjmp3nC6tdP7gKaLk+dDWd+eEE5vD7E6f64ueHIO7aI4gygX29dt1RzLd6dTL2mps92EK8uuBjto+2gZfzSPkd/7jHI+0LB0JGoy+uAyH54ohde7bKDsbgI3TDwBDkQbXGyiMb/DhhiipIufaqwsdA5zrx11AaW5TYssRUFQqNKUqIGvYdbt8Si4ImaPo+8HzzhKHvqKuC06MlWsPQ7/FuoB9A4bBaUVeaRaFY1Irl0lBbjbUKTVKeBI8n4gapC7NcrigKw/nZGY8fP+b9997nv/xH/5gP3vuA773zLo/eeyS1YIJYpw+DwyVTM7LAtKjQxlAvaurFgtPTU378J36M09NTfuqnfoof+eEf5tbpKW996U1JGdYGO0ixt7bvx21pK1V0i6IYi9oBaGMxRuN9mNImZ12KSr+nmdYEVLyfdCZpR+TyhErLvdVKYe2h5dXg+gNBHwdbiQcdmTBQMmCWRcXqtJKn5u7dxMrIN0MMdINLoZ1Bfpxjv9vhnKfrOoZhoOs6Cfe4gcvLDW3Xst1sOT8/G3UrwzDw9PETPnjyiKHvRcuSqudmS/jsx7JYLLCFpa4XLJfy79VKqhAfn5ywXq1Yr9Y8uH+fqiw5PjqirmpOVmvuvvkQay3LxULYE6NQVkoZeO8ErA2S/TT0A/1e6gjtL7fCCl1ccvH8TI4riS3j4IjOi0dKI+GqkEDIMAz0ybAth3TwYWRsGieFDvu2Y+h3SYCbign2PdF5CmNSiEaN4Zj1csmqXmD1VHunsgWFFsCyKOvRSdbq5C6bLPyLQoYikyYUGSAJHEkDVRrkr4pkc6jHZGDXDSl85fFDL4AkhSlzZWQdwRRmfFKVmlVNDkghRecOQEImOjMDgpqeVmFEEwXj5cnN4aeDvi4BmKydGcFV6h3VlbExh6dGx9z0tXzuH6Vlp90XDuhwl6PY9mWrzf89gup0LXS2ZkyAKfnaXt3N+F0938aVz15c+/CTeOVf+d68uh32aS/Cno83QqfeLm3/k2QxPhn2YtrWx29fOBACh4/1+FAeXI/kSppDMekVDiEmVmFSx8ekbsthAVIM3oc0+DgZXI02KKXJDqdaG4gGZbzULdFGOpQQ6XuJ2RdWXDqtUajY41RmYqIwHjrKj8kmUvnI43RsTPHh/KC3SXD59MlT3nvvPd773nu8/957PPngiXRoyXk1gxH5WmYvGpTWmI3FFpb9fsfR8RG73Y433niD09NTtNLcu9NTFGKEZq3Fp5nvwfWfiW2n4z28GSOdrdJyNZu5HXSUU8f2YndGYjLGDR18dsC6vKTzOEDxMbNbcl/FtMxIcUAlBmYxQp00Gd778afr+hGY5CyV3W7LMDjOz89p25aLiwuqqqTrOoqioOt6mn3DbreT7bcSvul9Lzoj5xiGAaUUXd8n7c6e3V5EsbvdAmsNTdexW63YrxvRoFQlzjsWtdTBqauasizQZUGh5b4ZY+TaJOGm1hq8l0wnFNp7Agrb13gUfQrHqHSdcF5s6p1PLMkEQvq+p2sauR5tR3BO0pYH0Z24vkOlOj8uehyBfhBmzxGI0WN9pI9BwGUKxYXB4K1UIu6j1N6pYqDQnjJ6hqSpqZHzKKOnx4qhX2JMrM7MicYmZs0ieiVN9v1QV6o4S6evtRrZkqghepUQRZRU46z9yGN/eq5ifjxl1JRnP3pQZgQJ89n8gcR+HNNmfii5XxrZivkLktcJU/G99A4pdWU+P+L8rDsLE/BJc4SPo+HI4P6FV+/KsmmIT8aI6uWcSDw8Y0bWKIfAXjiGlwGAl/Em46HM/pQDvm6C+7L2KoAwP6aPMlwfnvmLoCl/dC0Hc92OXnvFj3SAn1j7woGQOPu5+kF69wUMaAPKEpSR8uyoHPZNrIAejcxUmoFiLNvNlm9/+9s472j6lhA9feyp6wVRaZpuADwqKEC2XSzWaK0I0QhdqyzGlKyWR7zx8EsUVrO5fELb7bi89LR7mWlpZTA6YFQQ59QkTgspi0GycTTaFkDk7EIyOX77t/97/t+/+Zucn53zL7/2TbabLTpq7t1/IDqOYSASk0+ISXR/RSTSO4cPUxE/5zxf/9rXMNbywfuPuHvvv+ftt97mZ3/mj3ByespP/Ngf4O7duwnABbzz7FPqKIijawxx/Dtnx8DLO7Z5KGXE5eqwR5rWSV4jKZVSPECG+YrCbCTr/RA+pAvJ8f8YCQoIXur1ODUCpQx28hwnA5Axw0dJXZ8cdrp79zYhxBGgdF1H2zbjv733XF5ukjOsS6JSqdgcgqdpGi4vxCI+A5khAZPgJUXXe89+v+f84hwFfOMbXx/1MMaYZDAmoGOxFOakXi6oE5uyXK0wVvQZdVlRVxVH6zWFtRwt1+I2e+8u67t30VpRJfMxnR18Q4Tkn9M3HX4Y6PuOZr8n5HRj7+j2Ld1enG+7pFvp2pahTynFg2g2XNclhmXAd326L0n/EcWu3znPtu2IIWK6bmIxksbCJGBuFSOAqRKoLI2k4GulKVMYa1UvUsr0FD4qMghNIMVqzaqoxPNnVWBVJdtL4VvlAyo9PzqDkVQlOnrxjZFspOR54uxUayfIAOfG9zwxIWmyoWA8NxXjGIoiMmUSpX1m59exvk9mRWIK5c5DoRHxLyCHl8z47uU37MV3NYdsZn+POP/DmZB8DjEPxQlI5VpV0zbi2Hfn0JK8Y2a2jbxPAWgjwzIbUMd+JAn1DwDSNf3BdCoT6JimMS9+ax4EmlibLOo9HJWv3edHBnp5L+MVfOHT69rr7UJ/+Cqv1X6fMiFXEnRny/NkICHtWWaMABA1hWYTCMmCVaUUVVmCKWjbls3lJoEQcRddHC8oFiVDiHRJrU+UUIO1FbasRtAvxIPGaEtV1ZyenFKWBmKLMYGu2QgcihGtAlpLDFepPDOIKYafVP0I6xKCDEJN0/DNb/5Lfuu3/inNvqHZ7Ig+cPfWHY6PTxjcwG63JxCp6gpbFFR1zWq1IsbIdr9ncIPY2AfJ4nn83mOcczx5/IS6rvnRH/3XqesF9+/f5ytvv01ZlOP1Hfqe3W6XwIBQ/DHG5IRJSm/WSXejeUGoOpsezbUN+aMX15dl2Zwtg6H5jddagMirAEjeq3RUYbzveUvhuu8YMX8bzc/I+1IURZmYBk1RpNTose+f2KuQQi59PzD0wxi6ymmkIQY2mw1Pnz5lv9/z3e9+l8vLS7bbLZeXlynN+Cld13G52XB2fkbbtGwuLkZgFGMcQ0Naa6qUVrxar1mt19SLmlt371CVFXdu3+Zoteb05IQ33nhDKhbXC8piyaKuWS1XKbVYQjriHzKFM2KItPu91BIaQYhPIMSz3+zYJ7DV7PaTP08quKjSTMD3vXjyNA3tdjsWzQsh4NoW13X0Xceua/DRJQ1KnEI6UQzeSA6oOkZhTJLgvLIlpZFwTWFFKHtrfcyyrjFKBLRa69E11iYmprIFsRBx7aIqUUWBthZblMKgBBL4YAyFhF4YIp9CL2I+JyFM4+20fgIP82reI2BIovCcAq9n/x6jGjltOcaZ6dvM6n60x0/VoWHcb0IABxYYavYOXttmwCLXCprXDLo2NnKwLE71fMjnEucvygRGMthQSL9t9OzzOALQOF6riRTNpS4OWaPxLZ5OeDyq/PsQgEReDkAmCJK0NWoylxz7lWv3Mvvr+2Kc1HUbv7a91qavTPY+6qG85sKP1L5wIARefg0jJMGYEgo0Uc5zFkRisCKgzPVllNGYwqJtyaIWQ6ambXj6/Bk+OIy2aGVRMYnx4jxCK6LVGCWdlBBRCYQMvePp0+dYo2h2G/q+pUu0tTFK4uFWaOTgHREpYpdDAhgjYQIjZem/8513ePLkEe+++65YhfeOqpQsGaOtmJI5z5DMxEKIaNNLOKBpiTFKgTkvlu/KSH2b4+OTJOAUZuTs7Iyvfe1rPHv2jB//1/8Aq9Wa5XIhnhhJtBrtzLU1SkrmvF0HJg7uXoSQCpBd92Je9/3RR2RWXCyvl1NaX9auGj+9IJ69bv+J1VEpXCPLIQOTYRjwPvl2JEB79TynvjaO2zHGEBGdRgiB9XqNMZq+76nrirYRQ7Z90+Bc0pW4nvOzcy43lzI4b7YH2Usilt2nGkniOpsZJqU1fnC0IfDs6TM2F5c8e/qMR48eUVjLN4+OqctqMmGzlvV6hbUFZVFSpuwjKQioxoFEa5XSbJVkuJQF5fEKXZfEEDnKRQi96CpUlJl+DEEqE3vRmbS7PTF4XHaNbRr6tsX3vdTeGUM8HjcMUkww1eqRUJGYwOnILPSSiu6BiMGV4pyB3RDEmCyBUEMWt4IhUmjLuhSjtioZGhbWUheSXl0kt2WTzPtUYm5UlAweHWUM1UmbUkQ9ZfakZyFnac1n4xlcqLFyMakvkUdJ5b8T+FApC2dKRY5JQ5Lq/WTGIWfmjOtN252E4/JMv/jszj+PE8PwAhOSgcTs/clnGCdwEGHUvGRwTg4PwRTmSn0yCBiLSChdgFWyOkh4Km9//Pdo+HSVDZmONeMxNQ7w0/mqDDMm1CG/po7jYNIUERfdwASKZIt6ui7jwviCmPPV4ZzrWw75xSvrvlooOvvwpX3z67XEcxOTbufjti8cCLnyrE/LVf4ssSDGgLF4UiG5AD6KG4iegQ9txEOjrCpsueDurdvcOrnF2fm5GFz1HdaWAkIQu23pI7J6Q6O1TR2kJ/hAYTTWVLTNwHe+/a6EWmILOJr9Htf1FKWI6VZViVHg3IAnogpJO7XGYIqCsigoipLddsu/+P/9C373936Xr3/ta5yfXWCN5d6pzHB1VLjBM/SOtpWwQEgdUYiT+FF8NgLVakm9XFJVFffu3ccYw7Nnz7m8vOR733ufx4+fcufOHX7kKz+CtSVf/tIbHK1WIggsZfYYkiGU0ipVElajt8V4s667VzHRwsxmRvnf17QMGJQSnUOuYZObc24EAnn9D32OXgFA5HPQKQdVa510IpnhkH1mJmJ+nNNP/jv7p2h0AiCSWgx9Lz4u6/WKsnwgHWBKJ/VBfmR/smy339G27ZRC7RyXl5e0bctuv+fi8pKua3n06DH7Zs/Z2RnnZ2c0bcvzs+f0w8DT/ZPEYvQ0Sc/hB2ForNLCHBQFR0fHlGXJar1iuVyyXK24e/8eZVmyXK0oq4rTkxMe3L9PXdc8vP+A1bJmURzJ82E0dVmhVS4UqWUGm1OAW2FHhq6nbxoJ6fRS/qDZ7Wj3e6Jz+FaKA7pOqhH3fUe73wn70kqYqmsa2n0DwRPcMDIm2RPFuYHoA+dti2ulVk9IabU+WegrH1DeC4uist+JAIzCWOpSzNuWZSUFG6uKRVWnrB7J7llWNYuykro8laRXl1pCZTpORQSVURJGTH8TJGuJGJK4V0I6xmfWIYGmMWUZdGZCwpS5k0FIZl5UYtvG9eLMEj+Swmu8OJOPEJmYlGmczmDj8L1R1yzL68fx3xmAZDZlAl1xdi4TCDGJOUjbSNlHajbazkXFo8t0CpXNJzZq/HQ2emSGJo8bqU+aAMjUhynUtRGMvIugEks0MrnpJ0LMiIkEf+bXSU0MzrUbfkmL6bhH9j0v/1AQ8tHAx8tYmzjyZ1kO/PHaFw6EQLqxcOVmqSuL5KKL7mNiQ2L+bP6w5O0SyVkkcxHkOE7GNJgAYXYD8sA0ov60veADfefQKmJ1wGh50McjTS+eIsdBmWKUkTQYiS9E10mNlIvzC6ksi7wcOtHK0ckMeMww0VOVVFHjCUDoe8lmGLODYmJwIim7oBB6v+9pm5bnKRPn+Gid0nOZrpEfPRzJhQCZCceufTw/Ceg839zVDvE1Ach17eC7c+EyE/g4/P1q8CQt1UA5mF3G6ZlK+zVJ8yL0uugdQpy2EWMUf5iqwjvPsJDwR1mWtG3LsmmoFwu6rkNpTdM01FXNoq5p25aqruj7gX1K7RZB7U7YlDSYZytyozNTI0yLhK0i5rzAFgW7Trxnur4jxEhd18QYWS4WVFVFnfxBFrV4gpikVcm+IhAJTvxzPIFoNOgkzg6Biigz4RCISymGN3QSvhn6jrqpxxBQ8D5Z3EuIMIdGXN/jBnGH9bk+T2FQ6d8hAZSYUpGlfLFPhELKvkvW7VFMSDARiB4bwDnFoOS9bYOAkC4GmuAFmLhBqhynkJBBhLZK5ZpOCoMANCLCgMQovZSK4tSs8qxfjaEgo8USP/qQ2JEwAQw/ZxRA0pAl9EiY1s/pyNmNdkYGTI//HHCECZBMQOTqYx7GqE9e9YBRmH8fICg5toQCcoJAPq5oUqhj1rGqkCoVh+tYhunXvLZQPpv5UZHYi4TvJmA0j39dfbfHqMgVxmi+38zCTwsSEJmd+xU9nHTBBxTKRxrXD0DI1cM7aB8NhGRQdd1W5IPXDxN9WPtCgZAZCE4XPtFzMwAyotOUXgo6UbIKj8an2YdWSZia7NC7YcCg2Ow2KCKX2y390Is3Ru/QQQRCoo9QBIpEuUlGg5gmSVE4mZWAC47BtygVOV5ZYUi0odQaGxW+6+m1+Fasl0sKIsH1DCFIzHwYCE3D2dDx5MkTvvOd7/Ktb32Xy4stVbmktFb8PJRm17W0+z0o0SsYa7h16xbL1Yr1es3pbXESffrsKU3TsN3v2Oy2+MHx/rvvQoST27d4+PChVIbd7iAE/vk//2d859vf5k//6f8DP/IjP4otbHo/BYBkDcgUjoljKOBVVKOk3EIuCPYy8JCXZ51JjJMIdt5yuOTVgIBxHXGBVZN+JdcQmYlch+QWOwwCXzP4mB+bYLzrhV7j+jGOPh1aabFiV0rEx2EqSBgjIkbNxdvydhJ8Nia52wJqvYYYuXXrljAFzokgOYQUjgsj2PDe06Wqu/tkV98nw7O5ePb8+XOePn3K0A9jxs9uv6dpG9q+450P3mNwTt4L56WwoxbRp6QWizNsXZUYawWEGMNqtaKuaoqiYFnXFLbg1q1TFosFq+WC4/VKau8sltjSUC2PObJ3BMgkNiUGP7rZ+lwnJrEH+90+haecpAwndqTrWsnq6TpCkDCPGwZ8qrobfKBLzrOhd5KO7D2x60d2JA/C0csg23rxFBq6jn5zeTBDmcSjohtRQG1LCmPGAoFGG6pK2JLCWEojAC17pNRFQWXEwG1V1VLkMsi2a1OwLJL+LIMQn9jIDEyQ0IUeZzLpHJI4Nod75mGkA13IwfwuikdM140AQ119v9Kf3qVnOV4/NmULF52H8myaFyNkwzgv9zNqQ7Qmjdtheo/GsM1UqydjFM/Eiqj5PpkPv9ehJ2mSMZXNGJPO7ZqJRi56ysgyTe+4MB05fpOvzyx0PyvGmCDai9dqPg96VT2f2b/j1d/Xfu01QUi+z+rF3jtjKZUm9qMh6MdsXygQkluc/f8F6JgfhhSWyWGaMP6oUTcyhnBiRAVJRez7nta29H2HzzqDEKTSp5aibKQockALpRu8GJhlijXNOKKPDIND6wjRoJUo8XViU3I8WysoCosNnthLEa5slz70Pc1uJyzI5YaLi0uGbsAaK/VdlAAh7z1d32MLS1lJHZPj42OOj4+5dfs2D954A+ccprDsdjt49pQmFVDbb4XePr19m9VqidGaoe2IMfLog0dcXFzwk3/oJxmcQ5s5AySv0pwNeWFGNT6k8cVlaWJwkC3zUmGqTvt8MYzyonnZlVnMbLtTSOXFbWQAktNanc/gI4yi1/w1Ya70LOyiXtjmnCELyepeQO+4BmK0Jj9ZYCoiWDWCoVxSIOtJjNaJybq6rziup5Qan6G8PIRA0zTi5puErHMQ8uiDD3j33Xdpm0bq7bQtT589gwtFHzy7Zk/bdWy2W9pWwkFD10ECcVprqrKkSkxIXYtA9ujoiOVySVVKRk5VVXzpjTc4Ojri1ukJUUNZlpiqJKKpy4JyIa6yR6u1GOKlAVXJicg9SIPYbrcTEOIkE8d7T7Pf0bWNsCeJMREQIqFK14tfSnYGDv2AT0Bk2O/FSTUBjnH9FBYKzrPvW7ZOthtS1pBzTmr0ZGFqhEUhrrCFLVgUYu+/qBcU1lJaKQxYJCFwYSyrWAmQM1KZ2KhZyKEwVLUIZNUYUgngkwA0sR065Od0NqsfTdPi+FvPGMvMio7vQ36udDeFdK4bvxPYiSoxqhwCgflqB0yCVsJsZLOSGAUJBCWVqNOkQgbxFCrJqdP5UGMWy16zrzjtc+Ih4fqTyKyESiAuJQ4k88HRPI78ruvEQGUAIsd5HRVxADVGinxa9tIpU1rlZRO5q9+Ls5+DfR2c4fX7PACg6sX1r24uChI5ZHA+RvvCgZD5hR7hxphZolJdqYgL8uIpDyooXFQElYSqCcGJiZMHJYI3FcD1PRfn5/gQUscqjEpUKaTjk6wspfiGNIgYpcWoC4Xve1zfU1UFt249oCwMd28tWS0Knj9RPNo9pdCwqiqOF7Uo9BFuIYOeuq6xZsHzpz1Pnz3nyZOnXJxdsLncUFjLYrFEo0SYqBRVVVBVt7l37x7/xh/8g6zXax6+8QYnJydUdc1yvSKGyK7ZMwwDT54+5cnTJzx79oz/+X/6n9huNkQCjx89yhEXlFK0XYNzPRdnZzx98pjVaiUahqIQSjwJ5Jz2U8raGOucP6SpK7hm0Yfe8w8Jfcw/exUTMtqfx6k2S2ZVMgCZC1yVVhhlxnTcw32mU1CHQtmrx5XBhc7FE2eAySXGYrSWz2AlCuthrUVpNYbqMnXvnKfvJNtEp3CbYtKjxEDKJJIBcuR9gcImY7Cctp3egRxOuX37Ns65ZMDmJCOrbWm6lucX5/Qp+6rvO/quF7fYGGUwjpGubWnbRq6tl+J5WT8zOMezszMAnjx7KuZsdc1qKZk46+Tmu1osZaBO2gopNimz0LqqWK/WSXchYKcqS6pS1iuqAqNKjlY1xyTBsnNJByJMB8ggJbb0vbAkbcfQ9gx9R3N5iR8cbhgIg5uqFqcMnugDXStVjkkzZ+J0ntEHMToLIZmVSfFBk7KMBhQORRcjuzCg+gHdNSigSqnFRWJHlFLCqgSoy5JVtRAfFJUFtXpMT84eKXVRUBg7OswqBRaN1qJLMVaKZxYkszXyrHsa0aeJfCk50HOGATWKI0ePUu8xM5GsYMYEgGdZO25mrCbddpQwFwlYkTlWgOnaZv0ZIY73cNTU5MlQnDE1Mb+kWR8y/X5py5OojHljCv/MjjeO564nAfBsn5m9eCUh+wJqirNfcQprHax26AZ7zUZHRuZamuRgon7NeadfB3uJL34lgzW5Tr/PQcg8lWoU6ShhO3xETJd8QHuJpQoI0QQlFV5RChdh8B5wqGEgujCK4up6wenpbayxuPweBfHJQIkVNahkBe/R2mB0iVWKwTuGvmO9WvDwwUOWi5qH945YLyuM3/Pse9+kULCua46XSxZFIe95FGt5FQKL9ZLVcsHZ2XMeP33KB48ec/b8jM3FhpOTE5ZHK5nJ7bYE77l965Tj4yN+7Mf+AP+X/+v/mbt37/LGG29wcnKK8x7nPUorykr8H548ecLjJ0/5zne+jRt6PvjgA7773e/w+NEHLBYLTk9voRW0zZ4YAmfPn/H40Qecnp6yXi0pioK+76eZtsphLjVWJx5vUG5XWJEMdl4HiOTwyUufi5hTYtMseQYMsqg1e2rk1ve9DC5p0J+DE6UUtihRRo/OsPNT8H5aT+spcyZLYjKFnMMrxgggyS+xhJX6MfXXOTWep/iR6NGuvSgFOAxuED3IMNA14p8xDyeZ5IsRjIATqbsjz2ter7QFqiinqqlqYk54+FAGi9l1y799DPQptbtpGoYkjs1gpWmlsvGjR4/44IP3aTvRE7Vdx+NHjzk7O6NpGs7Pz+n7jmfPnrJv9mMHb7ToXTJTsKikqKJNx10YEQffOj3lS298iaqquHV6Ql1XvPHwDd58803qqubuaompStarlXj/MM1iJeFaURjxeSFGhhRGaPZ7mr1k5Zw/e8YwCMAakjNu27QyEKbwh+sHXHIQzk+ad4nB9GLs5p1jc3ZOu2/ke4kl6dscJurxSXDbbuU9Hgv1wZiim91dK1tQlzVGK6qxEGBJaQsKbVik+j3Hq7XU6tHiRivusgU2eaaUKY25Vlos7wMJCGQQMnOSLQwqlgeTirFOVF4WhReWrwfR2MQ4plxHH1Jl4ohPIcNs8T9P5c9/h+DwfhhDI6T3MmaXYZd0NEayCTPAASab/Vn4JoZsq8CL4aRrm3lBlJkLO5Iuk2zrMPw03jMgW+Jf167rxbJ78sFEKnck+Uor9ZJvpwmsDzC3L8hrz8FEnE/k1MQAqSw1nbEl153ADI1E/clYt3/hQAjMAcjM0lYlNJwRic4eIXJffEyhGMT1dP4jX5anqaoqSZtNdHdIgqsQp8FM+s1IVAGlIpOo1BOiJHlJjD/QdT1aQ9uWFEZi/tEH0JKiWxVWRGiZtx+b7Mc5Lx1kmnFqbeS4Ukw1H9N6veb+/fvcuXMn0d9SEE3SQRnrseQZvwCNEzab2zx48IAYI8+ePUPrpyiVjL8ANzi8d2NBvFwl+FWAYM6ATKvNzm0u3kr37pPB1Lz0uOahjhw6AGFH8sA/eYHokVVQSkmdnhSyyMArN2MsVVWilAyS4iMiadVXjmw892nfhTyqRo8ZP5mpyaxMjBHl5N555wmpQ1VKgSaJqKdOhBw+mtRw4/lDeg5SdbGYO7V8P7PGJd2QUeejFASPjRGlAnXKAMkeIj54FvUC50VEarWm63uOjo/p+4Hjo+Mxi+fy8pK+73n+XEBIDGnQUqkDVJL2a7L5XLJJj0GcV7t+4OLykqIoGNxAWZa4EOgHR1mWPHkqtXgWi5qqqkagq5V4gFhtqMqKxaJG5cwdxP9m6Adhp6xGqYJSK2xdUflAtZ4GxRii6Ep6Mc3LA48wISkjpxMQosuScrcnOi8+Ij4wpMwmCQGJRqVaLVJ141yjZtIm5Cq9Rk+2Az3J1FtFhij3xnmFiZqh2VEOXQIdAmCzxX2hDaWWNOMMQgomN1mTZrcmsSpaSRqzyqwKkp6cLfG1ymb4EaUhJtGi2BgYYlAiPA4SulZGj1kyE3s35rak66lRQY06l5hCI/LvJCKOufyCTuGXjPxJrEWEmK+fTiGV3Kty2NWO70364CoAiUjWzbiftI9w2NdkEBJhlOJcCziYLc+zFj3TFM1/pi2n1V/Sv42bOuRLXshwyc/TfLvpJUnwc2LBrgNRL0wqP37P/ZFAyK/92q/x9/7e3+NrX/sai8WCP/En/gR/+S//ZX7sx35sXKdtW/6T/+Q/4b/4L/4Luq7j3/l3/h3+2l/7azx48OBjH+y8ycDKHEYQEhMSlAJTgC0Z0Hgf6YLCYfDJw0NrKwKoHJpB1NH3Hz7gzq3bNPuGJ4+eMAw9zouDI9pgTEFQ4KPHe5ecKrWEcgYp965VpC4t3g08evQBZWEJ3ZajVcX58+e4rkXpknVdcrJaUlkraD0LEnOoKAR2ux3vv/cBjx89hqhSgTlD17bjU2Ks5Yd+6If5w//WT/PGl97g4cM3WK3E58E5h8+0PNAlMLJar7l1+zbr9Zr9fs/jx49pmoanT59gjBn1BLvdlr7r+eD9D/jm//pNHj58yNtvv83R0dEnej8/iTb38zhIFUaq6TZNQ4yRxWJBXdcALBYLYoy0bUvTNFRVxWKxSGZ20nl961vf4nd/9/fkXrz/Pn3fU1WVCC2XS+7cuU1RFKMGYrVac3JyTFGUHB8fURQlRVFSltXIyEhooZhRz7mTkb+6rqdJupzYpHL2yZNDoSiszOu1TmJopg4nG8fppGHKDM80y4r5ghEBn9MllR69XzI7kgsShgTA5DgUpSmoViUnR0fABISGf+0rKcwU6ZNle5/KH/gg3irOOzaXF+Iq65zUOBoGzi8upIbN5SXbzZa2azk/O6Prep49e8pms6HvB7797rvTOZFCV8aSAVgG5ioBKWNE53Pr9Bar5ZLj9ZFUK64q7ty5I1WLy4KyLKmrilunp5SLhbApVYW1lqquADUCg7EI4Dhbh8ElEJPqJnnnuTg7o9lJWn6/FxHs0AgTMuk0QqpJI4ZnwXmcn0JArhdnXdeLS21wfnSl3aUCgwqP9Q6GQPt8z9B1AjAScChTsT+LMA8mQoX4o9S2oLSWwkqVY5urIqe6PlX2SDFiXlekdVValp8XnZ4fbQTYGWVGhkOnwS3l5I2+KYfsQWYWApbsQhumgTMBwAzKcr8fo4SUDlrMYC5IllQML4CQOYMRQsCnatvzAfzgWCMink1CYX3dKJ1er+yc+8IcbB7yUGp8dyc/l4mNeiEcoyam4sXdRqI3I0h6ca3MtEZ0thYYdxPHCX04nEJed2pjC4X6RMxXPxII+W/+m/+GX/iFX+Bnf/Zncc7xn/6n/yl/5s/8GX73d3+X1WoFwF/4C3+Bf/SP/hF/9+/+XU5OTvjFX/xF/r1/79/jv/1v/9uPf7TXtAgjoMsXKWYmROv0/CalMyTIoidlb/4BUIqqqmSATU9jyJ1dkEJ2WbwUs9Q1d9wxjAp+jcYYBYQ0c3Y0bYHV8nc2DrJaYr9TrYr80CYxVhTr6rZt6bpewnCJ+h+V5cgsb71ecffuXU5PT1OnWpJtzuclwcdQgzEsFmJAdufOHWKMrJbLqUZOGrDEAM2NKZ1N07zSFOwH2a4KVOfLQWaqIQTKshwHqiz+hIktEKZCyeDoPefnF7z33ntsNhveeecduq4br/F6vabr2jT7ljDV8fEe5waqqgJEdFnXC0KI2FRoTWupmpwL84V0PGYmdp3CQ578+mc7a62mbB6Vnx85ifHeaW3G7Yw/IdUTStcqIiHAkFgOHfVYV0klLcb0HMkAbLUVAa/W2KSXmbNLME0SIohDaHqefRQNzG67oU9ViPvkW/Ls6TPatuP582dcnEvVYmOMFAt0AxHY70SjkssTZLAcvIRFcwq6LPdSJymJje/cvsNqueTk+ITNbkdd17TOsVgsWCxqFoua5WJJtVgQlNSrKbWWFOOqmq4laUacvW68uJ9aJ/WEMlMSvMcrsHWN63q6RZNq8AiQyEXz5HfSlfQ9bhhwg9j7+wQ+vPd0bQd7KZnQKwVuIKgOl0JOIUSiV+yCox1adFTjoF+QMkBSvRwdoQwyeNdlQWUtZVHQBSfZOt4lM8WCOgRMAp5aK8pYUMQgzsExJrYkYKL0ZSYJ8E0qFGlUYlaUPL9KpVTt7FGSGAgVE2NB9pWJBxlKowB3dItl1mdeaQmEEIO8HyGME9b5dzLQiImNm8/tR4HtCEKi6CCS8d71g33GUsJuXMeGjLoSpWSiQ7ohiREZAUl+1hTTUb2MgY4zD5b8Ah60xD2JkcqkZRkB4MTQvK7g9AcSjvmN3/iNg7//8//8P+f+/ft89atf5d/+t/9tLi4u+Jt/82/yt//23+ZP/+k/DcDf+lt/i5/4iZ/gv/vv/jv+2B/7Yx//iK80lQdsmMIryqCLklhUuKhoe0fnAi4qKS2uDcpYjC2hqkFbYlGjjKWoKsqypCxLqrJM9OswOvZpfGJgPAJCMpAJKDyKkER0GmsNVb1Aa0XX7nDthn6/RROxCgqjKVJ8VhPTMynZNd452iaOhlbOuVHDYKoaUxUQA94FlNacnt7i7bff5uT0lOOjI4qyTKXmXSJXDp8WnzJvtFLcuX07FU2r8SGIr0HSGKzXKxZ1TVVXqXM/ZBg+T20eT82AJGe7ZPFlBiHGGEljTZqQoihGDYb3ns12yz/751/l0aPH/C//y//C7/zO7zAM2eBrcpyxyXxMawmpaC3gbpUcR4+Ojkbzr/X6iMViwZ3bmTkpKQpLkUBKWZbcvXObxWJBWVUsl0uZHc/s8XOnnUGqTkxFZBZyySI+9Chc9akjD0nxr7USahzE93BkD9REzYYAepp9WWuFCcmhnyhxfxRT2nGiteeaE3KIND2CWmkW9YKqLAk+VYv2geOjEwG87dv0fccwOPb7Xcp2kayeru/Y7/aE4BmGVHsnsVjODex2OwY3cLm5ZLfb0fc925T95VKopCfy+OICvbnk/efPGI3UYhS32MVSTOVsMd7fxWo5pkjLfV1zenySqhYvsdZSVgVlKaAs3xddGIrTIyoUJ+lK2swMjIPcRL8PfS8mbs7R9p2YuCWw1ewbdput2N3PUotDL5k4OhmRNZcb+kZ0KKRaPXHoJ11KEuiGtoNUZVsqYkGH9G3G70XU38qgqEl1dpAJjDVmDM1kNiIi2p4i6VDKQsJfVhsKLd8RpsVIH6NzbR8JGdlUmNAoAU1KgTYyJJpoMMUhixJjylAhjq6rOZslRjH+U8pi6iIxMRN7MpKBeXshoDMTMvtsXC/PcAcHzh8yOLP1ZN20rSuTtesYhlGBNYKCFIqTkyELYye+VF3ZAuP3g48iSr96bLNvRDTZiyi79M5Zl2wF9WEtAqEyn4g49WNpQi4uLgC4ffs2AF/96lcZhoGf//mfH9f58R//cd5++21++7d/+1oQ0nXiZZDb5eXla+9/7g+SfwszolGmAFvgIvTOMbiAT6ZlaHFT1bZA2QqMJZQlylhsEiEWhaUoLN5bhsGNe5gSk3zm51InGxMISZ20Ams1i0WFItJsL3H9HtoGFaXOhdEKa/SUhofEZFWUWPjgpeS6Tx2oSyXlQ1mJ5iAEPAMKODo64sGDB6zXa5arFVrrSb+QaL85ig4pI0MpxfHJibBACXQR4+SbsVhCjJRFiVjBhxdB9ueoZaYn/2SH1XmYpiiKEWz0fU+MkfV6TVmWY6bKdrPhf/zq/8jXv/ENvvnNb/KNb3wDpRgZppzm6p2IkOVllutbFCVFElnmEM3t23c4Pb3F0dERb375y9R1xXK1oqpKlsslp6enLBcL+h/6IU5OTrh79y4nJ6cAeD9IJdqcfRHi6Dib8mIAJP03zrQEzNihGZMhYGbyZtHZ63oECxMzI34JMos2melIM1BiJOCJxBnrEfFMDJ04hBpJ7U7gXEJR9djZzY9Vfk+eMCENkiaZ8jnn6NL1zqLfzXbL5eUF/dBzcXlB3/c8evyIZ8+fs91uefToMV3X8eTJYzabDcPg2G43YxbQkDxT2qZBRTC5EFwSmRZlSb1cUBQFpycn1IsFD+4/4Mtf/jJ1XXPnzh2qquLk5Jij47UAmFRb6Pj0lMVyQV1WrBcLGYhLGYgnMJcG1Bjph17COt7TJpuAId33/WbH5vxyytIJAQZPTKyKTs9Fv90ytK1k9mTflF2DHwZ83+O7DjcMNFspiBmcPMe9F7FsCIGY9Cuu7+nbDhWhYKYTySUUmLx7vPcC2lI9nkVVS+hGS3mK0hScrNcUthAxbQJ5y5TZVBUFhTIUKKocPlJT5g+ZYSGD5DgOpDnc6NJzLok00hcvynIESzANsmo2cKgUppgYRQ5/53/3gwCR6z4btxtRbhgB3nyfB23OUGYAEmfL5+/rlYnfVaARUUQXRzHudWnS8oEmx1BiysQcjz9NcubX4LpthBR1CKWWtOmP2b5vEBJC4D/+j/9j/uSf/JP85E/+JAAffPABZVlyenp6sO6DBw/44IMPrt3Or/3ar/Grv/qr39cxTN1+btNorrUm6CTuDKLpyGwJSqNSum6eIcYgdPTlZouJ0LfSASiVaOdRiZ3TN9OYHqWqq/IRgkMFMEVBVVYslwuOT08SzbrB9XuJuxuZMceQBKbpZmtI+fOTac6kDsrLsn25IQSFkkmQGDUNPUOq1wGkASQkoaQIVJ2Xz6214+w5eD+KTU0SSGZg6AdZf9807Pd7qQD7OQ3H5DY//xyCyX/nwe2qh0ZmTXa7Hc+ePeO9997ne997l+9973s0TcNyuZSZmTbj77IsJRV1qOU+pUFFG4tJMXNhRwQQbjabEfgVVvxcrBXzqtVqRV3XPD874/j4mLfeeouvfOUr1HXF6a0TClsQUy5jQNJfQVgPjZ5mVDDd1zhlDIV4aL4kQtoUSddiCy5gYpp5SShyBpDT7D1dzHFfIB2THE+avY1CN9AxyGujUlaZUlK7SOU6NLKl8b6pVMMjigfP/L5moTgIM5M1PhG512VZ4pzUVDo9vUXTNNy9e4++lwrFTdsw9ANdqrmz2+2EZUzGbjGHS7wXVmIYxms33k+j6YaB52dnGGu52GwkZXhRU9cVRhvKskAbw2q9pqylLs9qscAay1EtVY4LY7HWpPVFd5Hj81Exum+OHleFZXFyPPYVCoXyUzVflTJ3ht1eDNqcw7VSX6fft0lM2+P6Du8G2t0W77I4NgGRRio85wKDrh9wbSfbD7MwVH6Wcqh3GFDeyzmkLMTeGLyGgUgfPIZIv99iEjuSBchlThvXBqsVhdbURkSzZRKfVsZSmSJpU4SFyZ5LjM/sxBjEFEMRICzM89zZQs0w97hAM6bYjmGY2UulIlCYFP688tmV/kdZCdFPTb34zwQ8ZBhJR581IRGkXAMp1Ji3FQ8AyPx8otFM2peXNXmbYwSCIuYCiLOJRR6Pssj2uk1EBdHq16NNPqR93yDkF37hF/id3/kd/uk//acf6wB+5Vd+hV/+5V8e/768vOStt9567e9fBSIRCWloq8EaXIy0ztGHIBkySqESC+LQdM4J5WwkQPnee+/zTtdRFcVolCRCQi1pit4TVURbASLBO4bOobywFwZFWR1xfLTm+OSUN956kxgD7f6MZnuJMZairLFWiny5QdL2dEwmZmnG6FIZ95iLNiEPavBe0jfrGu8cXSNiuazZsEUxAooQg/idWElJ9FEK2A3OYaylDPJ5nxgWbWRA7Puey8vLRAWL0+bzZ894/uwZR+u1UO8vaZ/AM/l9t6vhGJhqvMxTXr334yw6Z6LkcMrZ2Rn/4l/8C9555x2++s+/yje+8Q1u3b7N/fv30uxbQNlcA5HjsDlTJYY4aomyF0jT7Lm83ADw7W9/W0IZ3hHi5NxaFAX37t1jtVrxUz/1U/yRP/IzPHjwgJ/7uT/K4tZCgLXx9P1AmwYGYyxaT2Aqd8SBJLYL0oH5GGZOtiS6XFgdl6q6hiCVlWOM4hQcYypPL0UKTJyq6eYMGmYDZZz9RpH8eNJRJfAcctHDlFkjHiNhpNRjAnOk4x8S2Mpslhi7OUClsJqmqiuO8+CcBhEXvPz4FNYI4iQr997RZZ1FynryzuEGR9e2nD99xtD1bDcbmqZhs9nw+Mljuq7n+bNnNE3Dbt/w7OyMwTm2m62wFUkTMqZVa4WyFmXkWi8WYlJ2OxUMXC4WLBdL6rrm7t27VGVFvawpq5KyrlmfHEvhwOWSoixYr9bcenAvhYzEZbZIoY4YArEXdsR3PXGQon6+T5WJGwElPotn3UDX7AR4dK0Arr6n3e1H0zc3OMIwyPZ8YOiGZJcvfipS70eYE5uyfEJI1zJE+uSpImGggTgE/OZMJlJhygZR2TwtiIFapTVLK74qixTSWVa1MEjGpDo+mrqqU/hLj8ytLeyoA9KJZe5VxKggIe8Yk2A5sYB5wM0SQWYDO2osjJfX02U5imxHwWoOPaawJuQQ56xzGtfh4L2Z4iDTezKBAUm5HYZBKkZPXP8kms1bTex5LgPysn44pokFafJNMraLGTBl0W/MJRZm303HnvALcWEk8+ljtu8LhPziL/4i//Af/kN+67d+izfffHNcni2/z8/PD9iQR48e8fDhw2u3VVXVKOB7vXaVA5tKKcfx6qc0SK1BJaOb3LkpPf5IXRnZUogRAmJL3XVJ01GMsU+vPb0bIDEJY+2BzK+kVF3NlN457g/IOPwgLZhZeqWSmGVGpPKcqvH31ccqzh5IEIaj7TqWw3DAnoxOoTBbzgEVmAfBuq45Pj4efSCyuC6mQOHVLIuXaUMU1y8fj/eaj1/2jWmbH77OwXbS7T44VnXlenCYjgskYeRzzs7O2O/3dF2XfD6Si6pLZlfqUNQ63UdkRhU4uLfyzodJhR9jMvOS7WV2yhhD0zQ8efKYR48eYa1NRetcYmByBkvWr80YhPHUp6uVY77TIzE7Jqbvj4TEuFoWYE/PnnTSeVo+bSt3TLmfzXuPs+c5Xrn30vHFa39GlmX8G6HYZ8zJ+HqlZ1ybnEYqQ4RNjIIPgWpRJ1ZFUjwHJ0BOaikJyPbJvbhrOxZFRd/1bNcb2mbPar1GaU3bSr+w3+/ZN3u2u91kYd8PdGmGmQelGGUyEYfkIRKCCJMDlLagaaVSclXVBJAqxouasqqoFjXN0GNtwXLdUpYFw+BQSiePE8awRmlEq4PLWQ9CX0WjidaggsJUJdpadLCYUBK8x9bFWIPHDT2uHygXyySCnYGQVgzdhraXLKm2o+86vA8HYMQnwO/6qehgcF5+huQsi4DODDxIWUZEUEk8GmIEFzBK6n1Z7fGAi6I5ab2TAonRU/qkxzJi7GeDRacJgk2/XRSdmx77VUbjuLGicgr9kJaNYD19IftEi2G0OgAm8gxy+AIdQIE4vRjTi3TYUnc+phoTk1h5JqiduPxDRie9UNl2/uVMSHp3RtA3JSCErBPRfgQh1xWwi8Tp1H4QTEiMkV/6pV/i7//9v88/+Sf/hB/6oR86+PxnfuZnKIqC3/zN3+TP/tk/C8DXv/51vvvd7/LH//gf//hHmzrTwHSjSP/PMemoFLYw1OslrFbgAt3Q42NAlyWmKMHY5IKqCUoToxIjERVQ2lLWC45OTvjyW29TlSVD2+Gd4/n5GfsP3pM6IMmIstAavaiwaBZYTHqEt7s9Q1AM6n1ijFzsevpocU7jukBdgLZLyvqIqqqpKkMYAm3TEr2nqkrqWsSxRqsRuYOkAo4eCwh1/fzsnO9897uEEPiRH/1RSTmsSrKAMYdXihSLVUDXNIQQWdYLjNL8Wz/901RVxfnZmdh3ty2PHz1mv9tx7949jo+PWa6WY6cjmUBpEGAGnMYX8sNhw+sAC+DgHX7VtmKC60rUwUL9FshsKYVIjDaYmGBcAmFKG1wIfO/99/mn/5/f5tnTp8QYuXP7jmQNtJIuOWR6PpmV5bosMc2wQI0pocKuiP6kqmQmLDoUqcVRlsUYUsjC2WEY2Gw2fO1rX+f58+d85Stf4eHDh7z55pvcv3eXW7duYYzF2kKyIVApbDh1U0pLVzW6/MYMfhmBdQD2TStgKIizqTJ68pGpJE05pMHTKKHJFZLmFxKDZHLI089YJSPajd1eisopm7xwMkBRUVLflToEGvm9nj3rVpvxUQpO7OyzHsE7h8dPDBSR6OegLAHPlAZZJEF6qSMLU0m/scgsTEzsVODB3QdjDR7vPIMbJAzpA23XJtF4S9PsE5sig27bNpLxk9JrvXecXVzQtI2wV+m7++0O1w8MQ89mu+PiYsP33v1e0lxJWrPSUt1ba02ZavGsFksROtuC9Woldu/LpQhjjaFKZnxHyxV1VaXsOwG2y0pYmCrV9imqkuO7t7CFHQfTmFmpmI3GhPXo2yalukr6sRi1DSPTF0OQ8x4G3DDQJyv8brcXn6H0E73HJSfZzKgNw0Cz24qZmfMSUup7aDoBKP2A84FzN/Cs3432+CRAkqs058mEtmbM3DJaNCxV8kUptKZIgtiyLOWZNharJCV5vVgmgazolsRu36IVY6aP1QprmAEGJnCTgUN6Rg/JjilQlEOVmYKZ+s0EdvLkM4EOvagoZ+GY/NUM91UC9HNr/ikVeTZZzXOCscOc+sCYO8/kgK0SWzVfz0efMt0gEuCoQC7Gx2sfCYT8wi/8An/7b/9t/sE/+AccHR2NOo+TkxMWiwUnJyf8+T//5/nlX/5lbt++zfHxMb/0S7/EH//jf/wTy4zJg+oEQARlCgBJN0hriqqEqgTf4YMjEAUhW6HrYvaByOZliQ5TSqOLgrJecHp6yqKqZVbQDzRpII9huptaq1F8tTAVBk3fOvp+wNMynIvQtu09PmpCUAQnxkLaFFgrPgTWaJxDyqp7z6KuRF2elON55oeSlMrBCeMRopTR2zcNZ2dn3Lp1S5B+UrB7a3HOMQwDc4+KkPLnlRILb6M1b375TSLw9MmTUR8RnOfCWtbrtczSilI661QKfWJrMsBPD24CIq8CDi9MHD6sfcg60idkyjN7XMw6qJmzqfxW02+lCCFycXHJt771bS4uLogRVqsVSiuZ0cZJSyLGVlI0bt82B6xQUdgUKrAsl3rUEmThaz7z1WpFVVUjmHHOcXZ2Rtd1PH78mLOz53jv+eADcbE9OTpKKY86pVJPIDyDqXwjkofUjOFIszxt0MbKDHjoCTG5hsYgz2EhA19hZUDzWo5NYvdilOd8CvNpjTWSBq+chG9McjbNNyR4n0ocTFkURPBMWo9rbyQzJgnGNPPMBkHSUwEEARpZAzS/FznMRrpuWmlSzihjSGn+iF3DOl6X9t23LW3ynQnp2NpWiuZl/U/f93zw+BGXl5Kpc35xTtd1PHrv/VGL0nU9Xdvy7Okz+r4fa/uEGHBpsLZJSF3XNavlSrxolqIrOT4+FlF1kYBJUXDn9h2O1mvKopSCgUXBrZNTschnhaqkwGV1ckxd1zIQZ1+YbAGQ6uEMfUe7lwlPfvYzqJizen0nxQGHrqfbi//LfrOV9OLB4XoBH74fxOlXycSq61o2F+dirT848AG3b+gvNsJM7fb4fqDdD+ycZPuNNgF5xj5j96RCsehJTBK3loiYtTRWdCe5uKI21MltdrlYMGiVMnmEbaxsQaVSH69FVF2oiB/zegWI6KSVyVBfE+V5F4piYgHJ49WU64LKTLQaGRqdqy2nJ3Hk0l8aY2FKXR6FpnmiPtcVzp7ssROcrTKCENH/HIaGIsRUODKmNN/KoMzHp0I+Egj563/9rwPwp/7UnzpY/rf+1t/iP/qP/iMA/spf+Storfmzf/bPHpiVfRoto8kMSQSICBiJSWgUVMQTJIaVvUMSEpXrHKfHRE0xwN4NnF1csCv2NNsdfdvRdi23Tk+JRHStUVYlPUVPVVbcuXWP0hScPbtkc7kVPcq+YYRKtkAZC8ok4zOb6pkYZiyqPHhjiETMk7q2pVpUmMJgChE+Ru8Zgvw8fvyYb37zm1hrOT8/H6nyRV2zbxpc0yCnOFO2z7QQxhru3b+PLQvu3rnD6a1bdG3Lj/zwD7Pf7Tk9PeXO3TvcOj1NrqlTzRWVmBqV78U8LvnSN+eTbzlUkV81eX+mWjDDIA6XWSx6+N0cNgnjdcmgwyhzsA+lFGZhEn2puKNzOrCZDVgyu8gMR993YzpwdmYFEQBPIZsog0JR0Pcd+/2e8/Nz3nnnHZRS3Ll9iy996Y3pOY8jMzwC1Dj+kUOMKSuGJHYkZ8Ykt1gQQzOS6VchXUKbwlDPn59xkUzEdttNqkUj126xWHC0Xokp28mJGL3V4rch7E9NUfiDKOBBi7wAAuafReLoaIo9TAUlHXe60iO4UVc3GBnDid55ggpTx4Fcq4NvpNnp1XZdinu+bxl0aa2oKgGai+UC7zyr9YqmkYKY+xTmvDwXMJIN8vq+5/zsHDcI4yKGbn4EI3NHXzfM9FgJeIYQaFOWoVKKs7NzmbzMPFJWycNmuViwXC5TAsHJuKwuK2xhqRdL6RPyzN+a0Zgsz+5zaq1WCmMlXF0WlorEEDrRgmQGWaoWD0Q/2bZ7L75Kfd+xuDwmeI/yHhUisevxuyaJhNukUWlo2waX/FJyXaSx4m0Cgj754KicOeNFaBy9x0dFHyUduQsDKjjM0KOBot3zaLsRgazRKXXYUKW+Ivs55YyeLIpVIF4yiA+KSSHBsizGjJwMpHXSSM0nCzk0Y1PfkZMgJLQ4PZ8qM7bpMRx1WUxhE2MlEDmBhlm2TXpexuddTRmT6gDqMIUWRhCSCiNGqXKcp+7FkWiePm77yOGYD2t1XfPrv/7r/Pqv//r3fVCvdSyzH8jgA4IKBBWJCUZ6Ik7IIzBGXFK1sB/ynMq6MT0QMQp6brqeR0+fYJRmc3ZOs9tzcnLMg/v3saXFrgq01Tx79oynT5+yqJd8+ctvsqyWhPBddk1PN3jONhtihHVlKcsKhgKMFU+SoqQsKrQyks0V5MHSic6z2rBeLnlw/x4heJarJaYqKKqCoizwAzjv8cPAd7/7HS4vzkHBoyf/O9Ca27dOWS2XDMMg4ZPcaaXiaEXSIJRVhdaat99+mzffehPnklHSGBse0jYGyeooCxGyJgAjs1O5Dz45Beb0zM+yaa0wppgdx1SkLsapmFxd12PxtqzJyDNg78PokZJnf1prMIw6EKXE1K4sS+rFgpPTE4yxo/+IDDANXdfx9OlT2rZlt5PsouxbAtA0e2KM4klT1VhrWC6XWGt48uQJl5eXPHnyhK997WtcXl7ylX/tbTnRDPZmk5nxzVSMWRUijpVzz2RuIGXAaEVhynThZH1jDNoYnHOcX17Qti3f+F+/ybe+9S3Oz8741r/83+i6Ts7TWm7duiXVcI+P+PEf/wlu377NrZOTZGOvWK2WiSHoGIZ+OkCYtB05dDZrI+uBGp+jfE+c8/RDPy7LQuNM0WsOFUkKlXwXsgU80/55EVyg1Hj9pkUvQJvEqk8gXoDrYgQkcw1MTonOoafMHuTnc8isQWIssydQZksyUHn27BkffPDBKBzv+56zs7NUj6fn8uIiCWV3tE2LS2xXhAQgVHrW5H23iQE9PTnhaLVmsVxyO3nYLBcLirLg1q1bPHhwf1xmrWW1XrNaraTqby1px6tFPQpGbXJRVWky4t2QwIeAkOzP0/UdQ9+zT/WvLGlwdR7VyYAXeyk+ODiZ7IUQxB8mhtFTxTkBbN579nsp0On7Qer+9D3nT5/Rtx2uH+gGYWb6pkn2+oOAJif9qIri3yShGjMCkiKliJe2GDOaCit+KMuipLSS7VPm8FddjX4pOWxUJN2K0VocmcnjDgJyUnioiOI1k+sm5fDKwfuQXluBDymNOd3Pub4qi1DHasCJgSIDSK2TE7OwhWgjv5MXp+gfhL01MWLGhz9Q3wJTfDgm+LD2hawd88JkZ6S95KaOgCJ11iF3wnk5k4ZE/p46riQPJYRI1/cYhO1wXuzPBVHC6OqXOjnvA8Pg6Y3YU+f9jnR46rCyIFZSdc2o6h7jcukwE8eO1uI1UVc1trAH64OYZamkJdhut1xcXPD0iViv51lP7rBHyn5+7WJM2hI5sXmmhklGar4sGYaB3vZXskImoiPmC8OE1j/7pma/MwhS6T5FtI7EqA6unx5fWmFN8oAmFs5TaGme2quUYrFYcHx8zPHxMQ/eeEhRFKNZWdfJDLfrepbLZQIhe/b7/XikMUb2e6lGK+BnEqiCmsIIINkYu93I5Lz0tF9YrqZOLE5mTj54ef5SKmyeKfXDQEhiyXe+9y7b7Zbvfve7fO/dd7m4uODJkycMw0BRigfGMEjHv16vWSyWUh/m/n1iDBSFhAwOMohmwHQKr7wIVseQq5rAwiSKDuPpjstmqdZy2lcvSJz9/8Mu2jVt/qBfub7jEc+Oc5ztXjmW/DzZxDzFBFBK7+U9c36qODwM1HU9lhsYhmGsAt33Pev1mr6X5+vo6EhAyMkJbnBcXm5omjaFC/vxuc1ZXRkEj5OSFJLTXcdmu8VaS9O2WGPoevEtsdaO2T3L5ZLlaiXgo5pASFWWWCO6E6M0ZWElbEg8rG6bJoZRK1RhKRY1MUQBIQq0D+g6zcKdlLMovLyTIUoR0RBD8urphSnpenzwmH0tQK4fGPoO1/dEoxm6TlKRUxZPu28k9bUbElPjxlRkSedVM/+mSV81KI1XoFXARY+OkRAGrPNYpbHeYbSmx6dUZJ1CLGoMrWemFeSEFYrCSi0may2llWzMMUTGBEJGbYrKKcqgEQY4aI3Jz2K6ziEzIpmNT9tRaWKukIwknQNESdOStyksy5QGPU79lUJpASNX36yP2r5wIGRKBZzP/6ZckYhUyfVGg9EMCvoQcaRwjEn+ICBxu2RTHmLOshEuoneOs/MLsbdNKamDc+z2e4rCsig0Nlr6ztF2Ayru+d77H1AWBc8vNrSDx0UkVRiVzM8M0VpCcg+sqoq6rtHa4JyAAWGCJSzgnaMsLHfu3GEYBo6O1iyWFcZonBvQwNHxGmJku9lw9vwZVVXx//qv/isePnzIz//8/5HVeoUymuPjoykdMnUIPongQhfS32GWjy7NGEthCxb1AnWs0swujA+kDMpTfzzO9MeY5GfXrqboikX0NJhPz4saj1U+iyMN3jR7Li7O2Ww2Y1ZMLpTVO4n1a6356Z/6af7gH/yDvPnWW/zhn/nDVHU90ubibNvinGe/n2azTdOOYLFtW37v936P733vezx//px3330XYDyeoii5dUvcU58/f06Mkd1u91rXIF2A0dkyJJCaU2/7YcAYM1YGzsf9/PlzHj9+zPvvv89v/Jf/mA/e/4Bnz59xfn7OWEEaKFM9lTxjL8uC+/fFKO/f/EM/yb/10z/F3bt3+al/899kvV6P1z1rYwB6L4PGWIBvdg4eAReKqeJ19r/RSo1hmHxO89uas3VevDAzGvxKmy+as6uv02IMDEM42I4wg3pccBUUKTWJmIWCVywXS+DFmkfzjLRhGMZsreyiOprmzdLON5udMJmJNXLOcXl5SddJiG+33Y1ZjPm7Pogx4mazwXnPPrnN+uBxrgcl2rf8zhSpim9hMkMguri6qkWPUpU8uHef1WrF0fERt1Lo5+j4mKIsUq0eAe71rZPklCqDqsmsAUzW9gdXUMKLbdsmBkQ0WpLtJLqRkMwdxdhNBLUha1l8cpwNQVKYk0lbt92lrJ5uzBrqu5bgJO05JLFt37QS5s0uzK4l9mFMR1bEkdURm3x5vg1JeBrl98iiKUVZlMmwraRK5m1FIdfYqATOdHaXFYAnjIxO90LJ94w5ELeOUefxHRPfFFAoP0gRPuUhDMkqRZj4pS1ZFilrNW9k3p/nHF41fMQ35sX2hQMhMNHQ0uvMQjNqxm4oRdSS4iWJYVMM7pAJ0VMMOM6ATAh0bhB3U6TGQn75UVA4jzJaSrona+Xtbk9hLW3f42I2OJpXZJWOSad4nNEzJiQcMiG588kVbxcLsfUuikI651QXoywl0+Xy3CcNgWS2DMPA5WbDkABUkYy1hjhI5z+er4j5AFyY9BOZtlPWjC+LtVaU8P2QXkDZSMYbSsHBbPczBiGyz3RiqeUZxzyemp1flWKiz1NoJg+swzBI5o/OMVNZxw0ObTTr9Zo33niDt99+mx/78R9nsVgcDAZ5sMi1TJqmTTWAOs7Pz0WomOqjiBX8ZCsfQhx9TYwxo2Axe5S87J2/er2VFraN9ByFFC93XqzWbZTXP4euttstT5484b333uNrv/t7vPOusCH7/f+fvD8Lsi250nLRz322q4kV/Y7dZ6NMZaO2SlJ1FIdqdE6dgnNfqEeeMB4BK6N4wOoRM8zgDR4ozDAM4w0rA7v3YPdQRkG1UKikkpRSqkkp+5252+ib1c/O/T4Md59zxd6SUg3nWF5mWmTsWLFirtn4dB/jH//4/5lkuA7G90HIbDbj4uKCKIo4PT1zxMkeuzvbAXIX6fl2YLddPG3d2tfNu+fg23t9Ldsf40om78ZrQLxQ0h7dRR8uX5MfANN1sI3v/z6XA3kErUVDrFz3J6CO/vN9fOLdYxUtt8IfcxcJe9L5dMdLC73L9ZjN5iyXxUqQcnp6ymKx4OL8grPzM5aLJXmeUxSFoHaOg+RLQDM3LufzGZPpOByTnxfarjj5nriMv5f3WB8J4fXi5pjRaMTW1ibLYkmWZ1TWkGYpg0GfHjmpgizSEMWhpE4co5JUFm6lAgIQac+pkDuklwVxWQb15xCcGYNpxNE4jC8rwoumFi5J6cwBTSVS/tWyYDl1uilLUZddLBYspjMJ5mZCtq0jBcpiTROCnMLUsg7YhqapwBq0I3hq49Zqa4ksofVVWcTV2DUKSBASkSUpeVYG2Xvh9RAI6Vks/j1Zkwp64hRqtdZUENBrT26NnDWDCt06ygmyuefFKkEz3KIaGzm2VEcBK1lFmOXa+3X0J7F9KIOQ77VZnJOuwpnraOkvB2qF1LscUx9ENVVpsXgyVgsPx2czDhL39RSBqxvGkxk6UpzPZ6FrIo5SLJqL8RSUuPY2FlCaOJEJsyxL6mJJUhYkSkiMcRK7bNTB8cbfdKjrCoUlSWL29q6gtOLa9eucnAlR8Oz0lCSK6edZUGscDIZUVc2bb77J0dERzz//PJGO2N7Z4ebNG7LfqvZVk9BRECzjVUta9ddAiJ2EWjXWBnW/bsARyjIuiw3Z7/+om/2E7TLpU45LhQDEH6sPQsTuRESAqqoK2hF+oQtQrEN8sBC7zpe9vT2effZZruztCbxubfD4CeqzUcRgMEQpb2KXYYxle3uLxWLBwcF+CEKSJMH72mRZRlEUTKdTANI0o98fAIrFshD13w8Q4HlOi+gAmKCX4+91nAiacXB4yGQ85hvf/CZ/8aUvcX5+ztn5OWDp9/vO9l6CZmjJyMPh0PE+/PU3vPP224wvzrl18yZxFLG3t8etmzfZ3b3ixpx+THFXhU4CoLMQt51XQgi0Dkr2Zy56EJEboz4VeXzE2RBY/+B2QtnL49fWB0NuR4G8KQhFHQIRY53t/PcIdlq0znaCDkLHndeK6SJ6/h4+KcC/3AmklBYTvjR3HkIiWDcarTl5+iXz+ULa/Odz4ZQ1bQloPl8Ighd8dyacnZ+GgMYYIYaWDi0ovYZIIeqyWmnHZdBM5zMWxZLjs1Pevfs+URzR6/ck4JIbK0iIG1/WCeV5jY8oihgN10jTlPXRiPX1ddI0YTgcuqSoTeI8zyKJY+k61DmZT0D8+Gxc6c6JPmKt+OsYZ4DoZAfqosQ0NWVRUiyWASmxdUM5n4skfuNalkN7sgQ9TSmtyJX7O1vV4Ii6ZlmGwMfWTbimUi5R1EjSXNgajEIXlRu/TtDSoUSeL6JdQ0DkxoW/7sEYNXLKvZ3rGbnXfBIsGjuSrEgnkbQ1L4uSqZ6jLcRWyjIxLZoTKShRmFJe/XG2/78KQoAOQVWQkFqJbHCjpBQjxJsIi/Mi0DHWSntmY9uFU6EFhfJpvpG6aenaGotatEcGgwFrwzXquuF8PMcYQ5JmJHECkRaTPGsplnNMuaRvSrHVjpwYWiKKf01jUGFyVsJJMA1xHHPlyhWiOObatWucnJ5SliUPFguyJEGpdaI4Jst7DAZCbHvrrbfo9/s899xzRFHEiy+9xNNPP43Wmrmat3wIpaXG6ia50DViVyc5g8HULuvEERiVbyvzrq/gs0HRLvHLwf99YUiblbabzzh9FgCsZI+e61GWzpfHdOrmlrDw+L8R47k8BCGD4ZDICQc0Tb3C25AgRIzPfGCRJFJTL8uS99+/y3g84ezsTBRtmyYEIQKrT8RGPssY9PtYYLEs2izkB1xaYy3KZcfhnN1i50sjdV1zeHjI/qNHfPnLX+b/+3/9X0KC7ospW7/fI8/ylWBVRNYM/X7OYDDAGBNai9959x1effXrPHX7Nuvr69y8eZPhYMhTt58SH5SmDtfcOi5KN9MPwWzn/vjFNfByvJ+MFxJsaiHgsqqn044Lu7LvHzCKnvj3dvWFQAT0po5N03I8DCu9Bu0xWB/gdJATi0NSJTnw7szd4MKXWXxgC6uIY/dn5bJqP+Z1tBq0yLE6BlinhKq1CsdvLQHVG4/POT4WLpAnw16cXzC+uKAsSiYXF/K7iwvhLZUVy7nog5ydnQkfajFnPJ3ItVVyDZbFkmVZgiszWGzgGCl3s9I05dreVQaDATeuX+fmzZv0+wP2ru7Ry3PW10cMhgPnYC2k2VE+Is9SYlfq7vK/ulLn2l0AUVF1JTQl99ZWTdBFqcoqCKpZY7CVeMf4IMSrVfvkw7cvzy7GVIX49DSOj1JMZpi6ploU1IWgm+fn50Gx1xpDUdVUzrencY7Mwm1xZQ8fwIo5Tvta5yuNE5F3cGq7sQs8Uqec3XdcrZXyWpwQaUWuYyKlmdWQNhBbyKwispCjSJCgJ0VRxhGmGvE/XRDSqZYGsk1bjpE2RAOhDbdqGpZlSaVT1zHTnYkc5UddduKV31g300u0SIcA58osrgbUNL5FLMQron1mhfSDn0yVROva+F7wbpZOiEq9OS/YIMaTxAlbm1vs7e1xenoKCIejLMtgyxwnohMZV0JgOz4+5s6dOwwGA55++mkyZ6rmTdjAoQe1h7q1yyxtEGPzxYhwrIRc9Xvemf8h22N19e+VaT7xVYSQ2mbKXXjZb+bSgq3cvTfGu9ISApS2xdfzYvRqydTdV794tItKu1jYjild1+NmZTxoZ8KXJKJHE8cYLI3xHRceNfD7boMuQbLajBo6RFwjNfXJZMq9e/d47733ODk5cdfE6YloLa6zXgHTdxmZjoleWLh8BiuW8HXTcO/ePcqy5PnnnufmjRvESUKWZ6v3z+I6lFRor+7Wyv29AoO1HXGz8Ho78gJofLl88cSxYp84VpRqu3Ua76mk9cpY8YukHyfy3CjRALI6BAvK7SOQA22nDONKrtZYtJa218tj0qN6fkzKfXXEQe3Hul05dlBEGpSygnTSliEtHSTGBzFu7mvCvZSZVWnhImRORbmua5Ikoa4qenmPteGQuqqYbW1SOwG2peukK5eyKHutlJlTlzWmoaxlLE3nM9HXMdZZBcg4q730eyPEziTLUFqzKEpOz8+ZzReUVSWBRz8XUbY4JsvF1HMwHIgLepKQZVl7LxySJ+WNiDwTpdUsScXJXEekSdThoRDK0cq6sqYFnaQoR4ZuXGASVZUEwi5wMHVD2utJQFKWmKLAVDXlbCEOyPMFVVGyXC7JNtdD8OJ1V+pSrkFZCMrUlC0K7b3LrAtQ6qqkWBZ4F2isJXbSD1prTBxTKXG3LpuayFqWzirCz+1RJI7vkYoYxCmJjhiomIGKSQT3kDCjgcZaEqe/VBfxY07BP8r2oQtCoBN0uJ+sq141iINnpMBEChMpZmXB2XTKNO3TDPoYrTFaVE2NUivS7e2+BRYL+vxxTBRpqTFWItkeu4cdq6nKxgUhIlXTGDCNRWOIVO0IQhqVJCS2ITbtIJFJT6MieTgS5Qd54yYoTRRJRPviiy+yvrnBdDrl61//OlVVcXFxIa1kSULe65GkKdqp2H3rW9/i9ddf59GjRyil2N7Z4dOf/jQ7OzsUy2Vow50v5phGOhriXoRpDBjhiQjUp6WzRHmjNN9LI8jIT6rwcnkPP0qLr9YtxL0aGNnwWndh9tmsryeHjKZpiF27WuiK0dKa2+v10JGgSJUTnJJFyKysd9Z67xrTKRM5kp21zu9HOBcLJ3xlrcG3fsrkEJPnOb1ej36/x6DfE+JgUUpZycrY65acEuefYd3kDm6RcyWAKI4pi4KLiwsODw/5wz/4A77+9a9TVhUD303lOjF8WUiEtYoWEekEyLETzUrSlMFwSJ5n1HXNn/7pn7pj75OkKTs7Ozz33Ecc+ucDvIay7JjDuVp4nmWCnHQ8fugunhCCNmutq3k/mYPxeEdYy31q3+cF7TRxJq3Ls+nUoVcJqcsefYukRy+0VmFBs7RGd95ddrFY0IT2ZABFnIjnjajuynMeaTke32XVdXj2SKXweuIWHXLcsKYTvPogThIeh5wo/0vVmlVq316vAnk1PDIK174b0R8MGA4HuAsuSZZvf/fHhnWlDhvGsD9uY1qNnKIsOT07oSiWnI0vGE8mFGXB2Bk7LhZiLrhcLpk5d+PxxQVFUTCZzTg7vxByaFEIkdZZSyjtODVKObE9cW32go0DJ+KWZRlZmtHr99jd2SXLMna2Rdgtz3LWXMdPnktgsz4asbmxIfyMSDpWvEx+COY6CKH1XDOER6gsUnpxaIotpSyzmM0plgVVXbFYLoWLVrnuy0ZQl7qumbnnDhf0gA/8DaWT1R9fXHB0eCD31E13vmVXuoDmNE1NMV9QLkWxt3bBTTFf0lS1BKzKkuiIzXxIFidcHa5zZTgi1zGbcY8ETbKsiKqGno5YixOWvZSmGj32zP2w24cuCLlcs22DkS4iQiCpegi48XVan12Ficnn9Z3sSQmKEfLmzkPs/0Yr7X7vYcx2H6Hl13oTIPdOF322KEibMQfUwWdiXuPa7TPSmrW1NYpK2vOSJJEBVUsN0mt+gBOhMobZbEbTNBweHbF/cIBFuCn+tLvZqLWysPiI7HIppfve1fvROp76zOpJngM/7PaDApDLGf7jfw9P5Ac4JGu1i6blxnSREP97z6mIaOuqAd2wngMjbWyXj8c4d+Z20lo5mHBM3a9ulu4XnCjUdDWN9XwCP0IvXXB/Tp3rJB9EIE02TcN0NuNifMHx8TEHBwfBx8ln/jLpmYDS+HPzhMmVa2Y7SJFWLJdLLi4umE6nHJ8cc3x8HMpMLTLYBhNtq3RbgrGXrlX3XFbRpSegHyuXozvOn4yAdC7R99yXtZbSwebe8E7KduIJY908IR088WOjz3bOW4IeC0qjtA0iiZc/+3K3zJOON/xeJi5ZDJW4Kxtl/EUApZyYl5TpBBFxaGg3oHPX1uIE7GLpuNCqJWn7T/clbL/weUJx9xw82bsoC4ajAcvlkuHFBRcT6dg5uzgXbSLXPbaYz5lOJkF8bTFfsFjMmTcik1+6ZEH0U0TF2ncVBgEuN6/GDh2Rsqa0Eff7faq6Js9zCeiXS3pZznK5JI4jKe0kIuQXpWKglzniqDEWm1y6BwG6dG3HKGeep7BJA0nqlFUFJtdZRlKUNE1NVkky4REg2wg/pa5qkumAuhKiq0e7BYE0lEtRqCVLmDeV47i4A/IWBFVFo0HXNZUR7otV4mfUWEWJpbaNqONaaTHWRpHqmH6U0I9TTJTQMzEGjSkr4qohjgyN1YIEfb+H6QNuH6og5EnBBrQBR/idUhgd0cQRlVZUWGqlQEciS+w1rb3ZHF5Pof0U6a6RRbb2kagjjsqYcxBflBBFCY0yKKOcOqPvpxFBNIX4C3iIv4X02/ZPb5rURlUtFF0Lg5K9q3uMNtZ56aWX+MxnPsPF+Tl333mH+XxOL89DJmmRVty6rrG15e777/Of/tN/4urVqwyHQy4uLtjZ2mJne5ssTVwbntSkF4tFKP/I8qZ+IgPtg2yXYfX/YZ/TKSH4ycpn/IvFIqAhnnXujc6EXCo8CN+5orT+QMfryxkiriUZ5draiN3dK2xt7TMcDkNXzXg8ZrGYB2QmZJbGUDerHUyiutuB2YEqBJouoDFtB1Se5yRZxv379/nin/85+/v7HBweUJRFyMKBYPamtCJJE0ajEbdv3SbPczY3N+n3+5ydnXFwcMBiseDR/iPOz88YDgasDQfBiM9ayzvvvINSik9+8pM8++yzjEajIJbnBbq8aJcPnnDjznNzjGonvMeCK7f9oMDVuExe65Zb0f2ddDgY7FIQlyiOGQwEBaiqivlsxle++lUePXiIKHYahwJJUtDLc3H0HY24des2eZaRpGmQ6/flLAlM7coYTOIkfM5yuQzH5TV7ZJ6QOQNfasMSmSgEiKslXuW6vaQcZLyLsmp1KmInVuXLL15Dxl1+LJaiLFgspQ0/cfoVq2O6wlpIYpF+9/OOP3afVOkkJo0UWzs7NE3N5s42VVVTVSXT+Vw+1817xnMr6prxdEJZVo6fUXacjw3LhQgC1k3FohBUdzabU5UlZSVBT9M0zrOnYbGUNvnpfMH43TuAIs/uhI5DnxR69eSh4/uJc29GHMWMhmsM+95dPcV7+8Tu/OM4IYo0PefwnOqIRMfkacrm+oZYOsQp8aBHHEfkSSJoqytFmlpMA70fj2k8Ki6omffsMbUEHleLkqfms0551LKcz1nM5hLs419bUDoF20CsdV2Ok/EF52cnLGZzDu7c43w6pzq3XMxm9OOUa/kamY7ZsDEDNDZJ6emEus1Zf6ztQxWEwCryAW0A8lggosU2vFHSHWMQyNUqCQ58y+7Kf0pqqWFTxqEpjp1uW7ncEEBEsZBbMfK32oYgRwoyLlf19TztiGCRd0PVLe8COi6K7lwsodtiY2ODdeD27ds899xz7D96xL1333XtoLa1szaxZEJKssvDw0MePHzItWvX+PSnPy3ZQJ7Ru3GdOPaCRLXriy8FfnY27/bHL/n937wF/OoHvEc2v25VVevb4dtB/cQuHRBSh/aBSLswtOja99t8R47nCFgQtdX1dYbDNdeBAlUl5ZuiKEMw1OVANB3UQSZMj8q0KI5f7LRWKE0IokCk1pMkYTqd8t3Xv8v+/j7n55KJGidZD6ygH3Ecs76+zgsvvMD6+jo3btxgc3OTBw8e8MYbYrT3aP8R0+mUfp6TZTkKKV3Vdc2jR4+Yz+esra2xXC7FMyfOiGMxpyu93ocrWfm6vb/+7lFdIRRfuo3hlgdE7kn3wGWSSnU5Pf7+uODOQONq5mmaEqdpUBCeTqd88xvf4LXXXgtdFkmSsLm5QZalzsdlwN7eHv3BgLW1NTY2NshiMcvDLc4twtEeequiu2C5XIYWbV8yFJdYCUTk1DuZsTtn//y3Y1rGkzHSlm1cUBdabZ1hoSVGKS2Bp49BVOvFsywWKKXIMrsSvDVOb8NaS5ZmJL6MVMhYi317f5qQJjFJrEnSBKUIAVPdNCxK2UeaZK7FVBMr4cgsSzEE9O3YPqC21rKYSxCyLArG03FQlZ3P5swXM6bTCctiyeHREYvFguOTYxZLkcs/OTmR4LfpaLC4dnr/zGVpSi/LiaNIvscxWxtbrK+tBzJsFEUMh8NWQTnPhZDez0XYLcvppRnDwZBKK3p5j431hEGeEec5/bWh3Ic0lc7NqsK4MpytfZmncWW02pmOev6HCRwWQEpi1jI+O+fi9EyCoVza6svFksppndRF6cavXM+jwwPu37vL2fEJ9+4/5LwqKMuKCVOGcYbqN/SiBJX2UHFGoiNqK/yQn0R6+qELQvx2ORiBThlGtXwPY8UC2oCo0zmy1irioDt7pVuDkR915PTyfXkFFBqswjRSA22sda2/DgkJ2iOCJ/gMyAchkWr9F7pzpkUGlYfdZBDKoWgbYbViNFrjmWeeJksS3tzaoqnF2rpbszfWuhatNHhRFEXBG2+8wWIxB2sYra0ROf2POI7Biqi3ZEUGZRV+vHttEym9PKEE8H3u0w+7CSD1Af5SPQmlaZs4L4Hy4V+Cirryk6uFiRbH3ImMOWjUfwaEwCFJU9HJSKSzSYSzVsLiy4cTEInw+Q7J2N7edq2RJePxhYOfZdycn59zdnbKxsYGt28/xc7ONv1+v20vbqSGH+O1UFojLGnxdC6/tfBUenkOECzoHz16xN27dzk5OUEpzWg0InULrt+01lzbu8b2zjZXr17l5ZdfZm1tjZ2dHaeS2iPPc46PjzlyKr2RUowvLrBIey9WApqz0zNOjk949OgRdVNzdW+PNB22nA1rQ3C1WppyV7VTqtAOtRSE6LHb+9jmF9RIa6wTCvMdIt0tihwa0IiJkzUWFSvG4zF33rvD8dEx77//Pg8ePAjeIVEUMZmMnaJoTp5nTKdTbt26hbWWtbU1oigSuPzSuXWncF8O0U5EzhPItdd60codmwRsXrwtdhYMfrqytMGasdb5OmlinQAyJ8SRcJ3Ksgqoii9h+LJY7X1ZkPZy/5yYblai5HkA58fk9ht3gmRf7vHjyj+bvuPJWkui5fhjrdFId57nmiiUc1LWGAxW2ZAY6L4SV+BeTpbJ2O3n/SAJv1jMqeuKmzfGlGXFeDJmMpk62fsLase9ME3T4We05UcHuclxW7lOwglpOU3KwnwqyINy5SDvueNbYxMdkfd63Ll7lzRNGfQHZHlGmmUM1gZEcUw+GAgPB4ehK0WihbOTRBGJCxhj1x4vZFrdJs+AimM00BuN0EmKVpAmso96UArvxCWbdV1zcTFmuVig1wZs3b5JtjHiufmci9MzZofHzI5OKVCcNgWZqYitdABaLGtpztxGNPz4WeqHLgh5rBRz6cvrhAgKIgIulVNMJYrEPwblnANdAOLvIopAjZaQA5R1NuYEJAQLphYuiKktjamkLhhHEuR4ATRfX3EtwN7COomkxz2OImcU1WZ2Pvjw5kzGCnscpYjTGBUpru1d4Rd+7md57733ePM730ErRbmUcoJkOMLyTmLpVPBqoNPJhD/+4z+il/cYX4zp9QdsbW7ywvPPCdkyXFOZhMBdIyvXLtaihGpXpTge31yM8uNEyR/ob58EyYf/dffVqbMjE2mojWsFDczmM87OTplMJ5RlIWqcWIiU60aRlqVev8dgOKDX75FmWUfzwNKRwOscjIsgO5l60wji8PTTT3P79m0+8pFn+fjHPx6g+KqqOT8/5/T0lDRN2d3dpdfrsbm5FSbJsirk9FNLjPOAiDTYFhnx4mhZmjLaGKKAd997j/3DQ77zne/wyitfYzabceXKFa5du8ZivgjS8n4R/MQnPsHP/tzPcuXKFT72sY8F87MoiiR7XBbs7+8zmUwYjUa8//57vH/nXXr9Prdu3SJJEh7cf8DR0RF7e3t857vf4dr5NYaDIaPRejABswJ1yDNlTFsWcJvnj/jFCyzGtN0y5gljYWVcuMxfKbVSGvFbHMckSasCa5DsHuDR/iP+5E/+hIODA77yla/w/vvvS/eF+33L25D7/7GPfYynn36asizZ2dkJRFP/aWL/0OqgyKIvQWUUR0RxjziKybMMlAq+H7W73rWTcm8aSSSGqUD6/gGuSllsUAoVRcSKgJJ4jZe6rplMZ9RNQ8+1BXs0xRgT1EizPKM/GAgfxgmBhXuidRCwU/4aG4uOY1cSFtSvsZa6KFz2TnivVzPu9/LAscMFQGXpBPWiGB3FWL0alALoYctDaVz3mpTU3Bxqu1YIDu1qTFCHNcZQOIXVsipZLJaOcyJo6Hgy5uL8QpRkLyZClD27YDqeiOfNRF67ODtlPl9QLJfM5lNBMqtSyqeOt6ejiKSXuVKYrBNpltIf9knShJ2dXafJ02PY75PEiSjPxgkboxGj4ZCB8xFL05S1wZA8y9wqpQKhO9KajdGGBI6Aso0L8N1a4rg3y2LJ0VtvcjIfM9rd5OkXn6Wuaq589CMsZzNe/cIX+dZffIXJomRyPiGuDct4waZOWZqafp5z0SiqnwBU/qELQlBtAPKk36384DMD62LqoI7adsS0jUr+z7yCY4uFqM6Kqtx+hYckC5T1FQAXHQfvGqSThsukTx9F47O7J+E6q3V+rA3weJIkjNZGbKyvs729xXw64/TkhOViETJ3pVTwHuiaps3nc8qi5OT0hIODA7CWoijDoNWRXoWL7ROIfB8ECPkRiR0/Dv/EX8vuLlpfoNX9Xv6cxnETvD9FQEou7d/X07VTu9UhgP3gm2TwbTfIcLjG7u5uCELqug7quEmSsO4carv6EcoHzLQs/ZZM696hVr+w4ldzdnbGZDwOCw3guAayQEdRFDpyNjc3uXLlCtvb2wyHwwA3+/GVJSnLxYKdnR1OT08DU99LWlvHM/C1+Yvzc/q9fuj88NdVCdQRLuXl++PH9BM3pX7U4fbkfWmNMm1r8mQ84ejoiOPj48AZ8i211trwPuXa6aQTqoPwPIFcKvwwQikvADrKaXYg3VPGSodNVVcsFqJqKn4yy0A+X5sNgwy/D7Ksm5T8mE0S56rrRL7qpnG8n9bczMfKfrwEToc/Tvt4INA9fuvRAz8/dIKszonTjmAbAhM/jq2VTptAhPbVH7u6Hz9vSzmpBZ49MGk7c6pqs6vwGa3CaikGeLU8e8YY0YJqDL1ejyzNqMqKXt6nKiuyOCXPMqqiZJ5mVFVFpDR5Nme5XJAkEnAuisJZJJQUVSXXMXbPmD/HqsQuIK4S0mxC6TrtyrIkjmKWyyVJHIsX1XxOf9DHImWiWX9G7pAyQdVbAzshmOdujRLkL4pFvMxai9EKG0fEvR75cIDOMxqtsZEm7uUkWLLRGvnGiDqes5yK/tXSGhamZt5UzKuCRR0/ZvPxo2wfviDkCZvXBDEI+qGVxihRRpXWXZdpqVi+rA5fChW0/C0Wbb07oQCAyooTaW2M2C1H4kcSaQ3aMdw1gn7oSPxoVDupGJwYjjUIhCCtl1GkQs3ef14wegoPC04UTDILcYc09Hs9dja36WU5n//Vz3N4cMCf/bc/45WvftVlkfIA9139P01TUmcxPplMWSyXfOtb32Y2nfHss8/S7/ddHbtPnvdCNtidoEx3AvqeUeD/s5t1C9kHeZ9fuAWssqHmPw+E0EZKbcaTif19i8VPx7X8+QDSZ7bfK4iSdlbhI1VVjVJNCGiyLOP69WsBJRGZ9wWz2TwEBFEkrH2QgCHLsxYFcKTpBlYWj8SViyKtKStpsX39zTf5+tdf5a233wYrAnWmaajK0hH6Kka9Hi+++CI7Ozt85qd/is98+tOi8ZHlgAqt3VmS0M9ztrc2+Uu/8As8//zzWNPw1ptvYK140XjZ+TiJGY/HvPrqq+wfHPDCCx/l2rVrGNO47FyjnfZJl68RslhoA5Ufof3KuvKNT0AuE1NBFialFP1+n6ZpuH//PkfHx3zta1/jy1/+MhcXY8qqYn1jg0FPtDKqqubiQjxY1kZrDAaCAN24ccMpHWum06mUD1yLuzUWqyx4ThGEhT5OYuIo5uzsjLvvv89kMuG177zGwcGhIwIfOv6X3GNfEsvznO3tbdI0ZWtri8FgKPt142FtJMqjw7U1RusjZ0QnpQDrWqGV1mjX6jroOy8ba4IirKCzLqSX6ILKHbfnUWmlQplAa6f9oiJUFMs+qqYtI7l7UCyXWCuJgHElIKxXpZVnpq4qmZP8zYRg6BmeeV9acscUAlpfMnABkHVIiUVa13Uiwl15modrhlLsOr6JGzyApXIkWVM31EsJVhYzmTOqqhQuVyOy93VdMy8KFssltWmYOy+eyWwiJNliyWQyFqK6S/qWVcnsZC5E2vlcSu1K/IXiKKaf564UKEFYmiT0MjnuphLujDQ+xETOlTtNE27cvMnulV3WNze5efsWWZZx8/nneCaNuXvvHm+8+SZNXTn9EcPazWt8avi/cL5/yJtffoViMmU8ryiLJdXCQFkx7q8xK5/+oZ/Fy9uHMgjxzPDuK54L4ks18u/WIdcCrU+M745RtDG19QUYvBm3R0GsMVgHl6pIo6xBKyl5GC0BjHEZlG/9tSv/850xwopXzgugexir+VD3nyrYMxfG0DQ1cRSztrYGwLPPPsv6aMS3vvmtQKqqXOTdOLfTOI5JM+GGTJxl+OHhobCvjeHo+Ji858oLUSzclVBTaZGYy3fhMgRgL73Pzw0/CNyQxXv1/LtZ8g+zdYmJK/t8wn78WQJBB6N2RD7fkWJdJuHh48stsxYJUtuP+R6BiGp9bIxpOsdoSdOEPO+vHHdZloxGZQgmum3E3pHTuoXTy7F3jwFaM0Ff4y+ripPjE+7duxcE77RqdVC6/iy7u7tcu3aNa1evcXVvT1SCqzpAzFVVkbiFpJ/n3Lp1i/WNDXZ3d1cgfZ+ZR1FEUUjpBmA2mweSrnLKWypqW72fhByEUWnbUgb+Hn6fALB7vy+jkWHfLkgJwZvWTKZT9vf3efToIQ8ePGA2m9Pv9wUl6vel1bOqmM0kyOj3+0IeX99gbW1NJPtR4XnUyvfAdRONdrwqCDyTsiw5ODzk9PSUb3/727z//vscHh5x794DwK4ID6ZpymAw4Nq1a/R6PW7cuMnW1lY47yiK2NjalM6mrU0a09DLe2SZBLdBhySKZH7rZNVlJU61ngTbIhlyPX0m7EnUkdaoyGuZdGT+ES6ZdS3DPgAXwS3Hc+kow/r51QcAplNCC4GQBRN7aYDVe+q7HuU4V1tJu/8OxHKlSZy3l3/eTH9A0zTi7ZK24nmAEMtK4xRNy1Diq+uaummYzaaUVcV8uWS2XFLWFRezGWVVcXpxymQ2YTwec3BwQFmWzJ2pYFVVzBeCUJ4cH1MWBU1Vih4KotuEJRjx5VnGoC/lsmIhOiD+OiRJwmh9nSzPeWE85vbsNnvLBaOdbYZxxO7WJusb6zw6OeF0MpZn2q1n2WiNtfV1Ea1b62OqgmJZ0diaqLLkhWG60FRNyyH7UbcPXRDilz5rLQ0SPdYu4DAqgigBHTunXEVjHeneShZLFNP4+qMBagkSdCMTQxxZImWdPr4PXxosNappqE0pmbFOXbtajDNQll5qwU9c0COIeXdqjKOIXp7SyxOyNCJNFMoamqZCGyPGVzgVxktQfxonxE6IbLkUJ8crV64wHAz49E99mrIoOD4+5o033ghM7wC3O6M2Tyi0jeHs9IyHDx7y9a+9yqNH+3zsYx/n6aefltaxvId1CEFVy+JDVTvSVYzWSmB20zhdBB+62TCZqw7ht51s3cTgMpEwQWExTQuhwhPKVpfjCOsLLW2g4YmdrX9N+0fBzE573NkGvsdiuWQym7IsizCh6Ui5jFM+RSmcG7Lj9MSREHhV5Jj7prOI0i48WonYm+4ugIRzlQBIjtVPkHUtbHhpcRSYXhYAX+Iw4VKFDNsFI2UhfJEsy0jzVLQYTk8Zj8c8fPiQB/fvM5lMyLMsBC9SYtD0ez22NjZ5/vnneer2bTY2NyldYFY5lUatpIXbWpgvlhhrGfRFi+HG9es899xzTKdTDg+PKKuSNEkd50g7VdaIs/MzxpOx68RKQjYtXT165d4DAYnzGgy4OeAHRrh+LK2MIX/922BNumNkDPmA9N133+WVV17h/fffD90qvgRXFAVnbsHx3T03b97i5Y+9xDPPPMPulSusr6+HxRbVkZRXbcXCj9A4jrEWDg8PGY/HvP32W/zxH/8xZ2fn3Lt/j4uLC2bTWTuG3b6krNBqcURRzOHBoaBmDhmI4oi10TpZltLr9xkM+mRpxubWFqkztjTWMBwOubK3R6/X4/atW2xubrbXWYmjdluJ7TxbVjxN0LhuJnnOjZFEztCIR5p1TswOFfIEU7+fKE7EVr4T8PuSkUVKCtbS8QLqBpG2M2Y6SWq45Z2yJG0gYh3C4U9HOUSmyx2KIkEirO4o9pp27NkIUJpIx6hYE1mDTiKMaejXNaNKxsmW45rMl1ddV8+S6WQS2o7rWgTqiuWSuqmZzwRNKRZzCu/664IP38nn0+imaZhcSIeQuHgXUobLZMyenJ+zqCruPnzIW+/eYTAc8MlPf5Kr165RVRUvv/Qx5os579+5I+q2WYbKYposJdlYJ7WWalk5CQfLAMNcG5qfACj+4Q1CcHK/KGoVYbTGqhgVZ6BTDJrGKhoDjYEITRwlECVSqkGDkTYogMhIKSZRlkRbNJbEkVQbW9PYCttI371CQZxidQxRio4zrIrkM7FOWbQ1T2ofXEiSiOEgZzDI6GWaLFXo0tA4bwCFcbbNESpSAd1QSMugr2/O5jOiKOLGzRtgRefiys4u3339u06z4Tw8RNDKja+PRmitOTo84vjomKZu+LP//gW2t7dJkozRaIPRaI2NjU2UwvXyVzS1BH1RJKWAOI4xxVJIdtoZQCvf6tiI0ZLzrQiZOq3/h6+Teyl7nE6Dtba1otZtaUHamVfHQnAvxWXHWqFcrf5xRczOvhqxDJcyt6WxhtlizsXFmMVyKRNWKL/4YzYhCEnTJAQixiqaRvZvmo5xn/IlGCfjrS1WX66f+vp0Q1UV7pzaoCoEbqqTLbvPqWvhHbTaMAbjJu2lI9gJeTJlOZ9zeHDA8fEx77/3HnfeeYcoiui78o61lrqspN2wn7K7s8MnP/4JnnvuOQaDAUXRkW1HZKGTJKYxDbO56MoM14as63WefvoZPv7xj/Po0SP29w+Yz+YMdgdsbKw7JOSAsqw4Pj7m/Pxc2hsdHym0yeJ9YTrokYOJiVRQf/WZceAs/ICJo5sd+2vpg9b2jsjCvlgu+e53v8t//a9/SlmWaK3Jc2eVrjTL5ZKFa0+1Vlp1n/nIR/ilX/4Vdnd2uHrtGnmei8ZFp+PIj2UUgTuDEh8pYwz379/n7bff5utf/zr/7t/9O8bjMbnTAFI6Ci3ZPmAVj5fCITIzx8VxLW0uy/dGimKWKVuSpozWRa+ldLoaV69e5eMf/wRbW1v84i/+Ih959lnS1AWQWtprg4idLwU2vsssRker7dG2wSUXBusM43x7qVa65dXIzSGOdOjA8/NE0zTU1vMa4hUEyY9da9tOI9/6u4J2RL481HLjfPAtaJxx/AkZAaY2bnxV1HWFcSVNjxp5f5tQSotkvtBERG6cDbygIS3/sJ2t/LMtSDvWtbu64+mOF2stk/E4KMh69WLvwF0sl8yc2eDxobQiX1xccHZx4RIH8QA6ODlh8v77LBYLzs7O6PVyfuXzv8pzzz/HJz7xCX7xF3+R8/Nz7t29z3g6hygi6uc0eUq2s0WTRJxcjJmeW1CGnjIsI0P9E1Cm/NAFIZ08GYXuqNV1CKH+CwfZWefhAisRsbTqOgEypNasEHEYpZG2KKVAZ2Bip5JYyvPtWCQNBmtqjLIYIqn1RlGwUJcjdUduuwtU+x2c+6ZDdiyWkKyH85bo21pXElIi4uQh0l6vx+bWJru7u1y/fp1e3uP07JT5bB4CGSB0HXguglKa8cUFCsXx8QlHR8cA7F25gnKaAtopBZpOx4J/7O2lSUHOT60sCgFsth4paTkZInPctAuQDRVcQCSiZWLzfijuAoY8Uu6ez/r85yukq8BfwMeWqIDlt5mR14MJ++yerUcd3GSkO2S3J2XjFsdIN613zAcpLck56tVWyLBT64Sn/PG04lPGgFQ1bGizBILiqbdpX87n0jHjuxqUctooJsD6g8GAXq8XTMHCNb20iK9AfG4cJEkS/t5fI3+M1iEulSMBzudzcqfQ6vVxVspw3/N6XYIXOwHa45dsdcbw96J9vf28KIpYFgWn5+JUfX52xnQyCSJfAdlSDrlzpSt/vpubm2xubjIYCh/Dy9s/9pmXs3JsEKY7PT3lwYMHHJ8cOy6G83GJY4cOtCUd6yzZvXS+V6T14lZ+XvT3uXstmka6JHSkqeoqeL3s7++zXCx4/733UMDW1hZXr14N3LJIaxFqs+1z3EUhwhW1XaSqVVOOHLrlgzmr2gBC6UtjrM04L6n4tuWYbhLSHRPhfNUq6uHfF4Io2yENu4/tvtZFTi4TjMN+w2G6v7EugUKzMspUd9pxxFr3gvdK9ciZIHeuC8yVhOq6DqaTUSSS+mVRMFgsqMqSLMsplks2plO2JhMaIyhd0zSiXjybcTEeB32Y8XjM/fv32dvb4+LigsViQd7rMVpfx2A4H49ZLJZEaUra66GTBBNJYl9ZQ2VXr8ePun34ghBjaRor8Jd30dSO3RlFmEhaFY0SrZDGQt2ICFFklTMjStBxSo2irsQTJIkFZbB1iSkWRHnMWtYnTWNGgy3yLKYsCxbzGXXdMJ3OKcuaRS2EqVpFNJHBqJgsTUnyFFPX1EuRSlOOIquUkXKPssQa8Z/B0JiaYKOngM6iJQ+MoawqjGnI8py8L+68s+kMawzro3X6z/dEjTKKOT455k//5E954403pD5fLNFKu3YxTZbnXL95k6qqeO+994h0xMbGJotFwUsvvshTt2/T68UkSQYop+bpbOGNuDhKO7EEeTWiqhjHETqKfUoPFhFYcplfU3mPChm8VV1QWl+Tlz/xnRWRs6T2pZEWEVHOitoFJsFQrsP/8TOYmyEuL0b+u5/nvKeG9YJd7u3eJt5n6GmakGUputMd0Uq9Ozt3I5MbFuqqRaK6E/XlzcPP/n1+sQav0aKpnd6LTKJtB0Nw/aVV/vQCd1VVM53OuHfvPgcH+xwdHTK+OGc0WmdzYxMUTKczimLJ9vYWTz/9NLdu3WJ7e5vRaOSOTYXgBlpjNzkvHcYHQL/f4/r160Fh1pu7SeYu3QjLxYLj42MePnxIEidcv37d3f+FIANxLMRv/8z7Rc6VNYwbKF2E8QdtIYhSGmvb4/fX3avFHh0f82d/9mfs7+/z7W99i4f3H9AfDNjc2pJ5pbMQCQ+kx8c//nF2dnb41Kc+yUc/+lG00pRlRVlW0pXguQ8O5o9juS7WGmwk8tfz6ZTZbMZXvvIV/uAP/4DpZEqSJKytjVgbrZFlGU3tFFBN66njO6iiKOLKlSthoW7jtLYbRFrD5RoYY1gUS0xpgq376ckp+4/2iZOYd95+h53tbT73uc/xa//7r0krcL9PliQsi4amqtxcLGXVJE0CF6h2JRdPtoxcEKWVCs6tXil6JSnp3G+v06GUQkXKlUETh15272xn7jA2iA2GwBcb7rU1YtbpP8N/92Ro/2wGkq1WAT3yY77LswpJk2k7wcRPS6Hr2LUPf7/Eo1Ny9EG3vxZKBSn6fq9HL88DMuQ5XsZKy3HdQZkCeuRK6GVVhlKqJ1t/9atf4fT0jK+/+ipffeVrnJ9fkGc9+v0+12/c5MbNW7zy6tf4+re+RRbH7G6u0xsNOX34CHOSUJY103nBsimo/2ds0V3Nf3WbMV3+cu/zjZYuHncRppLOFqMcdBk5ZEI5a/sabEQSR2RJzLDfYzjIKIqYRFtRtayEKFRTs2wq2bMxoE2Aka1SnYnSH4EnqHYQEf8g+pn18ZMVRMf1uHsI2lobGOWJM/0qy5Jbt27R60lAkiSJO6cGo2TC0VaT5wm9vIc1ojxojOHk+ISD/QOuXb3qCI+tgV5dtwZsK94T/lWPOnQXWmvDcu/Px5o284H2gZetjfy986jCuofZZ3OyqGla5EuWwTbraP/RQSueNBdceq1rc79KfG4nST8JrcDOl7KBVbTHfZRSYfLyP4fD8P9WBHGpFYJdZxytZnyrCID/3rV792WU2WzGZDJluSyE3W9MaG80xte+Y4bDIcPhMLQI+wAroIeXEAQ/kfraehzHgbzZXicfTPsgqWG5WAiMXJUh4/PX8onTtp+s/Y4uX7vvsT0ZHeGx8/A/F0XBwcEBDx8+5Pz8nGK5DKJh3bZcd0gkScLW1hZXrlxhc3MrOM7OZ3MJ3Dpcqe4198fmS31FUTBfLDg5keAsLHjOfl0WQ6c3FIL2diyJWFpvpevH35OWJFyH1vKqrrALWbBiIlQkZOizMyEsxzri4vycmzdvMJtMSeLYBehuLBobtI9Wzod2IbUdlDAEzC4YCdyNzuLZDer9Ytu91j4B6V47GX8SqBu8yZ8JiUo7f1oM4qfTIhirZR3/vf3c78Uh6YwlfKJiOvtTQOPEK7/f5o4f5VCg9vUWRZIOntBm7D+3nWJDkL7iaYU8a4ULQvzW6/U4OjoizXKqr3yZo6MjDg8OOTw8ZGNjg63tLXr9PlbB2cUFa/0+e5ubct+SGFyCX9tG7Ew+cBrwvbcPXRDi+1e8IJh0wliMshAp4jRBxZraWPHZsCIeZrWW9toolr/DK2EibbjWoIywvaVtUDEc9BkOcp66tc3uzpC6rCmXlfgWOCLRyaTgZLxksix572jCvGqgLilnE5Q1RFZQEM8SiZAHJlJBO00i2rrGKum2kYEvgkaNMUFtUQh8Yq5cLBdyNbTCy1BrpRitr/P8889z9epVDtzAun//Pq+/8bpMOA5er6uahV3QmIa10QgLHB4fs/zmN8h6OfcfPGJra5PBUNT9DIaqEYRjuVyAEiGhNG/bVEG+mcZlMUaGqKkbrBEIuHZog0cdyrKkdu2B/tgqR+CKtAikKa9zoNqsX0cRNvbiVaLU6VKK9lgubdbrONhGdBKaJoj9KNpJLWRWVsaH8IosVimSLCfNeyLIpLyKZdPJkB0B0XV8SHBJQGNUOMZLmysnefMxubfaBcZtKzF42FqOuiwLyqqQkFz7IEQHxUZrRRvk7t27PHhwn8ViQZb3ZGGNdFjUjDEMBoPQWprneZjQ/e+lVm1DIOYRF601mUM9NtbXuXr1KuPJhF5f3HOFYOiDTQmMjo6OuPv++2xvbbPqHLwa4IVgtBPchkm1G5j8gM1aRPTPrmpoeCfZi4sLxuMxb771Ft/65jd5+OgRy+WSja0tMkfg9c62/jna3Njk2rVr/NRPfZrbt29z/fp1t18dWl/934EELChCO2cSJ2RJymK+4M777wk69Ogh5+dnJGnKcLAmuj2ItH1d1Q4NlczWGENtGhbFkiiKmC/mzj3ZhJKFnLvwG4wxrpsmc8mXCQEBQJ7lXNm9gg9czs/P+e53vsvv/d7vce3aVf7qX/2rpLdScQh3xnuhvGAJpWHtg0qn7BhF/jn2AQpM5+LTNJlMeHD/gXg3zcS1uChKFnMpI9eNlKTERbpPEsf0+iI9sLEhXUj9/oDtrW3pAkxTuV+dRMAHO9bDQ77EExZ/N64asxKYdK+fD4oEXawuj642AOsEEh9gVLq/6Qb07W996bwxq2VQP59wCRUqCml19nOksa2Fg+eO7e7u8tnPfpaj4yPee+89rJVx+dprr7F75Qq3nnqKzTwXs76moSoKJuMxkbsOWZYRN8bRD5r/GYMQn1V5NVO56UYZ0RGIFFEaY6OIxlqqxjiNkAjpVXerfoDuveujy+6RAMSYBq1g0O+xvjbgxvUtbt/YwNTQlO2Sa61l/2TOw6Mpx+dTTud3MNM5y1rMliKlyKLI9cwI6hErJABRikjL4VikBVik5oUB3jgUwBiDbZyXRZaEGm5ZLFFKk6ZZC/UDa8Mh29vbFEXB+fk5mxsbvPLKK7z++usCRaZyHeumFpKt0gxdu+/J6Qn3Hjxge2eH/YNDjMUpg6bUjaj+CZNb7KeHwyF52kOQApe5NAbT2Pa5Mpa6En0BvxCJfbvYSYtgViGE1ywFrGOKS7dGpCN5IFxnQhwnmCgmisS5VmvQMURRm/U8aQIIhDCEiFq7Y/GjyRdmLCJVj8V1OblAwy2gSZqRZrmoOCK2AF1xKBCIP1K+5mw75OQWaflew9tYEyacSLckOh/M+MXYt22XpegSeL5CFGnRf4jarH25XPDw4QPu3bvHsiiC7Lzsqw1C+v0eV6/usbOzE7J/OVTr7pmQZ317aJdrlMQRSRIzGo3Y3d3l+Pg4eOwISGgCAbBpGk5PT3n48CHPPvus070QMnaX3BiQH3+PXJYXnFs7QcgPngoFihfzuJYn4Z+d8XjM3bt3uXPnXV5//bvsHxyEFscWMTKBuzEYDBitjbiyK0qyzz33HOvrG+4+iJCb6QRfURQRJ4mgHsuFBDL9mDRJaeqa+/cf8PDRQw4ODri4uGBtNGJre4fYoRbyVa8EH03T0JRNKD9MI+ESNI24sbaZvLOMwC/mbYt4uIYW8iyl11vHWsvJyQnT2Yy3336b8fkFTz/9ND/zuZ/h2tVrokWhvPFd54lzSKJ2wbxP3uUZduielTE+m804PT3l4OCAV7/+KpPJhKPjYyaTCfPZjIuLizboMw1rw7Uglre1tUWWZzz11FPs7e2xs71DHAkSJEFWEvSSrG1l3v0Y7A4W76Xj7+3l0pDf2pLrKm9JxtCqcaA8sz9wQLoL15poBkBUdT/TI0qXRrNq3+gRTz+n+rbtbvAUO5f1ra0ttra3OD8/55vf+Cbz2YzpdMqbb77JdDalaWqyPJf5pTFUpZBhIyuUgDRN0WWFcf/9+CHIhy4IAQk+XG0YyZSMMRi3ykdxjIkiKiOOoxbpmNCRcBWUjmis6piAuWzTNB40lhppJLr/kdYUy4rJeM5itmR6MUMpRX8wlEnFGAa9jOliibLCAo+UqM/J4mbwnBD5ClWLVpPEQWp+0rU+K6YdezKgaoyVWrJv/Wyh7haC84vr1tYWVVVxeHjIU089xWw2YzabUdUVkfa1WRXqrJ57MptNuX//HlVVsrOzwfrGWiC/KaBkNRDrTnI+mldYaFwG7cS/wsPVNNSVN4oTLozWEEdyPpUGpURTRWgABmsblxnJMRrrHECjCFPHNL5rwCEQ8pT6jNn/zyMVUmLSUSSt3FZqrMGPI5bFYiX7CNCoDhOX+42bKAze1LAbYwSRtw7E+702a1qinA8qQndBF9bulmu0QhkHdTsSsTdILIvKeeIsmE6nQTTLt5p2S2GeqDwcDun3+47r4UsobtHXrU+On2T9BCrPoZAoU6fuuuLK6+rW/tp51+Kl06rxPIEI31XA6kyuhBNim7Yc6T//g5Ljuh47lwmHR0dHvPHGG9y7e088Vdz7o9i5+JomXAelxEzyqaee4tbtW4zWRuRZHsiD1rYtpMolOtbawHXqXjcFoVwyny+om0aIurotNV/mSOS9Hjdu3gzkYu3QD48u1q6Ns3ICdbJAyXfRDZLx7Rdd+bsmlJdAuBB9J1h2Mb4Qk8JHj9jc3GQ0GjFaG8lx1aYd327e8eemnXCjH6++1LVYLLh//z6P9h9xenrK22+9zXw+d+NhyXJZMJtOV5AQ5RA0rx6bJAlN03B2dsbGxgYXFxf0+z2uXNljOBxKh9/mZpAAUO5i+5Jr4Bm5so11vC9PJPbb5cCjawAYAjntg4juuPpgGN0KCfcJY9rFkD9wsW+DoRZBtTgdoEslJc/H6fV7rI1GLJdL+Vosg2p0FMX0e320MVRFSW2Ef9Ld908iAIEPWxCicB4ZCTUNtW1oMJSmprairZH2cqo0YVYbltQYInSSEiU5SZJDkomfTGOwKnIEMZwltSVRJmR1eZaSxDEXp1Pq2ZyD/Ue8+9ZbxEnCsx/5KBubm+RrI3a2NyjrEm0aTFkQZz2SNIHGYOsSZRo0DRpDhCFWcuH9V2VN0Nuw1tWMfYai2ky4XoqfSZzI8QlRr5Mpm1WH1eeee47nnnuO/mDAsig4PDzkL770JcYHY3q9Pmkq3TEhT7eCUhwc7POFL/x3rl67yo2bV7l6bc9ph+ROTGceXC09IdN3zoixUoypauqmcqS7GUVZkqUJaZbQ1JUj+FbC79Ciz5JlkvnXDbJgaUusheVvzZLaALVjgESJy6Cla8CiXLbpz6e72ZWX4jhBKclMG6CylkXhJbENvTzHGOvIpyp0BllrQ5dAKzwmZmJYS5bFrq23QxS1MoNUdRVIqk/crKvhFmI/nqaplMEaQ7GUBSTLsyCvD6Bsm8nrTjkjSRKiOGI6nXF+fs7JyQn7+/scHBwQxyJ05wOB1gogZW1txN7eHtvb226halESvzD5seVl/SPHtBeiHIFXMugY3GFF0MkHQEmSMJlMODg85OLigqqqpAU0SYhtHMYVwErw5UsN/rVwIS7h0k+aOpQijlvLBr9/L7L12mvf5j/8h/9TVHNnMyFFx3Kv60pcdP29jHTEs888y69+/lfZ3d3lxo0brK+vS2vvYoGYCAr3wVgfjFtMUwVEru0EEeGps7MzTk5OHJk1Dh1Ycq1t4GRpl83+2q/9GjeuX2dtJAhBWZbic1JVlIXwfi4uWjGs8/MzhzpWTkui4OzsnKoqg7ZEVbX+MYPBkPX1mPOzM+7fv09RFHzlK1/h/PycT33yU+x+cnclSPAlYx05P6xOsC5zk+X8/Jw//pM/5sGDB3z729/m9ddfl/nEdfB1ya2m6WiBKJhOp2H8ddu4tdb0e302Nzfp9Xp85CMfYXt7m09+8pP8wl/6hWB34NEOH4D4seXHlX9GoUX6mqZuBdLc33h12lU080lL8g/igxCuC7TGgP556wY0fo5vBzMhEOhyZIJfjOui0sj86MecrDGt4OL21jY3b9xgOp1yfnFBfzBgMZtTLAt6acaV7V2WsxkXh4fURUFUSXeO1Rqj/mcNQqDFqjpIgXX/KeWEjHTL9wjTlRLuROCDWNu5mb5+6GqCzmnTyw6LtXrDfLbg/PycOE6Yz2bkeY+0NwgPXSseLy22VtlALvCQvAwAtQKDetj08pd/3fu52EbY2I7B0I79AOPJZNwYqfV6OHxjfZ29vT2MMS1hEKSNT7dokP+qqoqz8zOyPAsLFchDH1pmVdt26E5Rcr6AqBCyCy/k1TQNplYrWgZay+Igi5mcRxwpTOSlit1VNUjZzDRO9wWaRrRVmqYmajwpqzNUUIEHojqXSiuN9QJg7nXP6peJSaP15Zba1qE29tmQ/5VdXQPbhXv1Qb1chun+7Mej/7fPrC4L1vmJsx3WaiUz81koEOBsL14kYlarnTQy4fngJSbvmJn5z2sna1eyugRJy/vaYwu8Hfdc+Pvffb8X1/IeHmF/jkzYtmF+79bm8LvOonJ5W63Tt5vWsrj763J+fsHx8fFKYOZ1avy1stZKgKBFF2VnZ4etzS3SzAWlCplDrK9RtAvEZZi/W3IyDonzZPCVBajDbfDzQZokbG+Ls/H6xjqj0YiiKBj0BytBSL8/QCmCN1RRSMa7WIixIQgZdTKZhvvmzz0ct7tXVVVJm/d0FhRgu8fpER8/P8k1lvtfLIugX3FwcOA0ZPY5PDyUTo5Kyol5I/OVlDFdl4krdXjtDGvtY2WTxWJBVVXkeU6/L75EV69e5fzsnH6/z9poLey3yytamfs7T+r3ulfd8/XqqH7daJ90j4rocL8uC8yt3l8e+2z/ffU5Xz0WXwjpvu/y9/C3HbTcqva5jeOYxAVovvvHo4xaa5IoodI6dA62Mhf+uH8ygciHKwhxE52xQkT18uwqjtERqDRGpQk6SSCOQUc0KEoDsVWOCRqHBz9AV7Z98KT2Oqcq+8SRIokVyjbYpmG5mHF2ckykI462tqnLCqsi8sE6dVmjlCXSYE1FU8oDqW2DCJBZYgV5mrA2GNDv97A2oqotUZzQHwxIlKKfuNYuI0FUpDWJXzQaR0qrSoqyACVKnCjtst+EupFsDIRMmcQ1Ozu7/NJf+SUe7T/icH+fPMs4PhL79TTN2NzaIYpjev1+4H3cvSvCNvv7+5ycnNDLc4b9HrGyZKmzBVfK1aN9q6aVY6sbbG0wpegVJHFMpBTLYsF0cobWijSLifKc4VpOr5dhbSNuxNayvp4CqfOhAGsIqp2T6YL5YoFSUivXWr6njqvRw91T13ZoaFrNDQ9HRhFRlJDEkrVFVpxHl4uCqqyllBOCQxGSyrKcXm/A5uY229s79PI82HYrHQUNl6axjMdjxuMxWivyXl+M3lxG1p2UWiG0VqMkiiKssaQOcRH0JQ0166IoHDcmDtmPUsq1b4rzqEcuxhcXPHz4iMPDIzEuLMugDSPy/qKm6zO/0Wg9kP28Mq9fBMGXMzxq5ie71QBIRzrUn/135SBh4zopPOIzn89ZzBcsiyVKK7I0QytNY6WcEEoynUnbd2zhygi17yJxvA2/QEW+NKZlssVaFgsR9UrTjF6vx2Qy4Wtfe4XDw0Nee+3bHB0dgVKkeUaqI3FwVZrGNMznc+Ik5vZTT7G9tcXLL7/Miy++6EpXseMuOMfk7jXyr2gtZGqko00WLykFeqEq8AuUQ2erBuW68aqqIklSsjRlMBxy6+ZNnn32WYZrgoQY01AVpWvbbARBK0rm81mwcvDXXbx/THCLfv3117lz5w4nJye88847IVABCWTX19dZX18PnAvAdTUJOpa4ecc0Jow/nyhppXj99e/y37/wBQ4ODvjzL/y5BHtlwXA4xJes/KKoIx0CVCCM8y6qolCOX6TC7xqnIvrmW28SvRtx/8F9XvvOa1y5coVf/ZVf5dq1a6ytDRmuDQWxmi9DYOmTPP+81ZV8fpLE7nlRIXCfTqccHx9zcnLCm2++GZyqm6YOflLKzcdaa/pO3t9L7EdRxPr6OoOB8LaSOAljtBv4e4VerbWoJ9fSmSSqsZbFsgjBoG+T98+iR22VUqhIOyTZOLVjFdBLnwX7a+91gobOvZemgcaiEX0X2zhyemN+MtGH2z5cQQgSNRo8YqEko400KgIVO++DKBIBDu1r/tCgpC3XTVYBQAgPgat/NzVNJWQ/rSQIUC4Dr8qS2XSKVprJxQWRjhhubFNXDaZuUEoQkMY2LTnTWvGagUBYy7OMNEmxiNpmrGOiLCPRijSOZR+19OCnSUIvlwfBuIlkNrMsFnMXHqsQTPmWyqqq3UMq+gRra2tcuXKF9Y11bt68yfjigvH5ObPJmKbXZ3NrOzwk8qAbTk5OUEq6BqbTGUkUkcZDFGI+1YTAqBHxGyeF39Q1ZVFCY6EyrqyiiZRmPpswnU5I05hef4MsSxgOe6yt9SirgtmswFpDnqckcYQHAYwxRIWlaRSzWUNVSRDSGItSMSghAFoFaZZjiYijxHmSdMhTLpsUhEsIrxHO+6dpKMuKpnbuwe3ygdZCiE3TzIl5ifpkW//WoKyD+S3zuehgyMLehMnHd5x41UvpYJHFWTUqLJ4ASRxLWySiFOmhb599+cW9OzmbSvRwjBtzi8WS8/NzJpNJ8KXwwYO1rW6FBEgZ/X7Ptdf2QqAk1+Iy6qFWXlsJQtQqFB/2Q/u5xsrCWhal8yapQpkrAHweZXMH0W0z9Eic9xxRELhAxhkAevfVEKC48y2KkjgWrkrTNLz//vvcuXOHBw8eMJlMSNKEvJc711EXJBori67WbG5ucv3GDa5fv861a9fDfuqgO3IZpm+vUXCoVvKMGeQx8Qrgftz5IKQxBm29RoVBcquYPBPJ9d0rVxgMBvT7fZkDVifKFUSuK0y3XBbhbXVds76+Tp7n3Llzh3fffTeUbJqmIUvTYDGfJjKOUQQ/IM/5sa5UFVAEp5WmtebRo0d88Ytf5OjoiO989ztMxhM2NjYYrY/CvBXGEIqyKgUJU4SuDh+8G2MwkUFbHUpa2ume1HXNyckJRSml5zt37nD79m1eevElsavo5ySJBKS+rbZuapRR4VyMMZSFIHSJa4/2fDiA09NTzlyJ6tVXhVA7n4uBXZZlIbjwgf36ugT2vnU9SZKAACZJEpBpP0d0x3hALa0CKx2bSZJgsSyciWSXj+J5KP7clBaH3cDhsG3y4DvpPOrqn9ksy0ShN4qcK3Lb+RNKRY7785PaPpRBiAQiNiSsQlBFAooowmpF3Vgq2wg10U1a8v4O7O13qsJb0M4jIIrkS0dgK98ma4lj4Tys3CzbBEKh9eGNkvKMByv9FmlxbIy9sE9To4x4xiyXBePpFNPUlEVFVTf0sozRUDLTXpqGUsDaYI3GGgqnqtg0bTtWEizfFXVVh06JPM14/rnnSZOUqqw4ODgiir0GSBkeep9xz+cLTk/PODw8JNaK7a0NLMohCe2XuAFLsOYHu2lq6kJ4AMqTVpVh0M8FAaDGNJZiOUPrkrouKZZTRC81oU60K520JTc09AcRqCFNA8tCHjiFEFerUghtURwzGA6lPdSXruj6yQhqU2Moa0NZNxRlTVlWQsxyD5lnp0u5Ign8kzZAEdg1iRM3AZ6yWCx46603+carr6KUYmNzkyzL2NiQbFL0HPou0xEvIA/7+/q2V7/M3USW57kQPpMU+qslBr/I+O/tkcFiMef09JTx+CJ0sWiXdXkuhBBS87CYSbab0DQGqBx5VQjCci0I8LMvwYS6f6ccEwSpHI/DlxliFzyJauqC5WLJYrEgiiJBlxz5Wa7t4wTS7tZVhm0cctIlDvq/85OvQPLSKu47M95++x3efvstzs/PZeGI41BqXC5Elr1uataGa6yN1vjIs8/ykeeeY29vL0zkH3TzC7Uvo/mCjHVJji8RxJE46UY6cihQC+17VMg7qYZzNNa1ILuxEMo3/loKaXHpSiPeldmPB1nsLMvFgrJYkvd6JEnK1b09nnn6aXZ2dnj5Yy9z/do1tre32+DMtQsGAzvHSTLGOBLqkrv37gVPnDRJGQwHxEnclkRCWU1K2Fpp4qRV6vW/9/e6G/j4/+rG+RpFOnBHlsslJycn/MWX/4J79+/x0z/1U4Ic4sdo1M7bvhyoBG3ojq/FYsHJyQnz+ZzvfOc7vPPOO5yennLnzp1A6qyqKgQyXRSjqzzs5fc3NjYYDofhWvn3+/nUm46ORiMnm9+nl/cZDAdcu3Y13C/pJgxgYTvG3PlZcLYAqyVLj6z5LylD+/K4C9qNOAY3Ve1c5hW1deqt1n4AxssH3z50QYgRgN31nMhXYxAjHaXRcQI6omoaSqNoAFxg0iAdFxIwykRu3f1RTgBLaYWKhIsQJZo4VtIGV5fgILs4jukP+gyHQ5Ikxrf1htp2mGRUCET8QxZFmizNSOLE1ewrtK2JrGU6m3H3nbdZzOfMZwuWRcFoOOTK1g55nnHNmdX1+n3WN0eUVc3J2RllLYNJJnpNr9fHWigWS8qqIo5iaCyD3oDPffZnePGFFymKmjvvP6AqS4qypKpq8n6PLMtc/XdBFInh2XvvvSd20LdugoPuLLhuDN/qqF3kTBjAi/nUORBLZ0SaRayPhnIXbUFdFcxnc4pCnGiragHKUteaKHYRvit5iGR0xGg9Z2tryGJRcXg4papksbRGUSwFZo3jlCx1hDSkZCeLSeMWTo22WnrdrWZeNCwWJcvFUqy4vQtxY9C6cfBqShynMpn7vicrpR0vl/3gwUP29/f5kz/5Y/7P/8//G2st2zs75HnOzs42W1tb9Ho9tra2XRaUkaYxaZbR7/fJsozr166FDpXBYEivl3PlypUQ9Pb7/SB77hfm1QW6RXDG4wkPHz7g+Pg4aBsIqiPQr5eBHg4HbG5usr6+HoTKgupi41VyQSlpsfWdUPK6Xfl8H4SEkkwUhwBBKUWcJGBt4C1MJhMm47Fo3KytddAlWXAjaY8Kx+K3bqboj1Wy6tjdu6ZzbWQC9qTYi4sLjo5EJ+GVV77Kd77znbBg6EhUmE1jpFtjuWQwGLC9vc3ulV1++qd/mk996lOsb6wHlOf7bd3F0wv1CSepK+duWkVOB+XHTgUV1eX8uO8d4qeCwLcqShGmMrWURjzPx4el1lon3z8lyzJGoyFaJ6GLyVjLbDZlMZ+xs7PL5tYWP/XpT/Mrv/zLbG1t8fGPf5ytzc1wTb3xmvdf8ZyzLBMu2TvvvMujR4947bXXuHPnDnVdk+UZvX7Pqa129FNwiYYVr5c8yunyP3zAopV42PhA1nOKugihR6emU9Ei+Q//4T/Q6/VYLBZcvXqNXi9nfX0DkelfUld1uB++xBRHcdDRGY/HvPrqqxweHvKHf/iHfPGLX1wp0XhJAc/BCqWlTnDeRZr9GuLHh/9Mn3D0ejIPb29vk+c5Tz31NNev3+CamxuGwwFxnJC457QsVzkyQSfEGEqnD9NtRZaSXNEJoMrQgRcpLc9s3bBcFNRFjTYyZ9rG3TNj8KPqJ4GIfKiCEBu+XMbta68+K6PNGowVPQhBOFtmj0c/bIfs46+k6ryuFEHIx+JaJ2lbJ/2NVn6g+WMKkGoITQNpy5Me4yhyiIqTtHZQTlmWnDq/ivHFhMViwbg/YDlb0M9zQUtGI7a2thn0B3LMfsJ2GZDSitgFWNoT6zrZhG+7G41GrK+vM5/PRXitacguCRwZYyjKIvAJjHGdKt37YX123C5GTVNLXZKWMKyUF9HSAfI0RiTcY2uxtgElaFNjamztgzlPcDMYzy/QGmtrQCTxjamRLhZN08j9D+JYjmRsQ0i4Op6ka8Eft3ELlsevXJ2VttwQR3Fbv3U78225ZVkyn89D7z1W7N2ttVxcjAWNynO3+CfkeerM8JIweRtjGDpUot8X7lBdN27iXGcwGIb73mb5nbPqzAq+W6NwiBSd81CqJVt65CW4xGpN09Qr+2+RBblyHl1oC5urRD4fhHfHE7TW6f6zfQdCK6N+aVq7/HNnf11SpL+h/mi65+nfq7VA1svlMtT1Z7MZRVG0JnFqFUUJwmSbm2w5RdThcBi4At1L/722biDSfS0ctvscCdY6xNTOcfi/iTuk38fQHuOdnFc+aeU9T7pPfi5LHC/ANIbtnW2uXr0m3VI7O2yMRqSubBIyb9XZj1295z4IODs7Y+Zs6j1qFkURta1Dy2eXmOw3/5oPLvzmNT+UUk/0VwpjQqkQBHiDt7PTM46Ojtw9XMPbfgS+USeQVq5MWhRLptMp+/v77O/vc3p6ymw2axHKbpB5CVFRqjUgDRwNFyB3A1gftERRFIjSHk3ypVKQfV2/fp21tTXWNzYkmOvs9zJSKI/l6v2+fI27bfqKdt43jTj2Smv96u/0pXH0424fqiCkZYSIe65FkI7aGGoUPR0Rpxk6SihrQ+HqrcplFAakbhwgfqQ7xALKYrXAzkQQx5okkai6dA+DqGZqVBSTZj3y/oAoSTBWBK6MEZExrYRHoF39TQWEwBDHkYtmc/nKY2whbpqn56d86ctf4nB/n4f3H3F2ciYKgWnGoN/nEx97mSu7u3zmM5/hL/2lX5RMMY5JtaasKqplIfK6QWU0cdCuDpO8J0U999xzfOYzn5F67Ze+FOrhSZaGB8kYw/nZOfsH+1y7fo2ikLp4yDKNOLcqpYTTYBrm8xmz6QSMCBlFWpMnMVGkSBJNmioW8yVnp/ssiwW9fkSWa7IsZriWo5RlsZxQ1QVS5nK1UNeBkMQ9kjinKqGoLU0Ddb2gaSIsMdakxEnGYjETaDaNidPYORMrlAWtY7SOsQaqylCWDZUrxfhuES8xHccJpS6xRhRiR6N11tc3SeKMppbxkiaaMlLMppOwsKGkXXXgkKvZbMrx8RG+E0WyH2kRb5pGevPjmPX1dTLX1ZSmKYP+gBs3bzAajfjlX/olPvPZzyKEP3Ep7qIVfvOTzWw24/DwiPPzc1dS0SukVr/AeoGx0WgUtCfKslrZbzcYaT+qDUT8AqcUgRTqiaHWwbh+srXWUjjOwWK5ZDafk2V5KKcECP4DzgpKdZx1HeITJwlplrn6vxyb1tJCff/+fX7/93+fg4MDTk5OXSAmuhiWjvaQy7B3d3f5y3/5L7O3t8dzzz3Hlb29H+rY/PXzomJRHLVaL47zsVwsxT6h8Vlr+wnGGBqHWq2trTEcDNps2t3HbneDdiRYD/cDATHwZYE0SWSeQrroRqN1dnZ2eerpZ8DC//F//L/4xCc+wd6VKzx1+zZaa+ZOal+C4z5aSVZvrAkaN10NmDt37vDd17/LgwcPKIuyg5pGQfSt7dBqz9dr23THtO+06/KPBoMBeS9fWfj9964WznQypVgWfPOb30RHEc888zS//uu/zubmJpErh3piq0fE4jjm5PiYg8N93n33Xf7jf/yP3L17l9lsFuTx/bMinJw24BAumFhmLBaL0CjgA49u0H25Hddzt4wxPHr0CGMsr7/+BlmWs7W5xV/8xV+wubnJL//Kr/DiSy/R7/dZXxePJ3FUvhyIqBaJR5DbJI4FvanEXsCX7JXW1I2QchfzObPxBNs0xNbrtAjiqJr6AwXfH3T7kAUhBFKRVS3BVJxFcdCltOE2xjpte591qJAlAY9jScoHIzhL+LZOb7FBfc+9wT3kXqOiPY6AhLjoxn/3k7iHW1NnBR8nEXUlvgfLYsH+/iMe3L/P3Tt3OTo4FjKr0gwGA7IkZjIec/v2balBOsgPpcC5JSp3vAonLuV+7Qe7V9Pb2NjgypUr4WGvqnbR6S48RSFup0VRCFGO1Yjfv89zKCpXGtJAgjx4cSI+PHFsiSOB9ZfFnMViitIJqIgoztBRilKWxhRU1RxjG4ypJCshcZ07NXVd0tQaYyQAlPZGjbUitIRW1I3YcEdxO9n7eU65NE5qpjIJNk/IWDzJ0rfyeoVamXzEWVgrb6pHMGfzegNKS/khSRLG44rxeEyrOSIqr1o7sqCbAPvDYYBm41iCmJPTEzY2NvjYxz4Wyg5x1NbFVzK4zqD2bZVFUayclz9//3dZpxzUnu8TUBa4dN8vP5odtMWhcXLtW8fZLkTtF86qqqibOlzjDwLyrmR1qkUbGndOMW1N37oynM/exuMx7733npAYiyXgnWiljbNqVvVc+v0+N27ccC2xG/R6vRUNiQ96rCuBYocY6M3tpKRqVkQIw3tccuOf34CG0ArihffpVV7OCmrURXEdUuSRsF6/z8bGJlEU8eyzz/Lyyy8zHA7ZdBoos9mM5XIZAjalXAutlVZ4bVuDw7IsuRhfiPLqdNoiXW58dEuJ3WuklAqcNB9QASE7D4ia1kFO3//dCmLiyh5+Qa+qiuPjY959910y57Hlr4sPVrrPfxRFlFXJxYW0bt+5c4f33nsvOCZ3+R/d0osx4uPl+Rzdrhd/L7s/X/63Pw7vaixlVOENjEYj5os529vbvPjSS9y6fTvYM/jy6uNI4uqPWikn3BnRmNYIMYiQGdF8qquKqqyk9BK5sepKaLH5CUYgfBiDkLA5gN1dD2tAodE6QSlNUxvpJDLdkoUrmShohTtcCCHIuwQg1pHqnANoWVbMZgums5nrNBCBncViQaMTTJRRLEtsY4UV7h60oIjq4T5rqWoR+8oiQ1FklBFCakGgxiiOiZOEXn/A2qgUeLVu0FEkLXezGVVZBZ2RuqpEhEYrej2RE/ewsm/LMk7JVblzUkoxGA64enWP6XTifD8ckcm08sTGNEFts64qklgGb1VFrG4t25xwPwy1MRBptE6JY4VSUjpR2jAc5iSpQUUVFiF2TaeFIFGUJAlONTKVII4GS81sPqdYGpJkyGjtJpHOWCwUZQmmiajqGK0iyrJE6wU6UuT9TBYqf3jKle2scYRe0Qipa/nZ36/G1KhaBlfktEz8+YZMGZnY69oIUtZZiK2FsizcBIUTh2tbXbUbb01dS2apNbnLwjxXZ7lcOiRD1CLFor0DxXcySb+oeKjfL/Q+AHgcxpezSZI0sPSbxiDAoUa4ip6c60mOrgTqgjpr26DusQmQNkiSRUi5cdAxAsQvxCY8kv76KqWkTRDCwtDdVoIvJdbpRrV+LTIGJGCr64q33xZC4be//W3u3r3HfD7Di6uFzrK6YjqbYaxhe3ubmzdv8uKLL/LCCy+wtb3tApBWPfX7b23JhXDNg40m/pfGGNcWuxB+gjOGC46pVUVZicbLYDiUdn5HaLTWhhvpr0/Qv+mUMyrnwK21CvfaGCH4b6xvcPv2bba2Nrl+/TpRFPHSSy+xvr7O2ekpb77+OsvlktOTU8qy5GMf/xibm5uSnNWt47VfzCt3vIu5ICdejE5pFbgjHpHpBrp+bF5z5Nc4jqVtO9IBCfE8lLqpGY/HzGbSgux9X7pog3XPY6/fI7c509mMd999h8FgwNnZWfCjyTIRBfTolB/Hjx494itf+Qr37t0LHVz9fp+1tbVwHD5Q6gZWSinm87lDFMt2HF4KSKAl2XZ/9rodnkAu3XRiYXFxfkFZlrzyyiuMJ2M++tEXWFuTgEfmbUPTtHyby3MBShE5ZG0+nzMej13burR/i2SF6xYsClm/dBqCXWOc/QJcjm9+5O3DF4RYG2opwZPD4kRYRI5bWe0WF9+r38muVupZnrNAmC+0C0K88qUKQcic6WTGeDIhdz/PZwsalWB0ynJZSJ+8scImdop12vWq+VKQKI7OyCLDsuiTx4q4MUSuDhknMUma0B/2qRtDXVYUi4ULQgqm0xlVWbogxFK7duI075FkmQs0hDbUWBGnMY3B1JV7EIQVPhwOuHb9KucX52R55iYw7+/ShKBisVgwnUyo64okkbpl2XlwArHOtLyZwA+payBCaylvGVvRmFKCkLWcrFYU5TllvaSsLXbaEEXKcSVi4lhQFGsbFuWCpqmYzcYcn4xZH11h78qz5NmQSFuWEVS1wi4lky+KkqaxpFmCUq1RVPvwSJDQ1A115b5qv7i0Ik2+BBhFUeuIatt6qjWyEle1LNYeDfNogheFAkuWpY6gljkEq+XTgEwYfiK4uBgzny9Y2iWnp6cBIg11fSXBrnGlDpnkWz8lXzMPWgidjG11k+w6z3tEjkQKbVnEGAU0IdDwf+PZF5fRpScFIo0ra3RRmBCEuOwrXAM3prxxXeiquXTs3QU23BuLc8a2QUwqSRKyVDLfN998kzfeeINvfOMbvP/++xhjgv6Fh9PLsmI8GQPwzNPP8NRTT/Hyyy/z0ssvs+Y8li6Xv77X1gZt7Xl5VFaF6UgWBx+EdImYPoAM6GKkpRwzFMuI0LJqWjHB8Il2NQj1QYgQnHvuvsg5bGxukmYZeZ4xGo3cfZGF9c677/KFL3yB2WzGxbl0WW1sbvDxj388lJKMMcR5LB0vVuzjy7Jkvpi3Tsm6RUCstcRR3JLzq7K9j1pz/fp1PvvZz9Lr9RgMBiRxEuaVqqy4uLhguVzyzW9+k3fefSegmV2UwTSGspHArT8QnY7xeMz+/iNGoxEnJyfiRZPlJHGyIkmunTnkw4eP+NKXvsTZ2VnQ2BkMBmxsbDhX6kkQUYPOnGBty6Fz97jrcuwJ0t3WX/++YMBnxedHEggpsS/mCw4PDzk7O+PLX/4L3nn3HRaLJZ/+9KfD+PXJY+AHJolo3XS4H8YFN/PZLAQhWSYIb6SEJ9PUDcVySRJpVCpyBCEwNtId9z9vEOLQDyVKZTiTd3GoVdI+qxpoqoq6Fq0O7wGj5E9c0GHDlyilygIaRZpEx6HUopU4hPZ7PdbW1tjZ2ibLcoZDcW9UsciHewdJz/3wE6tF+qo9IuJbdJNY6tMe8te27TTpwrdKCRchiiKnwVFQlVJPFZvvOCyOknFEaOuIhx75cZNRINZGrThNkkiZo6uG6RcJDw+2bVxtn3l3sTFW9EGapgbrjdcUxDZoNHifmMYIaVVHEFloTMlyOcM0BWU1IY40e1f3yPI1UNI1Y2yDtTXWNkSxJs8zkjRxJTDheIi4lsJmIrXezUy6k4G1PhOX469rUWxsmu5k3r0H7oFzAYMPTj1K5hcXgOFwwNbWJpubomLpM75uGcQ4ArKQ33yG32ZJ3fKKtMu1LXuRGwdKt8GQlIN0yJZksnDMqboJmgRd8lp3wva8AQ8de7K0BPBdqLy7cPrXWkTEv0+ptovDZ6/yu84xKikVWvfHK88PICRrV+qK2nLa5VKQUl6luO3YEQTHl4QkUFsul8xmM46Pj3j48CEXFxfyHHSeN39djGlIYimH7e7u8NTt2+zs7EgQ5BdR5xUkX27R9+UA/4J79vxxdMtUISzxfBoXpInTbTvJixtz247r2yflyxMvfdu5+wqXqL0/MpY698W2nC+szHmiruwctuuKkxMhYL733h3uP7hPVVYyDpOOAF3n+fIZsieEe27BsljSmEba8l2p2JgmzK3CnZLnaW9vj/XROk8/8zS3b98OnSJxkB6XJG60Lgqxs/mMOIk5Pz/n/v37QbwLn9C5sSzS+W2HljFioDeZTtnc3GzHbQdF8QnYZDJlPl8AIsXvVXZFJC8iiv39R2T+sxQsLqFpu578mPcBtU8YGncPusrBypFvy6rCBokAmeezPMdaQc5E6v+Yg4MD12gwcp1tXSK98CGtcSavEMaTNZKgKqVIk1SE09yzhi/vOTRpldKvAtr/k9g+VEGIq5gQuRqZNcLHiJTCKEWqU/I4J25qlrMJi7JG24R+mhPFiai+KVAOQrHKYlUjZFfbgDX0s4RhmtLr94l0TBQlbG1usZZnjAZDttbWSZKUp555nrX1DcaLkotZQVOboDxkqprali7wsGhriK0i0jH9vMfG2ojRIKeXZWRpQlSL0qqf/Pzk0jQVkdb0+z0irVksFpi6ZjwZM5/N6PWlTVhpzfl4wmQyQetI9DG0V+2LqJuGZbGUiXRNZJ/7fQmqBsMBWZ6SZIl0Dzjo3bftlWUpteCioK6NW4xdH7qbzOpauAd1XWGBJM2kl9xatBLfC2tqGjOnaeagauLEoiNYnpxzcnKPs7Mj3rvzBkkS88u/8itsbw+pm5plUWJtQ20LLA2DYUavNySJ1zGNoioNUbTGoN/H2Eh4IsYyXyycuFdFWS07Wb1GK0ijiMqWLGZz8bYpRIEQZUnTxC2svm7tFgWtyPKUXi8jz1LxwWka6lJQpqefforNzQ3m8xn37t118tjLlSykqkpmzisjTmTR7w8GbKxLNu4zKGMsaZqRJAnDwYg1F/TmeU+QGEcGjCLxwWmDBEVV1TSmYTabM5lIl1W39r10QkeiCJmytrbG5uYmw0GfNJFZtXBtoz6oaJ/Atgzj/90NSr2wm9aR6BGUFQrlWpyT1iDN28EjipC+fRokoGjqBuKYLEpcyaqhqR5v0RVFSbG411o7JMlzkKJAzj0+PuarX32FL37xi5Rl6dolV9ssl8slWmtGa2sMB0N+5rM/w1/5pV9ic2ODLElFFde05R4RNBRNC68e3FgrZT+Pumnr2v/bbjuNQluQzi5LXVcUyzmLxZyqLGiaCowQyrEiYNgkMWkckSbylcTyc+mEEXFKqSHwUY5A7C6qH9Pyeh2CYWstvbzHaDikrEom0zHTyZQ/+qM/4s033+DdO3f41re+xaA/4Od+7ufY2d12LaKaqjaUtQtyI4VRhqIqWFZLFsWC8/E5J6cnomici6ZF45IKSZakPJxnOYPhgP/1f/tf+dSnPsXu7i5P3X6KOImJdUvS9ePeO0d/5nOf5fT0lG984xv8+3/37zi/uAi8kSQVYrIPJppaOvHyfo/GGu49uE9jDFtbm1y5soOOtRMFbJgu5tR1zeHREfcePBBCfhST9SKWRcmyOEVpReq6Y7y9x5UrV3j6qaeEq+eeyelMjCOLouTi4py6ct1gRlzMi7Kgrhsp8xcFvZ7ogUggU2OxrA3X0HFCkmXs7l3BNIbT0xMePHzEaLTOrVv/jb29Pf7SX/oFNjY2XOLoWtYdirF0iGmkNWkckUQa67gfcRTRG41YGw6J3dpjGhHgNJHFNiaMZ3+ufiz/JMKQD1UQIptq/5OkPfysXd1MITXCpm4gSoi1d6VsEwW/yFj3Smj6VR1Cl/u8NE2JMWJTX9bESRIMuualwZglXi9ByZPiNAEALdmRHJ8gIZLZus9xUbsyKjhntrClAQ+jK2k7LUvRWFgulkRxTF8Pgy27LHSqQyD116zVc7icAYbP1536NS7LVB7F8JmOv15+MeqgIZ0M2/9O2PfSfmtM42DTBqUNkYsojamoqiXz+ZST02PSJGaxEHM7kadfCkqlxLs3ijLSJEMrWcyMcaZ5UYK2EUanNI3BsqBphHDqMy+R2PHIBgFOrhvpTjLGoCM6k16nddChJ4Fb4e278e3PMBiIV8fm5gZbW1vBGdQLGflFMyhWukzS+6TIdVyt53rtCx8U+jJPMAhWmsuiWZ7E58mOPpjwHIJuF8VlJETrroNty2954pP4hJf953hUzZe3QrdMQFXa8k7LC7Cdn+VHD483NJ3x3H6W349X2PTXQzRKRCthOp1ycXERTOK6pMIA37uSRZZl9PIew+FQ/Fn29kTptlNKCMdrCSTwcF7+4NrHJEw6KwUtjwC5bNN3SHmVSpRvZ27RFN15dttFQIXi2ApSdOm+eDO89vp2ETGI44iiFITgYnzBo0eiD/TwwQNOTk6C+WKaZdJRolbvXVf0y39VdUVRtqTocFyuZGARcbHYeRbt7V3h6aefYmNjg53dHXle/ELnvhtrqBtRkI1jIYAeHBzQ6/eZLxZCoK+lBO4DTE9Y9mPTqxrP5vNQTlEK51ukwnOzLAoWiyV1XTt7BL0iyibBtnJlaimVXdnbc8RymZ8mkzHjcZsIePNALxQmx1S1/A8nouZRQmzLxfBk26YRx2/P6Tg+PhajxboJyWEQC+ygsF3OWBfJiuN2fpGHYfU+2hWEjTDeO9XGH2v70AUh/kFW7h4JMVW58oyvsEjU15gGG5lW+6NbN+/szQLWZXtF3aBMzWRWMJkuwWo28j694ZCN9XWuXtlCKU2aj1BRQnM2YTyeMp0uaGqLtTqUhbSCWDnZdqWkduBd9TroqX+IQRxek1hIckVREPdE7lcB5XTGsi557733+cKf/7mIJ/3M59jY3KA/6JPkKeLq2sL58l3ayTwfRB6OCQ8ePODw8JCyKFoXzE5XkCyAUqOMdORqgi5Ktm0NNY5jev0eVRVzfnLKfDoj0Zo8jom0op8LFI9STs7ZEsUGZRriuCGOpUQznoA1Jd/85mucnBzSNDIZ6FgzHAlac+PGc1y/dgVsH1vHYCOUilEkGCNlhKpqGF9MmM1nJKlic6sP2l9jD717roJkA3VdUtcFEcoFLDZoZaRpQp7mQda81++7CanpMPkNGxvrbG6s87nPfZbRaCQT2XLpSK9SrvIw6mKx5K233mJ/fz/oefjOBl8GK0uRGB8MBoxGoyDC1AYSq3wSP7GI90YVSMW+/OMnqKCs6+7t2tqaaw3uYazXxWnLgd0g5INwIfzx+DHkZypZ6IVnUxRLZzVfrpT7AFc398RLQiDTPQ6PxvgFLukE4n7yrGvN/fsP+aM/+mMODg548OChW7ykFBmI2m5M1HXF9vY2P/dzP8eVK1d4/vnn2draCtm0PzYf5HivEYHcKxckdQNYj065wLFzbfy9kk4IkUmvyhKUIknFvVtrHUocXf6LkMhXu0u698d2SkG+5CEqwJ3kpjM/LJYLFssF7777Ln/yJ3/C8ckJr732Go8ePWIymbjP1YGjESdx6BaMhPBF6saS1/HI85yiKBiPxzL23FhInb7KYrFguVyyvb3NjRs32N3Z4caNm1y9eo0oilgsFw7yJxyrHw8+Oej1+2RZzu3bT/HpT/8UBwcHfPOb3+Do6JjBoB/Gr3g0SadMWVZB+2M69d0nre2FUoqqKpnPF0GEzAcAXZn6qhJuitaa20/dYmtrk0988pN8/vOfFw0Zx0MsiiIIupVlsSKiJjYC8pon8DaNCWjlo0ePmM/nHB0dcXp66rrlRIjS65Q0TcPJyQlZljKdioS81zwC8JQ0P09Lki7jpFgWzGYzkiQJXT+NQ82buhE5AxSR0kSqO74IwfFPIgr5sYKQf/JP/gm//du/zW/+5m/yz/7ZPwNEKvfv//2/z+/+7u9SFAW/9mu/xr/4F/+Cvb29H/tgIeTgjwcituWc+wzTNAYbu8hEt0HIyqTqL6ISIaOqNlhbs1hWzBYlSZQQr/VZW+uRxpCnMvktCihrXH1xwWJZSDeOVQ5NiYgURAqUbcLx4o6vw40lEPFwsvBxFDIzejbYoS/HE4qi4NH+I7717W9x89YtXvjYy4zWR+R5ziCJqaqa2VwMqnyNWmtNmrSlHqVUGNyedGWMCRGuXwg9cUoi+9YNNTCkVUsw9BOQdLlMyeIYlecC++WOMGt9ZgeRFp6F1oYoElh6NreUZcU7797h9PRBqKemWczu1U36g5yd7ev0Bz1Mk1FMI6yNkGEcY6147tRVw2w6ZzyZsL7Zl4DJxX/gyJwGTCOwv4fWG1NB44zGrA9CDFqn5Ln/yldM4LzZltaK9dE6vVw8WK5fvxHuYVs79xLQx0ynU+JYyiPeXdRa6zwndOdvDXneC54UbRCy2hni75sxtB0KrrvGt/X6zZeG5N6mYXFJ09SXg9vJ5kd5RsMxaTwHRIZ9G9h5iXyP1JhOOeZyJ0EbDK1+hnAeVAiwuudmjKHRmsOjI772ta+xv7/P8fGx/F6pgB6Ga2IFOer3e7z88svcvHmTmzdvMhqNWCzEPdsTB+M4CgJzfgHxAlTtMeOOz6k0224Q0r0eTScQrtvFIo4DQmqa1SBEa93hyDx+k3zLrtY6GMr4Ljl/TP46A8wX0sZ95733+KM//uNAflwsFoE34ltipbMmDiR07QzS4liIpj7QSdM0lHLjqOU1pVkGShbnyXjM5sYGuzs7XLt2jStXdtne3g58j674Vret2G955qTlr17l+eefZzgc8tprrzGdTgC70uoeRSpok4gOyZz5fE5Tt63h3jtGgoPlimyBH2Ndld7pdEoUR04ReYdnn32Wn/3Zn6XX6+FU0EPQ57lf1lrOz8WPq3G8GemOagOU8XjMZDLhjTfe4OzsjPl8zt27dx2HL+4kiFIOHo8vGAz6LBYLtz8bPtejqlmWBTKsH6B+fvBBY5qmNEY0k0zTBE5VpKWErcK4divw/9PlmK985Sv8y3/5L/nkJz+58vrf+3t/j9/7vd/j3//7f8/6+jp/5+/8Hf76X//rfOELX/ixDxZ82UTaFL0tcXeFt45i2thG3Dgx2NZkEKURGW+PglivL6DAKAySZSzLhsOjM2aTOcV0wmEvIUs0/Uw6T4pKURvLwdEZ4+mc+bJCqYgoyfA6JShch4wl0TFxbIIynpD/GiptSbHEkQQKg36f4WAQHgjvCaNc3KK0YjqdChGrrvnGN77Bo/1HbO/usrG9JedE6zXRncjrug6T6f37D3j33Xd5+PCh9IODg+ZTIcmVJZFS5C5TzvMereGalDCkRqjDcUqrcNuFYYzBaO9XEtE0skjiSjTW1mhtiSLF+kaP55+/hmkabt3cZH29J+WYokBp6A1j4kR628eTCyIFsY5QuqviKJ9jrBHX27pyHR+10JeVk8FW4ncmaKcnGDaIaivBBwcaLE7JVRkPs6FcW7e1BN0XQOST3STmRbk8tNolqIHIMV+5coW9vWOapuHBgwcYY4Jyp7XiSNx4XZA4CsRU4xAcaFGKlrvR6gz4SdfDx+EZWlkQxcCu1+u583hcG+RJfyc/+9d8QYAwiXdl07t/70s0K4RG0wbhlz9v9Vi7KpN+Qmz3IQQ7uRenZ2eMx2Pu37/P4eEhp6enEtCmIuDnkYiyFMnqLMvY29tjb+8qe3t7XLlyxUHcsvi391Oud103j0nnd9GmLhm67VpwYoj4kpUnbDcrBOrVYKYll6tQyu22eq7C7SAcOVBB68jvR9kWWfCdQHVd8fZbb3P33l3efPNNzk7PmM/mYVzUdU3lgp/Ede7JHOADLI1SbeAnmjvSXvrMM8/wyU9+koUTOdNaO/dpTVOJU3J/MCB1C6TsQ8o0kfbdWasl3tVrKzYCSSIibtPplF4vdzoq8cr46f6tH7NKrZagsa1+jdz3VtFV5rjVTphAFHaBYeTvm0VMRAMpm3AuUlKWwMWYxvkZSfLRNPL8D5wlyGQyod/vc+fOHbzR5WKxJIo0o9GIra0tnn76aV544UV2d3dZW1tzz7nnc4ntCLSeSoIES3nKd89JOa71D/Lk4m6QK8ElK1otP6ntRwpCptMpf+Nv/A3+1b/6V/yjf/SPwusXFxf863/9r/m3//bf8iu/8isA/Jt/82946aWX+NKXvsTP/dzPPbYvD1f5bTwe/4BPlyDEOg+Y7tRl3esGQ2VKyqakVm4hjEDFCmINVmOtxliNaRTWappag3HlCBVxPqn4zhvvEylLYisiK2Zy6/0+SmsMGotiPFsyni1p0Kg4I0uEsFVXBqPkWGMlCo55FEtLmNPlKIsCXVmSPCbPE4b9Prs729RVQZalIaNdLpdSk0YmooPDAw4PDxmurbF/dMjG5gaf+umf5qWXP0a/32drZzfU+bWWW2yMLGrHx8fMZjO++tWv8qd/+l+ZzWfM5jNw5MF+v09ZFCxmMzCG0WjItWtX2dxcdzbeNmQTbuWXiaosHclJWtFwD7JWkQRYaUxVa0wpmh/GlhhToiNDmilu3Nzg1u1Nkjjh+rWbrK9tMJtLfbqsCy4mx1R1QV2XPHr0kEGv4drO8yRxj6qMaGrh82SZZGqj0bqoZqYpZVkQxRFp1sMLhEkQYjG2cR07FcaUQEIUuQ4CVWJNA9Qo1bgvI5OulVq+n1iNMa7GXDnTqR7dEoLP+qNoyN7eHmVZBkXEuq559dVXaZomOJqOLy5YzOf0ez13/VL3lTmEpJXBDmQxN2EK5FwEsiV04eyWd+FfHw6HbG5u0uut6jasPHWdv/OTU4uW2BCQeIhZMjLf7t3lvJjAe/HBSghYnvS02253zePcF4+qeLLp2rCPQnH/3j2+/dprvPbaa3z3u99lMpkwGo0YDIZB76VpGsYX0qJ4+/Ztbt++zUc/+lFefvll9hwXxF8/r2nhicqlszPocqy62ak/b5FmaNU0pWVdr5TGqkpIik3ToBBrAF/WaDkXsnh5XxGl/Xyg0HhistdiebwV25cwPDLgSyWTyYQ//KM/5D///n8WEu/RIdZYUVZe67NcLplbG5AfaTONw/m1Ghm+w6cOHIpf/MVf5JlnnuHOnTu8/vrrwj9wIntpkpLlOdvbO87htg9K5BBASqDGGIqyXBk/1lopWwEmy1EKej3hk1hrhGA9HIagsdW46QZ9/rnpICshQPbPjyAUHr3wnUtRZFwi0PJCkjgmTRIxF0U6URaLOZVTIm0TAF9ujFlby9y4fsKgR9SOvZ7J22+/hdYi1Hh+fk6SJHzyk89w69YtPvaxj/FLv/RLrK2tsbu7S5KkKFV10Bfvtt0KW1aNoaqbME6V0sG2wc9HppNEBPsSYzG1eaJc/o+z/UhByN/+23+bv/bX/hqf//znV4KQV155haqq+PznPx9ee/HFF7l9+zZf/OIXnxiE/ON//I/5h//wH37gz3aVF/fd08IAZd3P1tW0TatboTxpTbpjXMFU9md9RqUcZuG0NaylKGs0hrIuUKaiqhps41qoXFY9L2rKusFqCXAk2/bZCyHSlkkKZz6lQsTcjTZ1pOn1crfwRJ3MsRXQUkrEraqqRmnN8fERRVlwsL/P5tY2g8EQ4wKKXi8njhOaqqQqpMZ5cHDAdDrl9PTUsbYlAIy8bXl7QVyWkbr2Pdc901kpVshLgeriESl/cQW90ZEWaXcl+/dRuPA+auJYibJqIuhLr9ejscIe1xUsywylbZi8O4cZrpHWHhkTVUBP/vWHHEp5HtoP+KI/cvkul7p93deVddS2Rkomvtq65jkz0AqS+WvqM1VfulJqVf2ymwm3+7MhA14ldq6iBJdrs92M7/tlLW0g4s+pFWP7UTefSV4OPtqtRU1W/3D15S7C0iXUrf7eZ+MOCaKFvyeTMYeHB6Hc6GFprZUrva6iMb1ej52dHba2tuj3+0HQyx+x9lmivmBQQQABAABJREFUEnuG7rl121+hLUd1j7V7vH6f0AZST7omjyNBHYKvvKElxarVa6tc0rJCKFSrx1kU4qh7cX7O0dGRaIk0ZuV6+3HhPzdk+4Gc7s/DolSLCMVxvMKnOT8/D1ocQAhqdnZ3xMtlMHABiu0cq4P7LVxuCV29ZqvE58sEaB8g2zA9tCaLXXTNn0xXo8V92so99EG3/3f4bH9f3K+686M/5u517V4/fx4iASDeTV5CQQKJFqnOsoydnW2uXr3K7u4um5ub9Pv9YN7o75cfG0/idHk0Up4L4fz4JCU0Idh2/Pjx9thrP4Hthw5Cfvd3f5evfe1rfOUrX3nsd/v7+0ESvLvt7e2xv7//xP399m//Nr/1W78Vfh6Px9y6deuJ77WA0VBrcc1tFNRKbMxqBY2GRltqZShtTWlrYdVLf5xMJFrEWHCLmHSxKJROkfHoURZL+wREKFNTNIbiQghqOHl4g8YQAYKwCNwv2X+EJVYNkZJWVYVxKqrSI5/EEakWZdOiKIjjmFu3btPLc4Zrr8iEbhqqRiB5FUXEui2O103N/fv30VHE/uERX/jil+j1+2xt7ZBmKevrG/T7fYrFnPlsTLFcsr9/wHw+5/xiLGiGIpii+U6CoqqI0pSs12dzc4vd3SsMh2v4YRfFMbEbzF72V3Q6LHVVs5gviBQkHXJrmmbUTRSY3lVTUdcFh8cn3L13F9NU1PVSFmibYBqpVU+mE1CGwaDPWjSg19siz7eJ1JCyKCiLKVVpnP9BSpzQmQiTjsaG0/aItBNOwlOSHeQthTwc0mFbj2ayPAl9+Otra4yGQ6ratMRW1wGAUs6QLg228b6uHASurCVSisghSKE12G3GuAzFWpSO0FHsrl/6GJLh4V2/KfX4tNAGjm13lBBfa8qycOS7hlb3og1AVTvUVoIp+Xz/u9Ugoa5r585ZBK0Evyj5yd8YG8qNgaekdZjV2gzWhkXCc17CXGBFTNXzD0TYyTKeTFjMF3zt61/n9112L6TsOHymdeqaTd0EOP+ll17kr/21v8r29jYbG+skSTtuPLESXGu0bSfxbteBcfohokraA2zQabEB+lZoZdHKB60SsBEYbTZ8jh83QFg000Qy7+691kphfbaKV0i2nSSnJdT6gGm5LLh79x5HR0fs7x8wHo9JkoSNjY1QKhJOiHWdE4nTqmh5Eb4cY60JHKTIoXZJnPCxlz9GWZZ8/OMf56/8L/+LLGwu6JrPhQybZzkbGxtkWcaVK1cI5aUwz7XjTsoFnfXASkBYliKvfnFxEXgReS6IUftMtZyaLMvEkHBrizTNnOWHJo4l2Vgul0wmE0dOLd38JkrcvpvMe7x45Knfd5wqWfmJkziU0TxfqNUM8sdkWkFEd155ntHrCddoMplwfn7OYrHEGMPe3lU+97nPCXn6Z3+Gjzz7rPg+Xdltif9AmsTkaULjkCRxAzfttVXKcfdErKyua/JejzTLKKtyxbDUI5QW2jIOwnv00gA/7vZDBSH37t3jN3/zN/mDP/gDIUv+BDav1PaBNqFt0GiLQWEUGMSQzij52brXGmtobBOyW4+EiCy7eyNtxiUXVaG8cJkikLqU1Gmoi4KiqGT0O+ElHSfoOApsaKyPREEjuhraWaD7aUaBa9dVRK6Xtq5loG5sbGCaOlwTCUQckdBLykcaa4QcdX5xQWMMB0fHGCDLc9Y3toIV9HA4ZDmfMR2fsXRByGKxIO/16fUHaDdpyALSWnPrKCJOk6BFIqUYOXgf+XuialsWaAmVRJrEZyZR5Ih22hfTQpvZbD7j/Pycslwyn12Q5zlP37pgfbTNshAGfRRresOcNIvp9wb0egNMk1EuakxTUpWx85JRoMRcSeGIZDoKzHyv2hjmb0UYHzbMbm6sALhgJI4jmRycqmSepRhburpqQ1UL+TR25oEySccrmXY3k2onIhOCFL91a97KQcZ+f09CQcKjcWku6GZdfpLrBha+FODJt0/e5yrCEpAy2v16ZMm/z59TK77UBkceAgcTxkvbLt5+UnssqyfV/fz2PNtOgbIsmUwKprMZDx485I033gjy4L7zQRauVkjKZ6W7u7u8+OKLKyhI21YtwlcAxkbtSGmBNwB33m3Q5V9byYg7QR60hOXL966L1LTzRev7cnnzaEjbAdMGIS1C03YqeX7YyckJk8mEolgSx1FQ9ZzPZ4Eo68tHXh+i+6z7ffvgWamELIrRifhd+cDZBuRTrn3pypP+OJVSYU25zHHxr2mlsdpLbnVLgF3F2Tqgkf46ebVYj1p49dJer0cUC6EdRZBt9x1vbQDZjvnumBWuVRM6paKoNbj316zLjWoRGn9vm5XxAbhkTp6joliGLhprYTgc8sILL3D92jU+9clP8pGPPLsyZopK9F+iSHRyvA6JEFTVynPou++WS/EEk0BTjresKpEtsKvzovVIngJF+9z+uNsPFYS88sorHB4e8tM//dPhtaZp+G//7b/xz//5P+c//+f/TFmWnJ+fr6AhBwcHXL169cc+WAtUWApwTiKWBiiVwmiFEcUviDU1DZWtxRk3lsi+rAqsVSidkEQamkiwicDi1wI5GcmBaxAEQ8dERKhUEVvdgTkV6Eis5b0CoEM2RMq8xjYFRhnoKaJISX0/jki0BiPEWSPLMnEUs721RRLHPPX00zz30ecpFgWz8RSAQZ5L655XczUG6/wYJPERAz/JruVhPDs7x9QlTSkCVXEU0XMdHiJgpFvF1VpqoUmScPXaHpubm+zuCkTtJ3lcBmmNkRpoGNAF1mVNvV5PGDOu7FJWFUUh/ioKTaRjsqyHjixJnKGVtNpWJVjTsL9/CDZiNp8xmU6IE832lRF5L+XqXk6/v0ukI7I0xZqUJOphTI+6tiyXS4w1VHWBsQ25cSiXUg718mx/MKZmMZ8xn89CPV7GgZ/kdZv9pAkqErfiZVmAEn0AhaVxXSwAnpHuhaBaWFdIjRbkenR4G13iaFj4rWTKCjpdCdHKguZ9XTzh0U9ykpUWeL8Wry/ghb08KuMXNL9/MXBbLTX4ibcbHLXbKvx/WYvCt1i3AnyPB1B+UYgjcYQNgLc1hCyA1f12pbK7ZLvpdMZ3vvMdjo6OePToYaug6Y7Pl77E6XlKluU8//zzrK+vc/v2bce3yAME7rlPZ6en3Lt3TwIrd+x5Lu3aEuRkIRDyqIsEjawcp6AJot0AsFwWXJxfOD+qskNcJqguA660GDtX57g1rkS5eaaj0Ny9vuGbdd1fogbbvZ/epiGMUxekah2hdRPGNFgn7593YH8VkjuPGPnOMmNENVUbvRLkBo0apUiCZLkLZKxI1Hf5S/5cBLnDBfsR4NBmrSiKJQcHBxwcHAYOjxyTDkFwN6COooh+vy+S8EkcgvLG8SE8kbZ0Czg8Xr5RSgXeXZblbaArd2VFLbgN4qSMWxRCCPb76Y5twAmNRVy9epV+f8DnPvdZkiThxo0bvPzyy7K2KsXxyQnn5xccHOwTRTE3b95iMBzS1BGV67DzaKSMaWnxL4qlEP7dM5GlGXmWkyaSaLbJk+sM8ghKqCBYGuUkMC4lBT/K9kMFIb/6q7/Kt771rZXX/ubf/Ju8+OKL/IN/8A+4desWSZLwR3/0R/zGb/wGAG+88QZ3797l53/+53/sgwUoscwRO7PKCjJS6AgTgUkiVJZgE01pK0pTgjKOISxStySgegMSHWNtRGOklKK1mwRNI0GItS4Igci1qOooJU6kXdY0rYy5sZJlWO3ab1wnRWNqquWMRlnIc+IoIY01WRKTxLIoNnWDpiFSDWmScPXqVTY2NnjppZeYTGfcfe99Xn34Ck3dkGzvikBOHBHrCGsNUZq4coIcR1U3zOci1HV0JJ0XaazpJYIIpGlKnmbEWUbi0RYl51uWBZPZlN3dHW4/dZud3R2u3xT30F6/R1FIN0DjSjBZkpL1cqqypFwW2MaSpRlmOMBUFXVRYIz0o2slpSWtIpRKidIBaRORpj2iKMHaEpk/Kt5//z6nJ2dMZ1POLy5I05irN3cYrvXJs22uXY0EgdIZihxrB8CAyWTB+cW5kPxshcUwqOPAtMcIEVUhi3bT1EymYybTscv6NFpFaBVJiU556/E4mPwty4L5ckkv75FlKaWGpk5WSi6+zOL/LVlQWwcuypLFUurx8/ksLNTdmr1FoGutFL08DxNmWza5vOi0C0FZepGlJiwQeZ6jtXZ6BJ2MyQWNgnYloRTiNx+EXO5S8Juf5HWHKyOvW0fGFbKvUsljAYhfKNI0IU5i8I7Utm1tbQMQ2bE3DvMTqCcXWms4Pz/nS1/6Eu+/f5c7d94L+ijQuq6maSqeGRdjtrcTPv3pT/PMM8/wwgsvMBgMXR1eArbFQjLRN996m//yX/4L8+DdAzs7O1y9ejVA+3mec/36tdBVI0hmGwAJOuLsI9wCO5/POTo+5uzszJXFvNGbdGeF8l0UBTfmpOM7opQKTqjdLSAoSpALLFRNu2DoSNMYWUS8WJ+oeAYFPLeAx+H3FkFZfSu3cK06XKc4JlZtMIGFxjQrxxUCWStlD0GLVCgZFkVBWZcraI8fC1XVBrSiW+RFHGE5n3P37j0ePXrEbDbrjK1WuKtbikyShLW1NUajkSjsKvHRkUCnEsE2V9rxpZRW4G51POV57gKaoZjtdZAhY/zfxu67t9eQkod3L+7ydKwr4UZRxNNPP+3I6iM+8YlPsL6+zjPPPEuSJJyciGLq22+/zZe//BUGgz6/9mv/O7dv3w733SKt/Er5ikPq5px5MNjrnkOe5yikJdwTU42xbZKO512JOWndtEH5j7P9UEHI2tqaGBd1tsFgwPb2dnj9b/2tv8Vv/dZvsbW1xWg04u/+3b/Lz//8zz+RlPrDbhYEdYg0xiopyWiFlWIeRitpqrRCLDVirSsDx3staB1qk1K/0XhfEKXEaM5Y48ivypV3oAEJUny21s3a3O9W6y2hpCklGQ2R9t03OL8bR2x0JFqB3yXbWd9YZ29vj9lkynBt5ISMoHItm0a7v1UC1RpECjrS1mVhLdExdn4nXTg3KEAibVeNNWFAJUnKaH0kuhe9nCRNwgONbRcmcBmbJTxk4WHCTYa6q6YKSkUobWShVxFpkpHnA6zVbG7WKBRbm5siDZ0kMiHG2ulnOGO+phG5fdugaNDauofOUFWlmzSb0MLddlasKgd6WFR0KgwtWu7Epax0TolHhKuJ69aOvjVz8p/R8i7ahXR1IfKwslYqZCq+FdC/DzlS6EzwEmBc0rjpwPbdgKTNYp7MYu8GE5e/nvTUdQMHf04eAVtFR1TofGlCkN4NJFb34YOubpbY3dfq37XlGR+U+MVBpPBLzs7OODo6ErJ2UQQVSL9gt+qYStxQR2vs7uywt7cX2hu7WhQeCZlOpxweHjKdTld+Jy2/KZPJJKAgo9Eo3P+V9lh/Hp1z9PwZ4R00q/elc3/9a34BltJSu+8nldLCVVRdBdzVQ+iWCv1nfr/NX+8VMqcVpEWr1fH7g7Yu4iZcGlC6DaTD+ShWxka4prROuXMnyjebzfCts91n0H8F1M1pHwWBu1B2kPHWbR33iaaHlVo07/Hr0mpweDSve09aFAhYfX8ol662IHsn68FgwNbWluiPWOEZHR8fOT7PfnDZtp6b54F62+67e929IForG6AC/8nPad3n1xrX9NFOkHJ8P378AfwPUEz9p//0n6K15jd+4zdWxMp+IptS2CzD9Ps0QG3BaoXKM1QSU6Yxk6Zm2tQUTU3VNGifgWQp6aBPo1POq5qynGNIJbrTELtJsbRGRKsQJUCUogZcmREb1A+d8I97yAPpy2e8xkKi0bUiUZo00aSpJo0VSQRJBDGKyCps1VBVSyklZZLtvPTSS+zsXOHa1WsslyUX5xc8vH+fc6fSF7nFaTjoE8XSGgaKKE5I8wFAGFCxgkS3Ez9A47L0umlYLBdhYKZpyvbWFi+++CK7uztc2d1lOBxIZuRuQ5wkggZZGyTIRbgpYTwer+hUGKspy4ooUkSxIopzCUQQ6Hlj4wq3bj6L1pDEliSJuXHtOqO1EZPphLPzM6qmZFFMaWxDmubMZnNBVOwUrQy93pA0baibJdOZICGxM/YzVlwo20XcZSbguDhynFXZUBYNaQKKGJBM0BpIoh6D3ohhf8SwP2CQ91gWBfP5wi+VwhuIBdqVEknbLtndpByWYW1DUzeh9u6tuCUrtC4blQzYt0b6xcfL6XukxU+8Xvq5LMtAOPWj1peE2glOOb5JjDeWkyBiVQdAUJGWQwGExV34H60QmtYiViekvnmnNu+zXhugfX+8aZqEBRw00gimV4IBuVVeoK1tQfWlj4cPH/LWW2/y7rvv8hd/8WXu379PkiTs7OyEBQJEQqAsS0ajNV548UVu3brFz/38z/PCCy84X558ZRGcz+ecn5/x/vvv8+Uvf5mLi4vw2XmeB3TJK7D++q//OnmesbGxwfr6BnHsOzNYXQjc7DGdzZxg4ClFWdEYEwLOlRZbtxB0O3jiWJBQr8vSTQx8JiwcOKd5o6XUrN1ruMWsKApB3KJoRcjRhkSuDYLSRPxYQlnQPJl78v02X8Lx2kLtoqvo93skgwFVWbF0qGsURai4FUOzzjtGxtmUoiy5d/8+7777LsfH0uHjeS2eb+HJ82maMBj0WV8fiW/WQObJZVG6+9gSbrut4z7xaZraPXuqE6Tg7n8m/BKU8BRNS67WWnRlxAhPPKG8OqkXF/PXRvbbTQoUm5ubbGxsUBQFp6cnjMcTfv/3f59vfvNb4Xm/du0qcRyxMRpR1TVVXTul5ioci7Wtjk9VVcFWwhjD2toaWZqKB1hVBS6K/8LolcTGs4t+ApSQHz8I+dM//dOVn/M853d+53f4nd/5nR9310/cbKSxcRTYujbS2CSGJKHRmtJaKutbdC2RarP0OIpQOoJCbOatjsVgCmfO48AM6yNj5UsV0I2EgTZrk4TZoSPt6zKne7MfHAlVOcKqfJZWYi3T+GzWOYFqrdhY3yCKU05Pz9jZFfbzwaN9EQkzDQ2KBCmjeAaDn3R01PGSsRaNEfl42ujcq1R6syMvNKYdaWtzY5ONjU3yXuuu6euD4mnhHhhXaohcwKZUO4GJmZfUWo0xaBRKRw5mj1BEpEnuggjNcCBlD++mOZgOyHoZRbnk9FxTVgWRjl2ZoSGixigxxBLRqtrJrzeoSIUnRCvfZngJTXCIWNuuZjFdRrLVDikTI8MoikmiWNqnXf1YKxXEr7xmhyzaMjj8ZBKQEe3b8KQttywrx17v6jo4ZM5B8y0UrFcmpzYrW0VDJKBsg4nV7K1FaLotv09aQLokui6y0w1mW3Jim0V6YuplQl+3hBRQIe3Jn9EKEnIZoelmo11Sq5RNRP338PCQ4+MjTk9P2N7eCYuMP05RylywsbHB5tYm2zvb7O7urnRlhCzaGBpXVpvNphwfH3NxcRFKEV0Jb5DA7Pj4iPl8Tr/fDwjQ99sECVmsICGX70s3gIkjIdlmjkj+vVAQJRewg74oCUT89exck6ZZNb1rR+ATuEHR46qlP+ymZIIQz3LbIpEeFUviZCUL9/c4juKgwQISXCyLgtlMFtLJZMxsNsPa1rm6HbeeGBp19HYECbEuwFgpha48T5fRJlFbXkWpOkhIuDQBIw/788+EVycty1bvx79PRMk8Oi8IkA/667pmNptxfn7GvXv3eeutt4LQYFGIanOSiONwY9qOmEAO6hxLN1EEAg+qbBYrhNz2azU5UYGQ/uNvHyrvGAvMjeHCNFTWUjoo0NbSWpnWDVlds3SLNFqEmIbb21RJj6IqaTBQa7RRKN04BVVLUy5oAK0a+rlkbcZULsiIxFtGtaCwdkGKr1ujLQbHwKYGDEqJWZvoW1jiSP7OON5JpCMSrYhJscqgFVSFlF36/T55f8BHnnuOX5wvOTs7ZdDvc/DokfgejCfUdcV0JpFsHCfEURJKOoAwnI1BW4NGUKE0y9BaixtkWaKjiOFw6Mio19je3uK5557j5ZdeZn19xGhtREvGQtCDprUA9+Qyz1NIHFFPWUOttSv7QGMUCQlJlGFsSVUtqaqSw8Mx7737EGNK6mZO+v8j789idUuyq2B0RMRqv3Z/uz1tnpNdZVZmVbnKf9kFVWWuLcy1QJbgBYQEkp9AggcEfgAZgRAWMoInixcj82DB2/31gwHJGK7BxoCNy2W7XK4uq7LPc/J0++zua1cXEfdhxoyI9e2TWV2Kq5SXfeqc3Ptr1loRK2LOMcccI03w3LNn2N/bRdVUWG9WkEpiMCpRDkYoyxFUkkHJDEVWQogCWjdYLs/RNBuohAKdNCOdEAoQiPfTdZSDZqn184kfK2sVYBVgEsAQwSxLR0iURtcC5+dLLBYbdNqJasnQMtrpDlyEMkb4wM6tt5c27VZT8HF+cY7j40dYLOaXSJ8sI83tp4PBAFmakh+Rs16P4XS6ButY9bXrFCDhpzjbjLOuJAnBTf8p41n+5O6N93w+LRGDz8/PsVjM0baN/14iesbmeQJCJI7sWHoORSyyFH8unxst+KTsytLXr776Gn77t/83jo8fQWuNoigvdZDEC+iNG9fxYz/2Yzg6OsLOzo5HlLquo9ZcNYAQQN3UWC5X6DqNsiypldEp2sZcGeae+JbrpiHekUs0RFT6I6SMfkb8gzWqilxeOaDz527jgi/dsywqI/BrKDkI88y4n/cCCyF6c9FYsqSvNpXnPVCA0N+oYNk9lRyKy6IgVWLD7tLf+RGjNeg6aMvkaEIQeZM11hDqEZVLtQztynmeoW0l7ty5g1e/9Sq+8Y1vYD6fY7OpkOeREaMNfkXGGOzv7+Ho6AgHBwckkFaSCy75GQkkSUAX27bpKaRuJxPxc5flGaE4aeBU8bNJgQAlJ3mR+RIJkV7hWsuN96kRIkGShC4may3u3r2Lx48f4969e/jCF76A09NTfOUrX8Gjhw9xdOUIN2/exN7eLqRUaNoOxgKsLZLn5G/EJnsWBnW9QV1XEAIuGFNQCXUPNk2LuqqoycC5upOqtADrlCTWQDCR/7uaAU8+PnRByMZozI1GZ1wQYi0J7EiDXBsUWmOjjeNwSAwHQ+zNZlgahU3boLMdoBMIo6BgoBRxQDYNkSiLMkGeJ+i0RuWgMi1SWOkWBiEAYUn7AwxJWUC4IMQSg0TBwAoNKQ2kCEGIEJZ0CpQkcS6pQLLgFsZ0aOsaEMB4Z4ZiOEKW5xiOxiS3rg3u3tnHw/sP8O7dd7FcLvD45DGqzQZ5XiDPCoe+EFLk2z8tmfIppTAej5EkCdabCqt1RboirpX3ox99Ec8++yyeeuopvPjCC9TlomIegnVkJ1fmSTKkqfKQJ6ymdtY8g9UdKleeIvhSQCBFonJ0WqLrFOoaeHy8wNtvPcB6s8DZ2QMkicR6ucGVKwcwliyvy+EAz82ew2Q6gVJDSElaHOWggESOi4sG61WFpm0IAodwQUjiHD8TwMLZxRtodjjma7IWhH4oWJvA2pQCtpQN4QQuzldkUhh1EAjJGXMg4HEHCkPkhISzQB05eHadRtN2mM/nOD4+9iRWfj1v0jFxlMoxzhRRKRR5Du02QP4ugDP+GnVdoXOtw6EME3RGaLNjN2ferEINnAKoWOmzLyf+XkdVVbi4OMdisYgcfMN7QxCiwJoSXgVUoLcRx8EVX4eUlLXxhrVer/HGG2/gd3/3dz2RkET6kieWCIQQuHbtOj7/+R/BbLaD6XQKAOi61ukxZBgNShckkPdJ13V+swjy9nRo3TmYXnjSbNu1Pgjpl5RMlEXT87nZbDyJ2G5dO5tKxqhAzHPhNdFaKgtzCQYytM96RMUjIG7FMhZNTd4hxpWtub0XNvBF+B1SCN8dQ+f37cXwto8+0hTUTBlRIlv7DmmaUlBqiazKXTwkHSC9/8y7d+/ii1/8Iu7cuYO589WiIIRJrXDPG5VjBoMBjo6OsL9PKBmr4LK3Uihxtr5bafv6nhiEZCnKQYE0S9zPgg0ECWAah1Jkbq51aJrOCUGWPpAN3TQhgNa6w7vv3sPXv/41vPrqq/gP/+E/4PT0FE1do2s77O7uYm9vF7PZLoRUaDvt1w7Sq7EuCFGQSgCWWn+bpoKUQJYlSFJaBwSEdw82li1GpMuk4NejRGvICAH9fo8PVxBiLWpjsOo6dBZoLajDpG0hrMXEaGghXLsstZhZY6CbFlJJjIocrZXQtYDsBKEYhiLHzGpoa5AYQBnAWg1FeAqMdT4ADDvzCTnEnwaDJp6xAkSPJZdYGON4jtZnFUqRPog1xpmrOU8KExYB3Wmyz7YWWZpiUA5w7do1ZGmK8XCE4WCI5XLh6ngkuw5LbPnGRf5pmlAd3QUh8SI2SXOMJzsYjUa4+dRTGI3HuHnzKVy/fgN7u/uuQyA8zNKVB4y2fea0O1jgiElfrSJOBiyRael3AllLxKk0LQAYjEc72NnZR5plaNsKSgJCpug00HXU3itUh64T0FpBqQxJUoJcMQ1gScm2bcndl9pgRSDjOq0QgpzjLL/PiyA9Ebe4W0c6dgFBXTVYzBe4uLjA6ekZho4jk/H9jRQ0eePzLYueTa/c4ig8FEq23o3PRKWMNUyCJgGT6S5tPDEkDLjF5/LrQ3ARDMxorwrZXVhUnwzf9ksE/fZDusaQRVZV5a+rzzEJ3xPuT6x9ERR56auE/54QLAaNlbOzM5yfn+Ps7NQLLPVLVtYLQgkhsLe3hyRJcHBw4FoqM3CrK3+n8GmFhXZj1HXtJRJuQAuMH2e/SDsCtY3GkV8fByX90lZANBhh4e+JX9/XVgnlld5nPSH42j56vAcfmPZ/b4zxHBKe0zFnpjfnv4PNKJ43cUnOjW4vSPGIDIu8AVBSQncap45z9OgRkTPJDJK2ssBvgg9++XuzLMN4PHbqoqkjYoZOMyZ0ax2I9Hy/wxzV0DoE8kIIJG7cQ5s9IZm9udgLRq2TSzD+OSSNjsSfb9PUePSIynuvv/4aXnvtNTx48ADCBYOwVGbmgOtJY8fzE4F2S6h0LJ7orkNJWqvZsRkI5FltNGDgOSHGkqiE0yP/tuP+7Y4PVRBiAJw3DfJNBQ2BDtSt0nYdoBQGTYc9kUCrBDLNoAyg6wbVYoF8kmJndwdGKBTzGsuqQ6cN2nYNYy0SN+lU11D3glu0tQW0FdCWSRykTCekAPdPKx5ct9kCjmeiWwhNQjPQGjAaiQSKTCFTArqqYXSHMqVaXmcsrKaMqa5qGAOffRV5jj/5J/8kjNY4PzvD6eMTLJdLvPnGG1guFzg7Pcf5+QVWqzUeHj9yOiEueLLGO/ly7fvg8AhHV65gZ2eGF178KCbTKZ577nlcv34diUq8OBn5qhjIiLTVtC35xKQKuckAAUeUEyjKAlLSRisXCYzWWK3XgKWWZQiDLFOYTnchxBRP3XoB1hrM56cYDUfQpkOWl2jbBKtNhcVijbpRWC8lijxDno1R5PvQWmG5rKF1g9XSoK6oVps46fwsy5EkKfIsR5bl4JIQZV9ukZLSt1PSH2qj5s3QaOKznJ2d4+TkMYqiwCuvvIL1Zo3bt57ClaMjtG2HChW4K4Q0O5TPeujBhf8eJoQRKWyFxWLhNq/A+YgDGZa3HgxIWIm6t6jmG9fOhRTIkgSdQ054oeWFhs6DyzG0JFGnDy3EcZswwEFOEJgC4MsA8ffGzpzGaGw2a5yfn2M+n3u9Gt542JeC3pf56+OOD3pNCG6YTNuvvzPa1OLVV7+Fd955B6+++hpOTh5DCIHJZNLjBFB3ywpFUeBTn/oUnn76aXzsYx/DdDrxPigxH8DreRkiXVPXxRpNU7vyUgkAvTZsKjcl3u04L0pYIXzrPvt+6AjZ4GvkhT4QGYn/oNEhbnDlOdFXAFZhk4yCE2O/PUJBG13jdWqYmEwxjONKaQ3hNlYpJdIsc+Vc5UsOHNh+J4e15PvCQSiT3bmVl+8FlXDd3HPkeZETj+L8/ByvfOMbeHxygj/8wy/hy1/+MgDqdoqDmNCtF7gv4/EYN2/eJMmBcoAsy52eD11D17Ve+TV4xyhPPM2yzN2vEDwoVxodDgbU7usQTx8UqRCI8JhwEsItxkJKlAU5AmtNhNLT01P8xm/8Ou7du4cvf/nL+MY3vgHyeCES93rtlGHLAeLgnT4/OJ13HfnsZGkGmVLiy9fn9YLcOshE2fVmA+auSBAiKDzq2qI1Bo0xaO0HEYJ8yIIQay0aY1FpDSNkCEJAj0GtNVqtoS2QJCkyQw9TW22QFA2kde1I1iCF8URNWpcNXPUO0pLQlnYEwYR6OYhtKijAkJDOIbcv4kLZj1swLXv1OiIPAkmV+vcNYDSIj0AIiKNdwGqun5MrpkgSlHlOcu+KmOKj5RJ1VWG1WrqHJMdisUTTthQodB2M0RAuCIH7bADY3d3F4eEhZrMZDo+OvCvjZDIFl7gYleFDbF2rZ8UDPtr3Cyt7ERjjiKmkkEqmTsJnCkUxxGi8A2sNlqsZtG6R5wpJKqGaFkJkgEhBnSoJYEkfxGgBrS26zhI6YyysdXdaBHEhryPhrsDPJQCIsjupQlmCHy3+X6oRV1it1jg9IyTk6ODAjY8BO4nyBs4bA89ZbgEHaEHkXv24lNJ7j7vXjDJst44GVKCfKcOViBKVkJ5MdA4xGhE/T3HW9B5PHX10L2uHDxC4K4wPXsi8GmZvmQoBBY9RTDDdvp4nZdx8GGO8nkOstcLzL26x5ExvNpvh2tWrmM1mXrwpziCF4PntCL5O0ZIDiLizKM7q+WeMWpEexLbPEmeo/XvSL9fE9+pyGalPWvUpRfTf7jutQ9Djj7D9z+dsvHNy5hCi97kOuAXApbTL/kW9cySosXfNl44IvaPXBQSIrjGYFIZxD8gUB5WnZ2d4fExE4dVq5UqWgy1uUzj4vPM8d1yQ0j9PfCk8PgHhukwUZruHGEGgeSz9WhOjrDyftlGiGMW0htS4+Xu6jnRENpsNjo+Pce/ePddBde5UsHfdHG8iFNKNRlT+84Gkm28+XLA2QnqsH3taq2M/GXff/Ofovh8bgO2n+3s9PlRBiAGwsNRRQt0rNOk7Q//94PwCuHMXNs1w86lb6ITAncdneOMbX0c+mmL06DFUkkGkAwiVIk9LjFJyb7SKVDsgJawQ0BKoBaAh0KQZOqVghAtGANiOWtS0NtCd0yNx2VTqJMsVFFKbI5cCg6TAIMlRqBSZEMgcsAJhYdsWdWtdVJqQt4QVrgcZfjUwRsMK4z0eRsMRRsMhbZJN6xx3a5w5Z9DVakXCTs7hhuu6UiWYzWaY7e6hKErs7R0gzXKUxRCmIwSg7YiUJpWEEuQwrFvK9LPMibdJAa1b2vzceiwdKsK1/q5tsTEatiUy5sV8gU2VAKJDogSSbIjDK7exd3AV127egoWBcmTezabCarmCSlJMJlegVAmJPQg9g+0MdNtCa4tESchCoGk6bNoWQkhMxjsYjkbIshzrdeWQEHp4us6gbjUgJCY7Y9RNjaJIoJSFRYOm4WiQF3INYzVOTo7xG7/x69jd3cXjx8d46aMfxWQyxbWr15z0PRxSwIx/8oIQQqCuG6xWazx69BB/8AdfckSzd+meSencL4XrWmphfWkr8+2giZOYftJCHwh4wGg8hgW1AjK0GosuMQzNVuFVVXlp61DG0P49uWvL5OyO24Lp3IPeB18nkQQ3XjKdYOrQISAlSXqPx2NvCcCfHQcu25tmfO1aa5yfn+Phw0fe/0JKiSwjaf3lcoWq2qAoSty6dYjd3Rk++9k/iU//Xz+IyWSK3d0ZiEyq0bYhO4eQaDVl4JtNRbyT1RrVZuNE0uA7Ffi8+LqUItlzdptm9Vxu76TXWB8cEYG5dRwi7buaKLg2aFsKfCigDOielMo/8xak62MtHMHSrY1+k+eAiTdY+jmN/xIXFwt0nUGaZC4o6/N+0jTDaDTGaDRGmmShfKkSABpCKLCq6LffkcKmybo91s1bAA4NSEm5uSJBuqIcQApBJnhn7+Ltt9/Bf/+N38S9e/fwzp27bgxCUMxoDqmSEjl8Op0iTVM888wzePnll7Gzs+NbzLl1VcpYUXft2rlrInQmkty2O1I67XTr0BvreBcFzeM8c2V7eCTiSV0k/Bx2XYfT83NIIV3rc4KTkxPcuXMHd+/ewZe//GW88847qOsa+/v77hlMweWa5XJBDuGKtJR4TaaueiqYsGcOP6/akWBJn6amcrcgJKltGuhOo3EIX5qmsLpD1zawukPbabSaknX2v/r+GSEfsiDEAqhgIS0/XvQ/nSWy59lqDTw+wWBnhms3b0OkKd66/xCP7t5BOjjDYLlGmhXY2T1EORgiHYwxTiUEFCBJsdFIAysEOiGQSgEjJXQuoFNiiLSgSd/ajiTJTQfTdZRJOC2KRAkkAkikRCYTZEoiUylylSETCf3OmdpBWJiOVAnhsl8h3QPtTKgIWKEanHB6FJnbtPZmMw/T0sTWWFdE8Do7OyNlPFCbrlISg8EQaZpiMBxiMBxR6SAp3Aai0bUGurPoGg0IIBOK2l2tgXFdMQnrbkiCUvkhEwiOsxyICACNVNCCFuG202g7hSSxSFOJJC0w3cmRpAJZ7txpTQNrOzR1i/W6hjUCWqeAlZCYAGZEXB69gdUGUiauXtzQBq4kinKA8XjqHjqnKMnkSENW1hAC5aDEYFQizRSksrCgc6Rar/NrEbShLJZzfOUrX8VwOMBkOkFe5Lh+7TquXb0WIS/EMGcFVuYdrNcbrFYkevW1r30Vjx49wsnJCd23CL7tuo6IrjYyLcvSyMDuvYIQ6zp3LMqygLXMCaKsJjZCk1JC69qXhbgTgImCQQeByWmJD144e+IAhaXtOYvuOio31XXtyy0x6Y95EXmee3Igz10A+PYdFxyQGyyXfWVLAE6EKoO1SzRNi+FwhMPDAxwdHeHFj3wEn/j4x/2ndNqg61bem4NRM76XXK6o6wptU6Nz7YzbZavQCRE4V/HvKAgJragxshP0KDhD7dfzrbV+4+cAhEtorAND5ZF+9s4kZ34yg/AWbdRaG2w2FdarNYwO4xxWVvqjFKEM1HGUOK4d/bGu3CTcQnwJfbl0xG3XbjQtPLGbnoPUB2NCCJQlKcTO5wucnJ7h3Xv38LWvfR137tzBZrP2QTMTr4WgoIKJxmlK5pPD4RBXrlzBzZs3XWAcWsbpuwMy1zSkaNrpDipxG7vR0EZ4mXtrmHAtfMk0SRKvFmu2Wlr5O6h0KiGVQtt2aOoNJU2uTX25XOLdd9/FO+/cwVtvvYU7d+5gZ2fmCdQAfPBa1xWRoCUrFjundo4JbehGsyY8N63jorVMoAc8EZj9bHj9MU4d1WhNJWCH9ksh8MHY133IghCA/FxqUCTm622SFrqqbXF6fg6dkINgrhSuHB7CQGDTalxsKtRNg4W1qOc51lmBZUYmSyLNSEMkTYA0gVESXZaSwuqghM0yQCVASszszEoXEACp85+BIpO2PEmQKgXRdVDaIhMWwzzFZFAgTxVs18FIC2gNYZzvgybiK3M9lUpogOMyjyNASilhI9t6AB4u1i5Q4Og2zVIIu4WEuEWE+CJAixbEjKYgBKByFn2+W7xgqXwkSKyMvpY8b+gwjMj6TTV3WbDRGkmaomk2qGvytOnc9WprIJVBpwU642qtrkfe2NSxthUSNYIQCayWWMxrdJ1B11Jmpw0pJxorUDo3yzwj4qHtyIwJgtU/aAGG6CClwGQyhu46TKZjjMcjYsa3jYMcNWCJNDYYlA75IW2H1179FqpqjevXrmOzWmMwGGI0GiHPM1ROkh0IhN2Tk1OcnZ3hwYP7eP3113FxceFVPbc7QfhgVICh2hgyftLBG0zIVkPgwJs/24NrR+IFiPuwWq1QlgOSFQcpYBrR77AIpMIgC84/5y6GxWKBs7NzJ4J0mSDJ51iWJSaTieeucADHXI4+oTUEXnFZg2vrUir/OSS93YBbfXkzNsZgvVljPl9AJQnSLHX8HennuhChiycOMshfKYFSZut6rB9jT4JWfT2XQGxk+W7lIX0+/9hIL96kefx5LNmrhDkvHHBcPkJZhY+Y7LqtE9EvK4Vx4sCKtTWY7Gyt9ecdup36ZaL3OxjV4u/iAJQCB7ovHOjxunb37l380R/9Ed555x3/7FiLqOTaL3eRUFeHPM9wcEBI2P7eHsajkQ8S6bN1FCT274vuOkq8+JyN9SWLXkkmJm37BoZwJ3whNMogBIhoSwio9GMcE2FZndkY6rrin1troRLysypyklwvy7JX0uQx9Vo2Pvmi7pe6rv3vE/f8tZLR9AqdQ7jdB8Ia26MXxNf1/R4fqiDEggIQhoNSV8vPM4rSl3WN4+U91AJ4WhPx57nnnsMzz38Eb7/zDr7wxd9HVW2wfvwQgKDOWE26EklRkhjPoIQqc4gshRwOKSgZDoA8R1oOUI6nlB0UI6QqhckEiaVJCSQ0oTKVIJEKprHQrUUugd1hicPpBKMshW1bMrXriLhqOhNNdse2h4JMXE3AISE+mnVBgRQScA8rt4XyNJFSYmdnCpVIxivhi8XWgkV6NAzQUh942xh0HcG/eU5tilrXnoBmoT0RK0kUmraiDhUEvxHhkJw0zzAaj8jzJknRdS0uzuE6eYCmMdBGAIIk2IUgzq+UQJYSaU3JnLwykgzT0SGSJMfDe8d49PCErlFR18umIlhxMBxiZ7aLvCgwGI6QFyVMZVE1NdVl3eKuNZHdpJQ4OjpEWRS4cnSAg8M9LJcLnJ41vnMJALI8R54PoXWHzWaNql7jt377t9C2La5fu46vffJrGI/GuHbtOsbjMTZORpoClgpd1+HBg4c4Pj7GarXCw4cP0LatL7NwxkH8pMDU58WaFyMgBJvxIrh9BFnqEHDEpnWs1sgbynK5xNnZmVugSbVUKglpY5QD/nv9fLCBSLtcLtE0DY6PSc8gSGhvowbWQeQTHB4eYGdnx4s3xa+JSZxxzBX/nkmEaZp4w0wub2ht/KJOm6bG2fkFHjx6hMFggMlk4hb1BEnCAUO4l10XsnUhBRJH8o3VankMkoSIxSwFzogF8yh4k01TgK0N6JxaXwoLaGawGODPT9OMNpyiRFkOkOeFOw93fu+x78dzI+Zy8FoRGyiGzqww1hQMUOksDhYDuqMjonH6xLn4XkcIGLicRMGw1muHLBCZnHlTX/nKV/Dv/t2/w3w+x/3791HXNTlaF0UvOOdSIXWe1RiPx3jmmWdw8+ZN3L59G/t7u9DGYO30UbgURiVK4qxxuYKEBDsACkYbGOG4Ea6jiMUEpfsbgA8oRXT/bX8C+98RyTjzgR4jn0Fanv5u2853AA0GpbtnREAfjoaYTqdkO+Da0rk8yIgjB7WNC0CWywVWqyUhIFlGf4oCTdNiU22ozNPW4G5CMlOkIMT3kr0XJPs9HB+qIIQPC3a5tVCwBLMrCWnoj7EGq9USMk2QD8fIygHKosBsOkaVp9CdQx86C9s4+FK5VNl2sJ2AFQamJqddKy1gGgir0UoBo1Kk2gIqdUJmtHuKhCB4naSQKgG6FspqJBAo0gSDMkORJlDC1dSUAjmeUNYJAESuhG8tNcb439G1O1TEWlg4QqGLcn0bsaDMwEvIW1fTscJ7nfj5Y8NC3+c6h4CHPpdJYiHS9g+Xrz+H93P2CAiHnJCqqlRsAkWtsLTykRmW0QbWAJ2wsAawikjAxPOTbjNOPBRsDNUn+fuU6+rJIkVJDsgAoJ+kOfXSRCHNEpSDEqPR0Dkt0ybLm/92dgyQ0NRms8ZiscDJ4xNUmwpCSCwWC1RV5WTLOy9CdHJy4ozKqqDfAoeU+PQzjAffZ7o28eQFzV97v+7MGx+LnT1JwZQPY8jYcblcOZdkRGS68Lr4nMLnwKFDticXzy26/vouZcfCB0qkU8KQd//atjdZyp7758StlJfvT/DwYej6+Pgx7t69i9FohPV67WvsMVrBn9M0DRaLpXNTJdKricos/XvASEifZCtEGLttAi7de9tDQvp/ovGM2q65dPV+Gz5/b/9nIX8NrajsqOyfokvjTJtlX7EXwFaL53ueyhOPeA77QG/r2hkpovbrjSNnnvnglt8TWnD7n68UcZkGgxKzGaEg3EHTZzKE7+XTCkhcHyGKx1NsnXPgRvX/bF9vfzy2UDWP5riSj/Wrfe++bCOkHPzKLT7PNmoqAN8dw0KC22u+MURWDs+i+wwbNGPc2fr//X6PD18Q4vavzhpUXYsEFkUqIbMUk9EQszSHthZ/+Pu/C5EkePYjL+DKjZs42Bnhz/+5/zeEEGjrFkYbNFWDZtOgbTvMl0s0bYez9RIX6zVq02G+OCFDvCWZ5m2ExEIoCKGgkhJSJLBpDmQFICRJkkuJ8WCIQVGizFLMyhLjZIgbu0M8f+MIR5MMu+OC/FxsRnLKHATwWFuSirfWdRt0Lbn6unZZaw1MpykQ8wQ5OHREOFEaga5tYDSbsYWFhh4gN2GFgLBcjxegLg+LrqthYdF11MqVphJZTi6uy+US1hLHRCrX9eM0RYw1sB0RsrI0AxKLRCYwrobddXSBKnFGfkpAKVIdbZoK1ho0VeuCgBZK1sjzFnlSwRYS5WCAq9evYr1e4+HDR2i7DuVghPG0wGg0xu7uHrWyWjK2EhIoBwOqhXYttLFQCUn4K5UgcS6uN2/cwMsvv4xXvvkK3njjDVhrsbu75zxxOi/8laaZg++ly8IE3n77bQgh8bWvfd0vELyAcwcGa4IIITEejyP43bW3uuwqoAzGfxZvAoD1RDNebDigo0WUyllZRuWyHTZBXK1xenriURQOglhc65133kGWpRiNhnjhhRfo3JSEspEQnTviDFapBHle+Lbj+XyOk5MTPHr0KOKTMKRsontCrYbD4Qh5XvjNmwSeeGPqZ+a8ATBSQIiW9lk9B3UxP4Xr+48fH+P8/Az/9//9/0FRFNjZ2cHBAbndslpwnmeO+KncmGv84R9+GW+88QYuLi4cAmF8d5N3XZbSe/vkro00Li0xCsLtnlS3Z7djMserqgpCCMefCT4+VOYQKHJyrx2NRhiNRt6zhjdGum7eHvoboF823SZG40/BInGCSBE2BBjM+THu51TqIkVQQmrIHbn1QSjNv+9iCe/N3RBcDofU4UIBbYuTkxP8yq/8Ct544w1885vfxN27d90zGFACHvMkoaCON9fpdIrZbIYbN27gs5/9LJ599lns7EyxWm8YWPYbOAfsHLQSytaAW6bZWkCpxCNixr2OAoDE8fQSZLlrNbdhm97uPBNCOANLQsOEkOh0AgigqtaYzy+wWMxR1Ru0bePHnxE94m0EV2GeF4SmJBCi8QGI1i0AQefmJPHPzk5wcvoYq9XSies1MIYkHRqPjnV+cnHJSlgLBTJe5Wv7II4PZRAiBPmtNK5GZyUgEomsyFEORliuVnh07y46Y7C3v4/dvV3sjId47pnbxL6uaBGu1xU2K2IJHz8+waaqYE8Nmq6CbSxsW5FSX2thJABNBFg6iQKAAvKS/ggJSJetj8cQgyGSsoRMBFKbYZwn2BmVGBUKWSKRSIEMil1KfCRutAs+OiZnSWhrIKwhXxMpoDXoumFdaSZE5U4XE0CAz7kMExZ35+Ar4MsUAHtc0UJkrFMXdXVTCwnWM+C2xSxLkYrEta65VciERUW5wERAwirjetxLl2EQT4Nq5USGtLZxn0+CaEKQ7LG1ROJKEzKmS9KMSFIOdkwS5VVFuTba6g6665CkCVIHITcddZ2EzJQWZqUkJtMJKSneGfrNmsm1dR3s0jnYyjLr+C4GFxdk2rdYzD0hkzNHbgfkg5CaMsrgttr1EEP9IQsKWhxPWNDY6saGayObcNro2ZuGs9eYc9F1GhcXF3j8+LGTzLbB/Exc9ieJz4tN+7gtN7YJ5001aHYEHgD9LiAhl7PCvq5CP7uMdRfCdXBgFGd+TChcr9ew1uLdd99F0zSYzXZx5coV5HmGnZ0dLx1PAmYUjBljcOfOHTx48MCreG5D/vG9jgMu3szjbJU37DhAiNuZY05IOAjJY0SL+Tx0Lk8m8MbPeB9xCOgKl1M4mAht5ojGOwSN227EjKYQSvLdcUH649mfx/w9tHlusFqt8K1vfYskyh89wmKxcPdigjRN/L2iOUUu1nzfiqLA7u4eDg4Ocf36ddy8eRPWGiecCB/oSdkXgAv3J3IXFiwpQK3eWikId59iFI1lCehzOxgjQvk7RiEF8Uis4XnkSh7WoNOdUzStwzxz5NfAIeq7H/Pc8G3HEWLNwTkHXdYYbKoKm80GjSekaz/mWmto507sUY8IFZJC+EaJDyoK+XAFIYI2SqWoTRcGsMKgaRvKAMsCSaqQ5SlGowGarsPp8UO0dYX70ykePnhAtbS8oM4HSy62xloI06FIBK4e7GJvf0oEWGFghEUDCy1I3GezrtBpg82qQ9sadFagtUR2rOsGpiVRrvVqgU4Azd03cZxlkBeP8AcHe9gb5zjaGSBPE8zGIxRp6lrgRkhcZsnCR1mae3trBVLcpKXN8QXgyjMWTlmwD7fzhKQoV0e/E2TMpwFAuz/cyke3OtSjFQCS/DXONyXLMlibEAri69duiITTTxEhyxeSvjfPC4zHExfJ1+6cNdpWQxsLIajUkqcKNjG+1pqoBJt1hbbRLlihcshgOEBZDjCZTjEcUVYNKXz2od0DLDVt+Kz+yJusMQa1U/a8des2xiPic/zRV/4ImzXJaW82VRSwsHlfCEakkLBCuk11N1q4+tlhzOXgYCCIm/UtzOONiNt0OcuJO038Q4F4AxZ+4yeBtMxvoLzx8Gewx8rdu3cwn1/g+vXrOD4+dq62BfI88d/FdWZrXUu0lIQ4GdLreOWVV1xr4V1orXt1bWo/1Q7douxzOt3B4eEhRqORDyhYQGk7i9++J4EXYjwSGF+zEAJt26DrTHTe6GW7y+US6zWVz4QbPy7NZBndr5OTU6xWKzfeVDJsmzYQNnNy4W67Dths8Oqr38L/+B//Azs7O7h16ymUZYm9vT1npOdtJj0yxEHItlZMDOPzeTPCwmUfrUNAGEonwUWX/w6BKc1fRo2YfEnKtpcDmid129A5wXNyvMaODPyU7+SISz1h7hNaWFU13nrrTXz5y1/Gw4cP8dprr+HRo0do2waj0cgHfTyH+dnSuoG18OTd27dv44d/+DO4cuXIuQ4nHv1zZwEgdESFpMD44Cw2cePXd27MlFJkHlcUKMvA7eJkJXSaRQG8u3a1dS94fiUqgdWEtNV17fkjsOgFHbwncEmTg1MfRNkgEUBlGlqzOt2hczYDWlP3XFkWTjiQEsz5Yo7Ts1MoQyKc8XmDy1E8EfDBxCEfriAEgIqCECGoJ6NqKmjTYWwnSDOJAhkmkxHqusHjB/fx9uuvIc1zFKMxsizHlcNDjEcjDIsBpsMRkjTDcDRGkaY42N3HaGeKpMhQzsYQSmGDDq01WKxWODm/QF01ePzwDOtVjY1HUxqcrWqavKs5Gq2xWK/x8PQxrNH4xhf/J0SisDsZ4WhvimFZ4KkbVzEaDnH96nVcvXINRVlgd3cXeVbg8PAI0+nUC+xIKSFduxjVMcI9sQCatvORs/GLB72obWlDpkkdVBWB7cWnn9FQdkIRNrWo0cTO85y4AIaiaCCu38uAsIARFoL1i3KANM3QdS1Wq6WT+F6jaVyAhARSAkmS+4BBKQlrgNV6A6NXnsWeJCkFbkmKyc4OhsMhhOtOsjYoigopIDo+D8KImETGCw4APPvcc/joiy/i/OICv/Vbv4WTkxPcu38fq9UK4zHBnSLilyjlkCQFQFFGROS9LIJCNZmTubJH49QieUHhsghnt3QfLwchoVSQuDG1QE9PU/jNQanQhsteH1m29t/LXA2AuqeMMXjzzTehtcYzzzyDBw8eYDqd4tq16yiKwn8Dy7EDFoOiQJaltCC3GsvlEn/0R3+Er33ta3j77behddcja3IQwmqySZJid5fQiMlk4seCFFbbnm7Ik5Y5a0OWFwchfM0UYAbSJOtQKJX48ZnP5zBGY7Va+8/g+89ZX57TPc9cO7G1FrUhTk9ekHKlNRZVXaFtGnz961/HfL7A4eEhfuAHfgCz2Qwf+9jLvvzGzyM/WzQ/KlemQ1Rq4iA5eOUU7p7HZFtjaMzj5OMyysABCZfsAjGVS4T8DPM84rkS80X4vfHvmNhLpM6+rP17HTE6Q3Od5om1Fuv1BlVV4RvfeAW//Mu/jJOTU7z++muYz+cYjcaYTCa9gIi4E8bNzRpSCozHExRFgeeeex5/+k//aUynU+zv7yHLUrRtH+kBAp+Hz4c/j5GIWBHWIijlFnmBYlSgLCkRYr4JPV/9sfbz6gn3g2w7SPGWEFtC7jZOtTQuEVmHZpNzt4JNEmSR4rCQwiWlHCSSbo5ySFyrW7RdELFkcmueZ26NNh4VnRQjjIshpTjWegSZ5SOs/mNajhEQpJevJJR20ugiIlo5VTchgMLJCy8XCy9BrNsOLQTWyyWs1tB1A9u0SJIETV1RG6lusKnXSPIM+WYBkUh0CtAS2NQN2s0autXIlADyFLmUGGU5mqZFISW6lsoApjPQgwK1srBaA4mAlQKDgkStCL5fom0aSCjUVYMsz/D48QmyLMPJ6Skm7oEajUZQiUJR5FBJgiRLkGSpX3R5c+VMmCFv/pOoBDZNifvESEhMEwEidC1Qj/xmGGXDUrhGGwjfskZvc2GHpDECAGFDe6TnAyQJ4FCRJOmCAl90QqwoKxi2FBbKAFKS/4wFkCYpBoMBlHKuou5BY/iTUQt+IIUIHQKyt5AZHy4JKTGdTHD79m2MRiOsViuwpDUjCHSpoY2U5mTIXIPGQ+ge4ECDiHIDHBwcQEqJhw8fYj6f+8yYP4O/w9ehk7Qnj95flPoEuLjUkuc5ptOpb+9j+DiUhwIHwBjyYnn99dd95kh8iawHBVtrUQlaoJerFU7PzvHgwQNvdc9OszH64u+VED6oKkuSOI+7YuKSRB8NCeRODt4YQeB7HTZAdtplYSf2zwjBWUAPXJBre7kprKX77JEJBJ2VOBPffk6WyyUePXoIrTVmsxkWiwVu3brlrz08TtbX2XsZruj7+DACFyMOYORzq1U0/ptLMowY9RG2PvGUApi4FMTzj4m04bv5GkILqegFHjQ+kUrnE3apHkrrvo87yN59912cnp7izp07ODs78+7SvtwRnYN7zHv3QCmFg4N9zGa7HmXj8iyjSrZ3Uv3SVz+43W49Rr+0IgDluFoqmrNbIF584XjiDXGfy2tQ/Ayb6PV8r+KP8OXAiNPCl8V8M3+f/YnFujb0jCilAql16xR95cWGOfNdwV7fwfHhCkIEUKQJRlkGdB1q28GCyDfWaB/ZqyTBwcE+jLXYbNZYLpdQSiKR5Ody/OA+rDHIVIJcJY7MSa2lMk8hsxQiURB5Apko5JMB0jJHmuYoyiHSNMPuzgH2pgOMB2NMR1NSGa0IqjUdtXG1TY3Nch7YzsagqlZYr+ZomwbHjx6haRp8bfN11Jvab7pSCoyGE5RFibzIMR6PkeU5Dg4PUA4GGE/G2JntoCxLXL16FUVZYDwek39BnlP7oaLyjVKK2o3loHcvSWdDw3dj+L/7ixrXR3VH5EwBwOiIqe3IsEolgBRIpKvrRnAukakMspTKAwAwGA5hrcF6tUS1WVMGoh0hBo4bwX4aAJIi8R4LDH1mGbWfdYak4fl8AXKatUqhbRusVxuoJMFwOCQOgpSkgxGZBDYJIQTPPvss/upf/at48OAB/p9/+/+Qpsf5BS4uLqi9dUDkOTbxIyM78pthtKNmd1JjwHbgN2/exLVr13Hjxg18/kc+jzRJ8Cu/8iv40pe+RKJFTfAhAVjwLUXpxnYyGYPdSxmVsNb6WjBvxhwgASTN//LLH8Nw+BZ53qzXTiRsFAVIwcX0q1/9Kk5PT3F4eIgf/dEfxeHhEQ4PD7G3t+c3ZAA4dQjO66+9ht/7/d/H48eP8aUvfQkPHz70c1Jr7UXEWIchSRJMJhPMZru4evUKbt68gclkgtCqmW5teNvaGXSPl8slLi4ufHsr3fPKQeQUlBNZdNDzeOGNkw9rqbWUxzEEFszZ6PwmRwqe8PfbWusRx8T997179/D6629gMBjglVe+gb29fVy7dhU3b97wG3pAEjrXKUV1ed7YGa2iTDXpeQcFIa/Ou65ucxnoYDXj0KrJr+PAgzZbSt7oviTuuugR5O8tSyLdssAXlbxSCDGAtdYjawzrd12Lrmt8MNLnVQgfTKcpaSmtVis8ePgI5xcX+E//6T/hy1/+Mo6Pj/H22295FdzxeNz7/oDwtj4QlVJgMBji85//Ebz88su4desWDg8PXJlCeh5F2Eu4XBr4L9ytxN1txhikWYZkS5zOuvteFiXKQYnEXROXlwAB4zSdBKMiNnS6xAGjtRZWCL/3MzrbdZ0XCOOggu4nXwd9bppSMlYWhZcskFIhSbf1aojUDcCJKWpkWYrhcIAiL5ElCVKVUEAjlE+sYElp2jhtJ6O1K95v4+bf+/GhCkIApw8iJRIhKSu3RJwxIrQXSaWQ5RmoPp6GXm6ANpy6IplzKdG6dlbPsEgUbCKp5JGRst1gNkY+KFCUQ0wmLYqiBEY7SHKDMk0wKQvACpiM2gVtx10IDTZlRkGI7mCNwWKRwJrWZVcEQc8v5phfzIkjoWnSlTkZLOV5jtGYmM+L5QLD0QiT6RTzxQLD4dCXATonrsNW42mawriFl8h/CiH7EJ5bQw+VewRMzDXgbFF4wiSshRUgBCTK6qxb2Lm1UwoJ7TOLUMMHWG0SECKh7pu29Ru65Bosc16MgdAkssaLFy3IdN1JmlL20DRkjmfhH3RfuwQ92GQ9HXgy/ohQHqM1hsMhbt26hSzLsL+/j8ePT1BXNS4uLvzr+DODAiZcMEzZMhthcS2ZCKoD8uk5PMTTTz+NJEmwM5shy3JfY+fMixcYVrFkfoW/3xEhM17QOOPmc+ROkPF47NEPznBj5IEXq/l87gmm9+/fpw02UdHGQegGl00ePnqEt956y7vZrtdrFEXujfoYSeJSDPGCSFadScSxyd42MZPPj3/H953JnLFuSRyAxTwbvqf0d9SuDQ5CSAqfs22+R4BF0wgE35jQDbNdfuDPr6oKFxfnvgTXtp1vKY0TyBCYXdZ84fGNx0cp2QugGAEICAsjGP1SRzwnQhkCl/7uIyHYmht9JISvl6X/jWn9OXEpKawdPBYBQeT5Jh1q0OnOCdyd4c6dO3jttddIKn+9BgCUZXmpPTi+Pj7XNCV07fDwEE899RT29/e83QBff3wwWtT/rD6K6ZGQCIH0YwVCQnhc4kCr/0UB/YlRhu3ziX8eo5n98w0IUPh5EMqLkRAWUHPLfTS28dyRDgmJEGKEPSI6qTBf+pfxgRwfqiBECIFBmmKaF7C2xqpp0VlLsu0A1qs1Tk9PMRgOMRxNqIWwyDF05DcpCRIr8gxZopDLBIVb3I11GvtKwEjQxppSMNJuVmjqNdYXF7g4PkaiUhy/cw9ZmmNYjjAajKFEglxmULxQSYkkTZAPMgeZEdKSpwmuXbkCaw1uXL8Gqw0FRI7w1rSN96QxOpAJudyyXC5xdn6GV199FUpJDEqSCx4MhyjKEkWRe2+EcjBAlqYYDknQJstS7MxmBNNPdjCd7viFRggSf2M3ziShNk9nag9trHe79MCeZdiVOBgAfGYaaso8drxRd444GjwNlEqRJgKDUgKCHV+thxpjhomUitrjug51S2Q07TYe4dqk4yNJEgwU1Wv9oh8FWyyKRChV5TMvIQT+7J/9s/j0pz+Nb3zjG/jG17/hhMYekjoo6GFs2xadqwOzgyaLZxVFjsPDQwwGA7z44ot47rnncHh0hGtXrwEAbly/gVu3buHRo0c4OzuD1p1HA7iUMh6PwSWI2OCLuwiAkAFzNk+cHYmDgwM3HjWm06lrLW2xWMz9GEsnPpdlma95n56e4rd+67cwHA6d2uRuNJ7UVqi1waNHD/Hmm295rstwNAQAr5ZKcC+8guxwOMTt27dxdHSEvb19x3VSDi0KZcQY+o2DC/47jF3hymZLj0IxV4HhaOaGAAJ5HnUQiBDoCef63LaNWyeUz5KZdEkcIFfK3FqTuA17PJ74rqTZbIa9vT0MBkMXQMYdPYEYyoJhjfN+SpLUkyg3m8qXkpKEurxYyG+7dMPn4p7M6Lnrb5DMTyKF25jzEZ5puu+d915hB9k+mtLX0SBkR0SIk/TKtUqlXjSLA7azs3OsVgu8884d/OZv/g8cP36MV155BWdnZ5BSYjKZ+vnAc5zRRQpAGWEBrl27jk9+8pPY39/Hpz75A3jm6duO4E9rRyCjsoJoP3jn62GVVf5jWDhSXA4yuBSe50FJ1q+JW7u0fw8jHi7Bgg3dNRDEb2Tia9uSLMN24BInIHAdjtKJdn4nqIQxJNtOcy2hQI29iNruifOJXZkFABm16H5Qx4cqCJEQKJMU4yxD02mkFhAW0A76qjYVaS24TTFJBdIsQzEoPS8E1iLJMsAYlGmKgSOqad0Sq1hYdMIASgCJhIHFst6gbhvoVqNtWlBrSQJYgSzNkSUFMpViUoyRqtR3JIwmIxxePUSapcjLHGmaYDweYbY7i2ruKRKZQEnliWpaaywXK28l/vjxYzRNg7P5OTabDR4dH+P+/fskMV5tYIxGkmVIXLljMpm4VsMR8jzHbDbD1atXMRgMcPPmTYzHY9y6ddttEon3N5E5EUI565VOlp6tbBgwsT1mPm1OldsA4iyVNw7SF1AADLRb+HjjkqBW3jRNUJR5lM0aR6wkTwPdUTmrYea61qhrGm/hOnGEtNgW7FFJgiyhMY6DI2MMkjTxhLL1eo22IRXT4XCIwXCIP/UjfwpN2+Lg4BBpkuLRo0fO2Krxn991Gq2D+wM5coLpdIrJZIwXXngRs9kOXnrpJbzwwgsYjyc4PDxE13U4OjrC9evXUdeVR094oc+yDNPp1BMiyX2YOpUAUunkTNYYthaXrkxFDrG7u7tQSuHs7MzPhcq152V5jpETOMryHADQOrGx+XyOP/iDL8Fai52dHUwmE3Rd5yFq3nwYNVFKYbqzg8FgAN1prNcbMP9DSunfmyQJbty4gStXrmDmyomcdTIHJs5a40yXj5gLw2MlpfJzjuWo+YgX1K4rPXHVZ5AJ1cO10Wibxp93CEakQw2Vx585I6QjeI4Mh0PqmChJIGs2m7kW7UCy1brfIsslZIbgASLQWlv7MhKNd0J6MSqBSsKGE6MhgVfCFIQ+p4CDkG0k6UkICo0LnU/sXcSviQmx/BwwGrJtQ0Aqyzk4IDDG4GI+x4MH9/HKN7+J3/jvv4Hj42OcnpIY2Wg0wnQ6hRDClau0v19d12G1onnIpMqjo0P8yI/8CI6OjvDRj34UV44O0XYajdtU+TqDR1EI3uLSVJ/HRW2qMX+stxdJFgnb6lozAQGOpgjdfxt4IfzsSiEdh44CFB2VY/z4RQhMeP76XJw+7+O9D8uf37ZQUcLiFbf9d23PiSBWJqKOvA/i+FAFIQAZqg1kirVsUEqFBoYiSBsaRqwhHoJUGipJUQ6G6JoGVUWMYyuoZEAZOd1wIgJRWccKAwsBKLrVSimkSJGoBGmSwVoBqyXIUE3RoFjS9hCmg4SA1QZLAEYGnX+VSAyHA2qBUomr8yrkaYE8y6n252Sh26bz5KiiKJBmKbKygLEGk+kUu3t7MLpD2ziFTwAWLJAUrKG5jn5ycoLFYuHlwk9OTvD2O+8QYuJaNcuiQO7aQQeDEipJMBoWyFIS6UkzipqLvOiRxeLsB3AbpKFAkBZ1B+dKJosK9xq3CFpCWbhLgA9yN3WETU2QdshSSDZZAWBPDks45NaM6RP9enA/hK+ZK6Ug8+BuGZde9vb28MILL+Dw8BBKkckUt9G1bYtqTT4xjGKMxyPs7OxgOBzh2WefwWQywdHRESaTCYqi9A/63t4ubt26heVygbIsQbXkICYWI00xRB4vcH1olha7pmkhpXZloBLT6RTXr1+HtRZ37971EtBMSPNdVdGGHW8ksSgY8xC4tOHVaQ3xhqyFz+zi81aKRK+OjohnkmV5lIUSwZxLUfGix9fHY5ckifeduX37NqSUGI2GGI9H/p5xwBl3gcSbENfWGfnpug5dFARwUERdOql/pmhtcSZe/saHMeKggoPnsiwQSMf9wIpnICMk/BnhuQ3dH4EMq8Lzwcj7VgCyXc5iBDhGIejetP48wnvDMxO4SYTKxToUfB08LvwZPF68psYkXnp2W+/78vrrr+G1117DW2+9hfl87lFI5nvxc8nfEc8/TpCeeuomjo6O8PzzH8GVK0eYzcjmvq5rdJpMKkN5K8yj7VImXw8HXkxMBezle+v+hCAk8JjI7j6UuPr3xV66d5w49II7x+PpOuKq0RTpjyu9332+Q92/nYouH8ZxyjqtibaQZRDu/voS4xYS4p9jEGeRBTY/qONDFYRIITBWGfaSEibRWKUVaqMhtUZjDawMA7nZNNBGIstLzNIc69WSdDx4YKWAcfoeLGJjjIYWFloYqgNKBUhB2vqqgJQKUqWAFdANkY901aGrOggroJsW1mp0dQspBOrTU6zeXpMHiRKAANI0QZ5lnigkpcRkPMFkNEFRFtjb3UOWZSgL4oQopTCZTpBlGRFTh8MgpQ4Agh4orqOuVmscHz9CXde+Tr9YLPDgwYNeh4PW5NybpRnGkzGyJMVoOERZFCjKEpPJFEWe4+q1q5hMxphOd7C3t4eyLHHt6lUMypKClrxAkiYoBk7FEdS1ZCw8WZT2FgGtW7f4SSiVumCLFsS2s6gbqgOnjrFdVa7WD0CgX8uXrtxF5YfCk/YatxHyoY1GF3lzxHVpRs+EEBiOKIttm9a3xzEM+fzzz+PFF19EVVV4fHyMqqoce39BRMn5HNZalOXAE/qGQyIJHxwcOnLpBOPxCAx1a62pPHN4CCEEvvSlL0GIC8znhLTs7FR+E+JFgBf1eJPeZvgbY7BeUytzWZbY3d3FzZs38cM//BncuHETv/b//S94643XkSY0D4WQPhuPTd9yh45QUNP48oG11kPQvEH5+dR15PXjeB5d2znio3SlqQN8/OMfx+HhIcbjsVd/5E2fxOlCtscBCkDZOAVVdG/H4xF+9Ed/FIvFHMfHx3j48KEnoZIqJI3Pek0l2rijhhAcao09PT11iANnzACLd43HI7+4s4V68FoJCz+hEdbJ+C+RZYRG7uzsgBRGuW2zL/7Gm1D8c0IfCe1iZCxJEt9xxCMuRRDa4i4IDl6shf8sa/sdNlp3WK9X2Gw2W0TNuJQTNqEsyzEajTEcjrxiKn1HKAGGQCps5kLAa1fwnN1s1njjjTdwenqK//pffw3/63/9L2w2G5yensIYg8FgiOFwCGM0Npu1Ly0mSeKt50khdIiyLPEjP/Ij+MxnPoOjoyO89NJLyPMcTdPg/GLuE0whgj6MEHy+ThAxQpEoiGw8ybmqKqRp4ki4MvjEuNcnaYpBWWI4GCDLSHSvbS2MbR0S1S8LxwGM1c57BoJcegUHuBZt1/oEx/I4R8FFEDekmaAkBRIZ64F8m0NrjfWGWqG5hT9JlHeL1nxuIhjEWkMSD6kUUEJBGgN0374d+zs9PlRBiACQQCCFQCYkMuchoqDhBE2po8JFk1J1EA7qVyr1kyAmMPIDyxCrhxFhXcTn4Ccv30tlGCjXISItpDCQEIBxD6KxMIJ4C1VVQ1sNKyj4UUqiTqiGLAWoHt116NoOZUUkrDzL0XUGed7SpmYLgup0qCMmrtWVgmjb26xYpZPhXF48Cd5soTvtnBQr1I7cmaQJurZFlWfIVjmqauO6T6jGv1lv0LYtBoMBEqUwKEsMyoFHaYb1gDpylEM73D2jRUBBOPVKXvg4aw9kQQNzaV/ljJUVXrdUILf42TYaT/R+6v4V/VxK6XksdD6c6YTX8uvZdn4wIJfZpmn8z+qqxnJAnUcchOR55nkWrPXijepMEP0qihJCCMxmO9jb2/fcgrquvc193MIaZ1CsbLt9nTG0DIRMdm9vD23bYjwe+4WdyzgBluex4Kw42lzArZ/oBXExYhTfS+6OMoaEywaDAYbDISaTMcbjcaQD0l84t6FgzsrjIeX5P51OfHDC2TN79ZRlifl8jvV67f1zNpuN52Gs1xvPIWGuAbfzto5rxNe4fY7bR1zC4GydycX8e76fvIH4v3ttl/aJn9sLMPhVUXbOHRn8HfDPyuV2fT7P7dr/k7J0ng9MjN7WvuDx287A47kkHd+m6zoslys8fvwYjx8/xvHxMR4/fuwzcL5GMmyLyOJRoMDI23hM4o77+/uOX7SHshy4QKCFNox8WACBhN0/R0ZH++363A146f4E6MmfT9w6HSNBYSy35g1HiP5vV46J3x+1XguE4LCPhMD/zM8NGXlQbY3P9tiEFl0ZKRq7a2Zkj+eim3OIvrP3eU/4xu/2+FAFIbBAroGhBmok2E1LrEWHRdOh7jS0btG0GsYKnJ6fIcsL7OzuYjQYoe1aJCl1zJi2BYyBEXCdHUS3Id0RCfJPkS77FugaDdN0kEojSSxtriYBrISSCjIn5dXMKgjLA6qRigwjNYS2Bp3poK0BbCD4wRLkptsOy8UCSZLi+NGx28wTSKHIw8MtApPJBFmeIclSpA4eLYo8Ys9Lv+BzqySpm7oOAmNQbTbQkVAR4JYta7Fer1FXFTbVBucX59Cdxt07d2CMoXa9wQBKKQyL0pOasjyjtuCdMZIkxXBQIstylIMS050p8izD/sE+BmWJ0XiEyYSstAflwJ1/4UtjPYQb6NVC+QUsQka8Hw2rOyc4xhTaPl6tXHeHMcZnf+TMm3iyHwRgtEG1qQCQay51YdTQ2jBwhjRRmE7GMNogTzPsTKd0Xx10XOQ50iSBjRYOCiwEuq7FckmEOvJ/gev0GeAHf/D/wmAwxHq9wsOHj7Ber/zCv7e3B6UkqmrjO1XiEg2VboKWQsiwKehrGlKa/KEf+iHM53PMnQ/K+fkZ7r77LrQ2nrDJCowAsK2imTgVXwAeCWFOCMAlMdp4jeMdXFycwxiL5557FteuXcfLL38M16/fwGw28/A+B0u8OTLiEzoOYmG5gI4IAYxGY4zHE8x2dnDj2jUYSxC8MRZNU/uAu21qaENEz6btnDIntffO53NvcEftvyu8++672GzWeOedOzg+PnbBu/BZfSzhHnMO6pqcWzebDRaLBQYDKr3FAnbClVkIWSIOTsNmYlEgE8pxNJeFkDAWaFvtggt2AHaJUS8Rubx08t7BLaikzaH9Js/lt3gMeL4VTphNSe4wDIqgSvUTgThwYNG5u3fv4s0338D9+/fxX/7Lf8H9+/dxfHzsvU/G43GUWNEzmyGHMRqLxQJaa4zHY9y4cQN7e/v4wR/8FPb29vCDP/iDeOaZZz2vIb5ftCaGll7aPEXEx6FEQKncz+Wu055z1raNT57AyI+VfpGSUiLNgpJx7DbdD+S2xyEKYqJyVXiviQIzCWqdZkG4OIHj0ndwb5a9QMX6NTWunnB3Wde2lEwWJZTjVLUteaoZ45JvDs6oXxGQod24z0r5/o4PVRAiACQWyDRQQmGoMsAKKANAU4tuCw0rJNbrFVqtMZ3NkGaudueyP9O2MNYDF9zUCXrYA+tagmqZRmt0xkAqAM7eXEFCuixAJAmUlUihICybypH7a56QoZ7oGghDQmbadC5T7AAbVDupv/+CzolTHhFqkEVBD0yak/VymiYYjYh9PxwOfa18PB77IGQ6nSJx0r7GGNTrjYfWmXtQO7Gg4+NHFHycamzWa2yqDR4/OsF6TdCoZ2AzRO4IuEVRYGd3ijRNMZlMUZYlmaddOcJwUOLWrVuYTCY4ODggDkyeo3Ds9TRNkSYsOdy3q+9lIG6BbbmGrzu0XetZ7Z4t72ujrojjAjTesAkhC22nMfRtOkNEVhe0UJAWQptESiRORVQp5Xgc8GhOkZOmQKeNJ8UxAbDzSoUBBubF/datp3B4eIC6rnHv3j3POVmtVp44G3gigStBPjt0P4hwFx5nym5I94BlrOu6xjdfeAHnFxd4/fXX8Mo3v4m2bTGbzbxvR1xeMcaSmJwlwm8qKEDhOjjdT8pi05RF0Giz7brOl7Umkylu376N69evYzab+Y4fjzpykByRTtmUj9dVPh8mKCqlsLMzRFHkEBh78jST1PmQQkC5Mu16U/tNhgng6/XaE2fX6zXOzs7wzW++gvPzc5ydneHBgwfufoaOCO5eiTkkrN/BzxZt9DUhtdEGzxuhMaSL03Wd49LESFZffZTRDGuJuChM8K3hFvwYkaJA53IkwqhXrK8Ri5VtZ//8+fSMJq6F8zKvZbvMFHhD9P7FYoE333wTb7/9Nn7v934Pd+/e9SqfPhGRQXBRCgmRCLStRVURYjudTrGzQwT7j33s4zg6OsLt209jf3/fXx8jMOHcY38ZRjuYVBsUSLl9XRtunXb8iKg8ad1DZ6N7kyQJOYNLCZYn6KOw2/dfeIRDRve3j1QhGpfgvBwCc77n0RglCaRSIerZBhJtPzjRLshRUlEZRwq6dif22ePKuPcYWH4IiAIAwGx91fd6fKiCEMBCag3VdshgMVSkAlqqFLWmrhb2LaHwz0CbDp1uAQEUrkyxqhto3cIKRc63VsCqBMIIGNvCGA0JBZnSQqgJFyO0xHDOrQm0ciGhFRJKJoSnSFeLFBJCpNR1YzsYCG9+YyUtjgG244noHggW13FRL01QF7g0NDHaWqJtSA1zuVggzTKcnpzg4vwcWZrh7bfewqAcUHdOXrhNnb6NsyhagGiS5kWOg2wfw+EQ4/GYtB4WweIdDmbvWu1JpZazchcXt75LpsZyOUeapnhw/wGKIsd4SnXyLE0xHo9JaKcsCVFJM9L/UMRVSJIERZ77FsfRkP42Ds6UKkGe9/UPKAiRfoO21iJJSeSMSVhc59SuU8oqyu4EZwpdh8ojVTSX2qbFfL5womzKBwXsPioFEXHbpkUn6AFvO1cOkUHjIXHlGJYRZzInLBxPSGJ3touBE9nqug55lmF3dw85cy22WP1SSKSuYyJNU7qmKHhgpIEh79u3bwOwmM1mPtCZz8l4j+vuvBBSphhq4f1r5xZOmjv8M2beSyVxeHiIoijwkY88j5deegnXr18HEJyfgb4hX1x+UG4c400RCF0JPIZN0yLGv/hfnozsPgvW+k2FRc04s9RaoygK3xKtlMTFxRx37tzFu+/e8+278TlylwkjlEmS4vr168gyCsSfeuopF3CNwOWRNKXltmkarFYrL9lujPHBHwcDzMthh96yLOm5UNKXBDlYiYnU/BzwdXVdCxZJ43FiefRQOgpaKvE1EopDXXyD4cBv1jGZMmjlBIQgSRJ0XYc7d97BarXGH/7hl/CFL3wBJyenaNvOdbXkyDKyf2jbzgd5PL+4y2kyGUPKHbzwwgv4+Mc/gYODA9y+fRs7O9xdFXPAqLySOq5YIM3y/DLQmkq8XA5ksq8xVJarK/pe5dDoJCLc8wbOY0Ytug6F4WRlC424TCjdPhihsR65pPGpXYDEhGQJKi3R56VujcyLAlmW+w7HUE8GiaAJ5xNmKGzoWu3awSk5GQ5HUJK8uapNDd1d1h/qjPOckQIJKPjoQMYRf+yCEGEB2XZI6gZlmsCmGRJIDJMCjRHo0KG2zpYaBrAaXdegbitAAqPxGG3TYD1fotMGVlGPtbCU4Vup0DYautUQkEiEcm6HAtJ1zFhD52GtBixnQJY2G6fWKBPpvU9SJWGsRatbGNNBJhJKcKslIwBR5ueutWlbdLrrXT8rr3Zdi8a1p+qon90v1JFcrxACmZMLT5IE0/EEueMqsIPoyBFfj44OMJvtgCWvYzjR17u1QbUmKJfJsMvlAu/eexd1VWG5WvrNbL1eUvnELZJJmiLJUhdUjFzL8hjD4QCj0RhHR1dR5Dn29ygQ2t3dxZWjKxgMBrhx4wb5wwjimiRKeu0BJZXPpOCy3qYhkyY4UiwAQo+MdhB9A8siYJwtuQy+bhoIwPsubDYbNHVDmhquM4gPpRQSt4BvWOPFaBhN1u1DFzxZG2TMK+E4CMagqWvn4TBAaS3KnGzkk4SyTyGdG7FAb9MyrB+hFCSXlpzxmnWIgbHWb5QM+37iEx/Hxz72Mr71rW9hMChxfHyM3/7t38bdu3dR1zU2riTFB6E1Wc8Rl3kXXFO31npkodpssFmvsTOb4SPPfwR7+3v49Kd/CH/iT/wJv9GyjHx8H2nu0gbB2SkhKsF4kTM/PnwXQa+zRLnyV+AaJI6DxQt04uS2AevPiTeUtm1x+/ZtLBYLfOtb38Jrr73mNuxgTMYIFBMl9/f3MR5P8JGPfARPP30baZphMBg4J1cyNUwS6fg9RNCcz+dYLZeoqwrGWId4EWmSgzvm0VDZaYzBoESW0nzVXYvGIahho+tzFUgTpPFcJIACoMVigeVy5Ym6FLgQLyuG7gG4Fv8dh6gm/vu2+U0xT2IwGGC1WuHrX/8G3n77LfzO7/wOfv3Xf92VdUuMRmOPArKoHZVJUyRKYbPZ4OLiAlmW4+mnn8bOzg5++Ic/gz/zZ/4MxuMxrl+/7kmonCDxOcQlxfiI0TYKCJk0y/OFPJBW6xUAIiKzYi0jIaTjFFC0siyddQTJ1VsEHhHfQz6vXoAXZr1f/9m1d7OpMZ8vnVgbt7mz2KQLzCGQFwWKssBgNELhuHlsqkncI0GJFSOJxsBoUkvdVBXqhkQ3d3ZmSFSC5WKJ5WJFjQMRv9BYg0a3aHWLPElgIcmYVQCME3+/x4cqCAFAUKQ2kMoiEQKpkEiVQpYkUMbS7xGieWO0yzZdJmItqcRFrWPWkhiXNcb3eXNGydoWWrsgxMFuvrfbOgEZG+qphIQICFdHZLdYa41THw0HQ4gUulow39A+YXh7MBlnZE/4THpB+KfWhFwkSQoFgca1VQIUUbe6c5G1hNYdlEqcLoDwtX7/nYaQCIZpi6KA1h3GoxGyNEWSJp5hnuepzxi11szEhXKBWdcZD1kbA6QpqW0aYzFwJYnNeoOyLFFVFT3wTqWQSwdSSs/vkEohyRL0yFiOtEX3LmRrvNH1yF1w6qp+QSUycqISaNWXROesjd5Dn222CG0xZyAeszhg9OMaZfy0ifSNtdCDwC9nVTbiBPDnwJ+H8RLYPG7j8RhXrlxBkiS+fZdQkYUfM2OMX6S5xMLzKXS0OO6NyxiVlBg499hr169hf38fe3t75H+kglPpdgASQ+k8fvElbhPi+veh3zLLz3Q8DjFhkz4PPdSAgyIO2GLNkvheh9PgsZSOcDvB3t4ejo7onrK9OqMCgfArLp0fn1fMKQhJRFBMFdFn8FgCYbbb6HehLTduAWbibZAFj+fMkw4/HyM0gH/+pD9t2+Ls7AxzpwNy9+67ODs7Q103vRJCPHbS8fKMNmjd3GAi+JUrV7C/v4/Dw0NMp1OfTF1qtxf9exvPmTAPLl1dNCYWuqMEJSAYTIi2IVGJ/uY5E88pDnZjdPb97m+Y69u+U8E4ML4OWgsC4hSIsXH34NbnOwTbk15dHYUMHZ2sPTtd8/7nidVOnM4FT1Y8+Tn8fo4PVxBiLWTTQVUVMiEhcgErE+wMBhA6Q1Otsapcf3XXwQig2WywcaS6yXgHWhtUyw2VTpxCnuk06s2aBkFoQFJ7ad1QprHeVKhdmx0sTb5BSQ+D9ZLsAhvjlB8lBSrUk+1s2412QU2YIdST7er7vQUT78N27h9SStcDG9+n7dtG3heNaFC7fvzj42MSavJ1SYksT5FmiV94pKR2uCzLUJYDjEZD5FmO/b0D5E5FkYipu9jdnTnUJXOZvwF3w6zXa4KBNxus1mt0HatBkvBQVW2wXNIGCAuv2lrXFTbrNXnGlAOwcy636B0cHBCSMxqhKArinRwdIs9z7O/vYzAYIMtz5EXhV2ohhGstznlKAQCUy3hIY4PKJ9T6m/Rg7/Wa5glv5taS9Ly1Fh0LHElJglJCoKkbErgTHBiEhb03PlEnk1+QXFBD6onGWXLzouBKCYbKgrrRvgOKNg3ykaDg2GC5XAIghdg0pRLP5z//eWw2FV544UWcn5/j/v37ePvtt7FcLvH2229jtVphs1ljsyGPE26l5E2AETMS3qPy2vVr13DjxnUcHh3hM5/5E9jd3cWN69dwsL+PummwcvdvGwkBqHPMGKp3P8le/vs5eMMzZotj4RIHDqyapsFyuXRowRLL5bLHVem35hKS8swzz+Datev41Kc+iZdeeinaFAgxmc8X5NFR5P46Y10d3ux4A6P3ax9MeOl0IWFAZd5yMEBujDN7dEG95gCZNpC4HMHoTVVV/ro2mw3xwdoW7BbL94YfGJrnGVSSQhuLtjO+hTPIhYcg9J133sHv/d7v49GjR/i1X/s1vP766+Q66/2eAiF5vV5BumfbGIP5/ALr9RqHh0d46aWXsb+/jx//8R/HrVtP4erVq7h+/Rq4LB37AcXXSly3/vwK3UPCowXEIQvteMbESrLBmoHKWbI355kIyn8SmUCJBEZYP+4OsggBSLSUC1fQj4OowCdqPIrH48HwVCi5WY+e8hqllHKcqH4iwjIQdduhaxp0bQcBCyUFioI6/BS36FY12k47fSeyxZBJAi2AThgYCUBJCC3AbRsfxPHhCkJASIh06pkJBFIB5EmCQgqkrSJOhgVgDXXAdB26tgEyIkIlihaONm9hbA3dtE6ljrprZAJvV8yTses62khcEKKUgsndBHYTJIjUAMLQhOdFbTsy58M4CI7fG2dHKkm8Z8F73wx4qDD6kQdW+LCWNitYG3maAD6DdNE+txHHsO50OiU+x5j4HIPBgOTqB0MIKRzpN8HAeTyMx2MUZQEhuEPDYLVaUSfCYoHzi7nrnJj7zg4S/WqcvoX26qjn5+d4/PgRWAJcCImdnalXEr169aoPPgaDAWa7u2i61mdLWmsUTtjMZy1S+AXRug0aQCT6Y3zZgbNi1jmgeu3ab0hKKehOe90WzjTi7Ig5GVRGcgvDlrS8D1KjFMZog852DgImVIJLIvye3lxyGZQU1LHFgTCjNyxORYupJk+i0cjDyqvVCtPpFEopnJ+fY7VaeSEybvnlxTFkgAE5GDjzxKMrR3jm2edw5coRPvKRj2A2m2E0HKAsclhYLFeBr9FHGHjjJNTi/bPH7+2IM2L++Djw40WeSdusLBrb2YfMNEiUTyZT7O7uYn//AEdHR/77tNY4OTn18H24pr6wGC8LzAnpI2WBnMtoa0xWVJK6LAiNo4CUP8MY5YnXFHCZHm+HnrXuEhmRM/oYJWTUOLS/MhrQf816vcY777yD+/fv480338Rbb73ly0pxSysTteNsnu99lmU4PDzE1atX8dxzz+KZZ57BaDTCcDh0LdUhUGC+HD/PPIbhWqg0wQvidmmEf8Yk7nicLn0WAqE0/kOdlPy8XUZcrCX8vBeICA6MXBIaISDbxGR/rtah9XAmdT0kJEJLsP1cOS5fx2JkFAglDgmRbq/qISEilDYtt+xybPoBgyEfuiBEWgtJTwOs1kikwCBJYITCoFHIJWULXUsE02a9gjUGuUqhAAilMBkOkckEi7NzXFwsvIKcNRZZmiMvU6RZisFwCAiBvFhhU7EctONZRM6JgBtslyExyzo2HtNuAnSa1Bk9qRXwZDq/yH2Hoxw8UCKYHr3/jH745MNvjhCOP9GHHLke3jQNVssF0jTF2ckJsjRDlgdPiTRNCYofDjwUXRS5/x0RQqU3VuIOCXJRNfB6IZayAmssFos5zk7PqK2wpnZZLlUI12XAYmy8SX/t619DkpB3S56ThknqWlDLooRKFEmRj8fIstyRChNMxmOUReGhdOp+GfTgeQAYDAY+E1FKUUtulhAxtQ2KoiohuV0OLrQmnkh/I6OD5wUQyjzcBRI4DcJ/ZyyxzIEJc1EAePEjKSUSl6XGeiO8yHEwMB4NMRyUSNMEs9kO1us1nnnmad9qulqtvc6Gca2uXdciy4hrlGUpdnZmKIoCBwcHODw8wHg8xng88u2P3CVUuO4iLhG4WejP109ZGy/CHzwE/F4Hl67atvHBSB96l71AgcTFEjc2gay52ZDYnFKkkpymqRu3PsclJCuEYmUuWQrzoMO7796DtaQfs1otkaapFzIcDgcYuC4t41C2yYS640Jg13fR7boW2jipfLc+8SZIG3HYCIWQTowr8WhgvxxHqMabb76Jhw8f4pvf/CZ+53d+BxcX52jbxicxrBTMSRkjCtoYnJ2fQQqJK1eu4tlnn8OLL76Iz372s8QJu3LVP3PL5dJf0zaSSB2GgZjKAcSTSkb0DBBqHQcc3s+nqlBtNkhThURRssWHiT6XkRAhAQMD4ziC1towZTnY5YYJ92+u8MSlTua4hODX+iCAv9c4KC9z7rls0uepBcZGj5XwqC7xgyqv8qy19g681tC4NC2xPChocUGZcZo3CKUuYync/WPZHSMsIKyFNEQiULpDIhQGSQYkEoNNglwKdNZCdy2MFmhWa3Rth2ExgAQR+cajEQZFiWa1drbGnYMyiTw5HI6QFwV2dmeQUiLLl9hUgbBnbbDx9hs2s/al7EGFvPjXVe3Y6BqdZjSCo2HlI3ru9ba4nO1uH3wefdjjPe6dr0fEiAwHPRxECa96bl00w5bx1hrA6Oh9gBAqIkPRZxDcn3q5cFINPaC23dkMu3u7HjGhv0demGs6nVJG5ALC1WqFxXxBvjlnZ47suvZ/Hjx4gE21wfHxsZeDXqyW7t4TqZOIwpQ1TCdTZFmGvb0974ny1FNPoSxLXDk6IuXayQT7+3vuAa28WiUrVg4Gg94CGLeANnUXLc60uEhNnCBe4OMMig/tdCPihbLThL6ROeHlYIjvN4mj5Z6MyguatZZIrSLx81AIgeVy6TsPqNVVYjoeI88zHBzsQz/7LLQm0jGXn2KyqtYaDx8+xMXFBQaDASaTsXccZsdTFrbiDhdWgGSBNyp71R4l4mvha+uL2rHl+vsdoXXx+w1YKCMOWhFt27hOsswt6DHpm7t1kp6aKJUZl2DV2qKgzjQ2SNvmBYVNFM6LJNT5u07j3r17WCwWOD4+xp0775Auz2SCLMuxuxtKodyWeu3aVcycUSU7TjNiYW2wBeCuMThiZNdpF0hr151n/RxLEnUpCKHvk2jbFq+88gq+9KUv4fXXX8fv/M7/RtM0TjV26oMm6syhlujhcIA0K9Cu1zg/O4dSCi+//DKee+5ZfPzjn8CP/diPYTgkBCVNU6cGvXJyBKMe8sFdQNbCd8ZQwNdeQnMYcbmUvEVBSFVRGZisK/pS9dYRygXgky0IUADikk+at86dnb9ni99kfRQCAHEQUveCEPreoL/iA6AskJ99i65H1S0/Fa60Lbw+DAch3Lo/GAxQbSqsq8qh/c5ozwXjRmu374pQErIUgISn9/s7PlRBCEDJegJQoKE1IAgdUdYiFRKFStAYjUZ3hDZoTSWZhvgQJmULYyI2FmWJrm1grXaBBdBpg9TDjrSxKgfv85/KDaRfSN3gcA9/v+YL38oKEJQWgpAARfO/6eP6cPUTj+8WshZPwFis9TwDmu2Mpni82pdsAgzr3+YfMn44miaQN1m1lVU766bGpiLDsyIvoBKF0XCEclB611hqeSWSaOeEpTod7nOapRiKoS+3NG2DwrmWNk2D1Wbt760Q1J4Gt1nkWe4XIhKmWuL+/fvIsgzrJWlyjEZDzGYzV2IYksy+aydktcaQ+SokSiHPU3fOhGOnSeo3fQhCJrikw/Xl7dIcH772rwxsElonObgB+m2tXq8iyrhC2zT8hhdnhbHUtpTSlSM7b/xoTDDj4/fx67XWboPL3CY38M9STBgUImhV8PPAgRmT9i5Pz1A+CmP47ab0B1u6icsQPZRT9MskSkmPQjFnoz+mIVAB0LtmlssmxENBiL5OSFgngvcTryVdRyrKJKOe4vz8HKen0x5CcHFxgel0gjwvHCFYOVRSeQG2i4sLKMWy6H07+nhuBP5KIEkTspKgbVs8fnyB1WqFu3fv4s6dd3B6eupRjni+hlJemHNN0yBNUly7dg1FUeCpp57CU0/d8lwvMvLrK7zGCEeYS0Efxfp1KgS18RyJ19d4zGNe0HY5pt/u67Q+JHvHEBFeu73jkqpsDPjxohmdB8+Y9y/HBE4IoywxTyWed750En02bFAw7hz3hNeT2HqA1gqnqwTrUbGYBK2NgbQWGn9MdUKEADIhUEiBWms0mw2QJEgzBSNSjJTCblFg3baom8pp9AO61dikC5weHyMvSuzu7qMcDNHu7KC7QsHJyckxdQRYYL2pAaEw6jSEVJjNdpEXBapNhcVigaquML+gh4/rnBaAceRV3mS5PhdDnULQZthHOrjGDL/TP6mT5ju7Sbg0M4SQPXZ7XLyJz8O2PLWixVSGzVXIxGd/8UJN1xeEuBpnFrhYzCGEwP3790INO0motiq5fbjwfiOcSY9HYxTOjXTsCI/jyZi0RIYDr7aaZrTQMYHTWIPOBDTAGIvWiZq1bYe5c8Alx85TnF+c45VvvuI5KNZYR8ItfKshow+MiOzt7SPPc+zs7GA0GmI4GGBvdxdZRtLog3KA6ZQ4AmlGRFpGBzgjlnxP3WGcbwks/RuWVCNNRuekO43OkrS/cDwbNjqs6xpt03qdkJi8pnW/a4u/m2zOKWsGgLqusN5UngeRpqR9wYFFfN6AwP7+XjTJApwcMlPuBmIbeuU1MrjDpl9uoYBDKc7+w+L3QRx07d/Za4UICsXBRVdGJEz6oDTNHE9h5IS3MmoVB2WSSaKgdXiuw2YpvKDfaDRGlqVufJreOgGQX4611gun0fiwjgVtQKMRdZGE8xe+BbYoCq/HM50SCvj222/htddeR9tSMLO3t+vLj1wWtZa1NoTL9nMXVNO4FXmOPM/w8OFD/P7v/z4ePnyIX/9v/xVf/OIXkWfENQrrgvGtwoD1uhdt02C9WuHGjRv43Oc+j/39fXz605/G008/7RWfKalpYS2X86zv7olLikzEDaUW3d84t+Z/EAMLAR9xTapATJXcWEBCgLxu8URKlHIk+TGkEGibFtb93Fr0EIl4HiLknuHnoOeiaVs0LZdjmlBmMf3OGQnnOl7kyLOM0A4hfOnXI/QiEEi9Uu5m49EoIUiLptoEzZgkTZDlObSxWG7WaNoGSZq5ckyLpu1gtSFRTnwwqqkfqiAEICREgcoy0AZCmggJEchUgk5rKEsIiTUGEERQbaKMQioyQGOdgCRJ0WkNCDKm464CYwyUE9DSnUaaJui6fiZL8Joj3LnP5sNHrz0yV8gqqD4o/NxkkPC91szLWd+TUkr/P9F/+5N1gc57PCT+DOiNgk4v+ogntOb586CF1lrhH3IAIPQ/PonwvYlzKuXNjssmZVFgPBo7wS7ndVKQQJAtqNRQ5AWkClkcQOcaghCDVgfLdCmI47JYLGiBcnX2pmnQ1g10p13pgmryfD6s+VLkBVarFfI8x2Ixdxon5B+T5zm01kT2dH4pjIakaeqJaT77iO4jh4VxeCgFkWgNgg+MsQbCiGiRgQ9cpJG98QxA1raKZb/Fkxdk7yYbCZDFJZIYDWDIm1s+4wUynktx9smITjDgelIOdZkvs/3f2wcHGOHjnvz09L8ulMsuvS5GkXD5+QgZKmXDfYIiZ7fOpVvGWXi45jSlYD7LMqRp5nki2/eFN0ytW8cz2fguJ0YsNpu159kwQlCWFx5tGY0IMWFNoIcPH+Hi4gJAQHPiLD8uX/A5PKkdNlEKRhucn5/h8ePHOD05xdnpKSbTKSY7O5BSelPEPlrRZzcWRYErV67g6OgIV65cweHhoZ+bfL9Daa6PEsflChnxNmIkqf9MbLe5x2Mb3Gt7aZpfvwOKwZ/tOX9+jN11Cbc/bc0x60rcfZIqrZ8x58Pay23T/poR0E1q2+4/Mz2EJ3r/eyEtNLbh84kSENBX7oQSUsBqp5NDgPkfT9l2GgGSLVYQyKWEsgaN1pBaYiIVbF5gKYBVkiCFRSNJXEV0HdbzOXTTot3dhzWU5Q5GI8gkQblaQriWValI7pva2Mj6e71eI0mU5y8wTFpVG2w2G3RaY11tAqHQZYiseqqkQpZnvbLG9sQCZ0ygTVa6oIYRkV4t00+2eLIGrkd/z7fQ9nIF7/IifLmmbl1m7oMkKyB8ZknfE5eW4r+3N49Lj4eAI0Bp/5AIIVBvqqBDkudQiULhSKKpK4UkSeIVcAnazpBlKcrBwC0QNJZlWRLBGKAMLsswHAzwzNPP+IXHWuuJw+zrYQwJifF48p/lcoVFTR4sofZKZRTKbDOMhiMivKaJFytjbkBRFNidEUoyHAy9TTqjQFTrz/wfvgYeL55PvVIBhOe/WEt6JRAGQigS44s2Fe24T6TaWsHavnV9nmd+bjN3pBeCCoG27XNaaL3lgCUe90hp0mWjcYnGzyH33/Hi+H4lq/c+bFjoRb8NOpQZ+oENb16MeOlO4/zsHCcnJ66rq/Htk9uLNYTAdDKBEPDQOH2Wwmg4IJFCh+rE72NC4/Xr1/Dxj38cjx8/xte+9lWsVoEYSGNF94yMJAXKcoCdnRmo/EmfFwinxo+tMdzCShuaEBLz+QWEENhsKj9v6TMC8mktSEtIJWBZ8+2yCr9PG6Cqazx6dIyHDx8BQmC2u4vCoZShXBK4PdbyvAOOjg6xt7eH55//CD796U/j4OAAV69exWg0gEeFERIjryDtx0wgd8mC1hp1w0ROuPdTMhR/DukX1e4zOLCizyb38WOcnJx40mbgN9HzYCzpJKVp5tYb9yfNkKa5RzMAh1QJCVgNI4JnDY+ZlBJQ1CprDYnPsUMzo29xRx9LNhjHR4ErOXnPGiEocbaBsxGv7p4T4jyVOCnxBna+O4YQZWElmcK69bnrNJQ1EJaS/g/y+HAFIbAQTEoVAgnI6TYzFJgMlIBVKYTVGCgJYWkApQCs7lCv1wRvt+TdQptbCQiBvCxhhWs5c+ZfTMgTAmhbMgIbj8d+Iek6sgzXWgNO3Inrbb6G6chdvBnRzsu1y+2IPshtQwjf821FFNBE9+IyChJF41s/xbedOHFpKPpZBJvzlss21Nvv3N6sekcUF9noNcYCwpDqLJOx1nbFJx3e7nwgrKEHRSqFzPnPsFfOYDDAzs4O0pQ2fYKb93AA+DZSfj3xPVIMh4PALLfWkV+ppfjMtVcyEZYM4OZYr9a4uCBNAy47EZqWef4LtwFzcDGdkCT4eEJGXGVZYm+XRLz4vHNnnDcajQDAZ6kcjHBwJESw2eYghO4WBSBCCggrnPlWfxw404phfyZcEnqT+q6j0G7cL4vE3RYxVyJk1P35ED8PHISE0kY/g+VnIQ4gvptju/bfP++gGxGCENk7H2NIU2U+n3uYGoCfm7yAc3mG1gjmgIXPLArnwbPW6DrTCxrIkExib28PTz99G1mW4pvffCXK+AEOJgB45U7iImUhSzUhe+d/MwpIG15srkcbHJFskx4SFH9vEMjj+xJawr0on9vo6qbF+fkFzs7OACEwGk88z4UDQg68+Pv4fu7szPDMM8/gueeexQsvvIC9vV2XTDAPZLtFNZS0GHHLMlIVrpsGVV2DWvm57bUvBgfAE0/5GeXnnoO28/NzXFxcRF14iUdkgneT9cFJmpDvVZoSmhvcq4VzE5ewwvrx7LdpM4IjIQUFAJ0zkAvPVfgTz29OXH0w7e9vQOMh4C1jOMniRKrTJNfgS8Mi+BkZ//lhnDvNAa6BFP0W4A/i+JAFIQBgIThSc5NSag3ZCShQS2JqLQqlYK1BaywaY2AFEVR116HarLFeFRAIzqFJmiLR2tfnjVeOA6qq9hE8t0SlaYaiSN3mkaHtWkxWU7Rd530htNauVmh9iYYCkxAY8ISCjYY2mlgAiJdhLbGgDcW42w8YfZa/Q5cDDyEuxyy9Q0CIEAzxz8J3xEHHFlSIJ320RZwV9/CaXjQS2oxD3BFKF3Ed1iMu7KzqHqaq2sC41mdSfA2iSMvl0pHwws+otY27Xcrod4k/U2MMWifVzWPOnU6cUXGZZ71eucUeW/cvHEoqEsJaLHH/3n0kaYKzszOURek7XBg2L4oCg+EAo9EIWRrIsFwjTtLEy8czQTYvcm9254nBrjOIF3C+ldZK314MuI1YCN9CCMC3ZHIQQhtD5z6LxZ4A0vXojzt/H28WzKmhe9T539Np9t//fujHd4uM9EsuAaIHeFMzzk3VIM/hywCzGXWbPP/887hwPKKNEzNkzxXOUslGvnQlPOYDmCgw0H5u8Dzny5jNdvHss88iScgtmQOG1Wrlzz+4CFvHk+k8evVe8H0SjWtsbkfnrLYQonDdxN2gVmHSBCoxnU6CKJcX7AooAncS8TNhLZBlbDdBzysHXszVIFSidh0/j/Hqq6/i+Ji0fwiJC2JuHMTzuVMg07p11MCkZARI1g39UhZzr8il2/r1NkYZQokyIM0BLQN8zZM3etjodXFZLxDCQ8ARulpoXNgBG9Ez0G+/JVRN+UB3m39HSL30iDAR2UMS0ktsoznR6S6S6bdgSSjp1FKrzQZNXfl7x0h+KE1SUPPktf77O77rIOTdd9/F3/t7fw+/+qu/ivV6jeeeew6/9Eu/hE9/+tMA6Mb+o3/0j/Cv/tW/wvn5OT73uc/hF37hF/D8889/ICcsYCCgIa2AMhLQFknbAFYjMwraJtDGYJwkSIVAtamwahpYbaEFZTvz83N0ncF4PMXOdBdCCI+IVNUGVUMCRcbBevP5El3X+rJLURS4fv06hsMh9vbJXMwYg7pt0GmNBw8e4PSUsuiFk8FuW+rNp8Xk/YbRtcw+oT6u8IQNjieJW4yMDVAtkR2t/6z3JJr4Izxc/UCkj2HEDOz3Oshu/P2/kBcGeEjYQfO+hBAWEK2ND0j4U1vnG9I0NQSI2R1cdOERK1ZH5fsZk015kdvd3XU+HSNvsjcZT3qKrEopfPTFjxK507UiG8NOudr7cSwWC5yfn5Mo2/kF6qbG6ckpzs/PcX5+jrfffpsWGVcyIm0CauvmGi+jbmVZ4ujwiFqYd6YYjUYoyxKznZlDcobO9+cIN5+6SQTfIrTKZkXmFm4eW7dBCUcE9aMh0HYdWrfBpin5nMReLLSAGRgjIYTxCzUBd1sZlTGo3aI2Ho+R57nfmLnstT2VeyUm0f/Z+6JsvXlnn/B767LOmJhoeq3Io1FoqX/qqadwdHSEqqrwzDPP4PT0FO+8844fW96oAeDKlSPs7EydpUACbYG2pbkQyqfhvPk/pZS4desWZrMZrlz5Fr7+9a8jTVPcu3cPx8fHztdjx5e4ApJESQiXeLaDEC6rcSDCz7KUyqNo/DPjWu45EWPNHaUUnnvuOdy4cR1Xr17zraAcDBAniO51VdXOCHGN5XKFstQRZwj+ecsy4r5Qa7bBcrnCgwcPnQEhHBo49d/FhN+joyOnNktIJwdKFDgWyDIqH3mPF8vGiwrsGaTcpqpk0CmiayECMVsTBHSQhbpkNL+F53h0mgTeyKGbFFKNMT3PFdKXCcgHc8yEoPZ01hSijhXj27cBQc+eIN6NkEGhV0qJJCLJD5ypoXRoP/gcXNATAgaLpmmxWq/p3hnjgipqWGibFhfnF1gsloCFW9dcYGQNBV6wUPwYipjH9v0f31UQcnZ2hs997nP4sR/7Mfzqr/4qDg4O8Oqrr2I2m/nX/PN//s/xL/7Fv8C//tf/Gk8//TT+4T/8h/iJn/gJfP3rX/cEqu/vYAcX98e6tlgNz6NQ1iKTCtoCismVHDmbQFRk8ysIJ0GcOJMg9000qYWPVLsuZAp1XSPNUg/XCSmdQZrBcDj0xmEs+lLVlWf984ZAVwMfofsrdHAYzBMW22iBte61wv9bAL4ODADOcC+C7N//uFzKic/JZwX/pw4LeHtb9KFd/3hZlr93VCkmR7rrZwg2JoOxlLFSCapqAzLrE2gcugEQaRAW3mSL1R1h0VNSBRg16JdNePy7tkOapiTfHolfEWxK18CIgYVF17IxXHAUzVJqh+105/U26oqN70pa4HUHqegchq7UVAzI5AoAuJLnr515M8ItuFL4urvP7KINkzNgihf72RkjXtubfz+Y/a4HvjfmfD68Kbzvu23EWQpn88Tz5KyX7lHgo1gbnIazLPPOrqPRyAtuWWs8EsKlM96EYk2HfnAVMszUcYbGY/KdYWO7xWLuu4kYgeL3x9/B2TSP1/sdcbmMrzu+X3ELrJQksEbKxIOe3IDP3j2f5Ds/GHXhayIJ+QUePXqEsixQVRvPnRqNRshdhyHz8DgIYe0iNsHj54DO0fox5GSjzHNI51vUvw4grCOXvZf8PBH9ecNzMlHBGNK90L83fl38M/p5GDfeW7g9mAJD+56TPEZEVJJEqFTYDy5hkzZoEcWeNNLzyIxX0SWkjp832/s8y4P4xAL89358V0HIP/tn/ww3b97EL/3SL/mfPf300/7f1lr8/M//PP7BP/gH+PN//s8DAP7Nv/k3ODo6wr//9/8ef/kv/+Xv+4R9XmRJrAxGQtUWVkkkxiKxFoUQ2MlLlLCY1w0WdY3WGBhX110tF2jcpjIaj2GsRV7mkEmCpm1hqw2EkN4dFSAjL20MTk5OoJTCar3yhMJyMMBgMPD97kdHRzg8OHQw7gZd12G5WqKuqXa5Wm9o4nVU/tFdF/7tYNbGbXzve1jrFO3g4TeC5KIMjCfS+6IvAGBhrIC1bpHjLgYEQl0IRL791PtOkHMhiHAlEBZcDsqMMWRBrRlmpHOUih/6IGJFGTb4KeydAJliNf67ANF72Kr1GkIKLOZznxHmzpGS299cEgSlEpQFLcqsbUJ22CRJzcJKzAnJsgyT8QQA8MwzzwAIrHoA2FQbH+A0NZn8sc9OXZOminGy9hvXWsfXW9VVcOw1xi/SaZp6cutstoud3R2krqRDxnUjv2nmWY4kTTBzJaDSyWtTkET3kRGgNE2QZyM3U3iRBeJgkBd5bmuk7JRQksq5xXJp4slBy5PnCW+4XMoIgQ8QBxe8cLpP83MsfF+YdxzkDYcjWGs8wZEXXqUUbt26hWvXrnq5/oB6GdQ1mzTmuHLlKsqSxpvMGju/yBPRU/pzpvFr0XUNjLVIM4UrV4/w5/7cn8XZ2Rm++HtfxCuvfBOL+Rz3799HVbWonGuxjNRaOTtmDQ/pM2b09YvccUlPIiod1nWFzYaum7RyRnj++efxsY99DLdv30ZZllBKOr8n7Z6TBE3ThjXQBQ8cFDCywCjBtsJvVVWoqhqPHz/GW2+9BSGkn5eJazdXKvHdPczBYYTNWovRiJDC4XCIvb29HjJYFDk5U5clbj31FEajIUbjCUajUfQZ8HMo+La0YBVcz3HiOcMBpDGeb7a/f0A+YiqBSbRvkxdOfpoQGSp1NU3tk1kmg1MZq8FiscTZ2Tnmc1Io1g5xV4nrpKPVDEpJJKlCURaufJUHnNoFNXEAwyFDtakwv5ij2mwgXSm2yAlNsYbawJfLpQ+cLQBtrftjoK2Fco7kQgAS9v8/3TH/8T/+R/zET/wE/uJf/Iv4zd/8TVy/fh1/82/+Tfy1v/bXAABvvvkmHjx4gB//8R/375lOp/jMZz6D//2///cTg5A+Cx+Yz+ff/kQECAUxBkJYSA1SUhWC2MaJQpmkUALIpIIC3VCrNSyAtqlhhEDT1ui6FnDaAEFBkL6DJ6ExgSG92WzovF0fNxMip9MpDg8P3cJGRm9d13nb83IxQFVVWK03UEko0fDC1kX/9hH5t0n5emiK/9mWzgdoIzbfRt+Ovo8RIwsjQnDDAch3W5P/ducdsulIptWGMpJHhLaOfhYeWhn7FUuXdRrrjAMBmbiNymhYB0W37tUbZ50dl3SkoIdf6464JlIhL0ooqZw5XtYjlR4cHPj/HpSDnvYJax+kaYrBkLgby+XSc4e6lsodDPezNgSrjbKSY9M0WG/WOD099QqUjK4AlAHuTOl89g8PsO/Uavf29pDnOfb2dn1AQihKjrpuMBoNseO6AuKyAduiSyGRO3NDVoYO5QHutOh3bHCw1XVttMH3x/A7nSu0mbHjKiMiNJ79ks2T50v4PWfkdI1ZRtcXd1/wZzLJ+UnnRCWIVQTtM6+iiz6HSl5MSOfniFVJucV3PBriIx95Huv1Gqdnp1gul3jwQOH+/XtoW9LcoRZz6ctjjLxQpwZd13bphs+VXx9n6PEflpNnEjTNl31cu3atdw8YVeSuGyK6qkDUdIFD3NbN3+d5Sg45jjlVXLriAIUDTTqfvMdh4XIMYJ1nFDkYX7lyxev3cFDEJc3BYIC26zyRPe6K67oMSWK3Wldj4rWIZg78uqSkxMAln+y/4rteLL+Dyz2JP3fWL+J7wmUY6rQMiqakGpxCGgErTZjrDr1InCCiUsmlcX3ChPXf0Xadv7dMeLawkUaKfcI8caVzjyZbrsp8IMd3FYS88cYb+IVf+AX89E//NP7+3//7+OIXv4i/9bf+FrIsw0/91E/hwYMHANAzceL/5t9tH//0n/5T/ON//I+/p5OncgwgtYEygBQaEgIKAoWDnEd5jklbYg0iqBpJ6nFMZKybGkmSosgLQAjk+dLBsUR4EoJUOpXMkaYJksTBiW4Ta5qGzMbaDq/KV3tZsJKBzKgd6ZUnL2cHxhh0bYs2YrgbY5BzuSiKbntEIfdv7QzawoQxDr4N3JBtKPZJh4WFsG4BE1HgYSM7836S+b6byHs+EFuvid0s4+DE+i+KwEDbX9ACaW/LZ0QAwXwpyE+zC62JINjQ/SPC22N43l8HLSp8jzfVBk1bOz+GCkmSYrlcEqJQUHYmpSDeh5BIXStfnufYmVGtnxn33kiKs1lnsre7uwutNXZ3d0PXlIVzJF5Dd9oHLbFktM+WXRdE0zR4/PgxpHTuyZFiqlIS4/EEeU5oyc7ODqQMJF7u3smzDJMJCa+lTrclTVMUReE3r7ijgCF82uz7gSGdY780EeZMPD+4rTHMDQpEYqh7G+5+75Jh0EAJyAq3tTJhk7kSvDlTabOPvPAmSQFa4BeExRtb5xT/d2jvtZZsF4SUZPxYFHjpox/FaDTCyePHuHH9OjabjQ9G27ZDXTf+GaCyRiihMQJa1423iGBCfdMQGkitmB2E3HaGzbCzs4OnnnoKs9kMzz77DK5evYrxeOJ1TLirhsnKXacxn1/g/Pzcd53EZUpWPOWf0/kGsjJ9JgXDPMZhLrA/S9YrQdF7gvkk8XTmMIaMJx8/fhzUjBOyh1itVtjb28UP/MAnsbe32wuYw/WwlobxQSq3AvOYxfyWtm1x9+5dV3qtMZ1MoVRIZqlFl9HXwAnh7wYslFRI0gRwwpSMisbS/iERDucrHJcl3bJxCM/N5fnftS2qmtywCamhe5/nOaRbI9qOSrpJlqJl4rPjhLgCrX/EhDN5/z9ejjHG4NOf/jR+7ud+DgDwqU99Cl/96lfxL//lv8RP/dRPfU8n8DM/8zP46Z/+af/f8/kcN2/efP83WReAgGAh5SB7ZS2kpkwslQp5mmBalqgBJF2HTV2hE9T6qh38VlcboACmM4Kt5/O5a79tUbcNhAAGZYmiyKF1h3JQUHlluXTKoBXV8WFx7/49APAw/Wg4wuHhofccSR2JalyM/QMZt9mFhS+0hBljvE+NdqSjmE3NQUtgy2u0bWiHM8ZASPkey/LWbbVBJpw2YPRU+LjdWMjthf/ywef27b8zdJXw0UNHotdRyYgQLXodZS1cOnA/BESQzWfBHYi4rRXQIL0Tc6lM5TYTywz3iDTrNg5tDKq6Aptg8QJFXTThkeJaK2s1CEEB6NHhke84kEpiNBphd0YtilevXsVwNEQ5IO+dNHWqq2ni4W5enLSmFvHNeuPnYtu1mF/MUTc1Tk5PcXp2iqYh2LttW8znc6zXa9/x4Rc2IXz2SCUdUticTCZelO3KlSPvW1KWJSYT4jJkWebRIDKuGwNgrRbqGOFz5o2MN/LQ4WGjBZoOyhxDe2+YW/4O90orPHeenAzaKNPl1xmnyGk9IdIYg6ahMgJ5x/C5K7c5BXG8NM38xhRfy5OO8KgIzzEwxkC7LojplAS+xuMJPv6JT+Di/BzvvvsuNpsNHjx4gMVigcViidPTc3SuA69tW6xWS//v9XrjUQ024NtsNv7eAoQCN03tStETV6IjF+obN27g858n9dKXX34ZN28+1XuO05RbuEOJ5eTk1M+t0EWTutfT++LuKB7LGD1hhdXNpnLlrOClxM8xr3HSySfwf3ML/fHxcS8wJdPNFqPRCI8ePcTBwQF2dnbw0ksfde/fTtBYp0ZH483zSkboQQpu6X3t9ddwfnGOpqmxv7+P8XiMvb09KCVROL6gNgbaWNeVN+TliVcako9w1+OFEx2yycg8l4A4mVKSumNiAjLP8V4AEgX3jZsLdd14YmqWpeR4LqVTXm4oiFIKVd34Mgy36nqcmW4JNSl+AFHIdxWEXL16FS+99FLvZx/96Efxb//tvwUAXLlyBQDw8OFDXL161b/m4cOH+OQnP/nEz8zz3HcvfKcH5zocp7KKauLYBZTgkmZCAolMJUiMocjUuo3PkI1107aQvn0wuDvSIiQCzwKBSNSHlJ0pkqUFhaEvANgkFRZLcr3stEaa0QOa5TmsRbT4mt6/n4Re2HgSWIPAiVAwRrqH00BrImdxQMHZPP8N/xmBf8E/87wSSx01lqI9L9JjBUOVYebFpCjwvyx8MMCfz+V7Grft2vR3EiLBP72hRLT13hg69ehNdGb+oYzO9dIRvy+qrT4xa3f5gesEiqHWAHWzFXzQ1aA5kXi+gNYaAi6ISRQGK4J4SQQpxWq9CoJneUEteq72vFquHN/C+HFLkgQWFsPhwBPS8pyC5+FwSMFK2zhX3CCiREZjwUDNWhJ4Wq1WnhyZpgnm87k3ozs/P/dBCHU1DH1L8WAwQGxwyFkkISepQx8Cz4HRK77f8SZk/XgIP5d4qikloaSzTuCadjRO8fj3y4osaGaj8TXRa3k+ANZqP37WrcQxyRFA717yV/BmTagQ/HfxNW2XpVSikCFDORhgZzZDWRJqSvd1jdFojLbtsNmsXTK08ro2HIQsFgtsNsH5mMjwrUMOajTVBipJMHSWCDs7M4zHY1y7dg1HR0fY3d1FUZQ9RJAeZ4b+GYXRkdJu67lAjHYwSiOlfN+yalxyE6LPmwraM8yDCcRhXns5eIifSWPC+XEHTzCJ7Aet/Ldv6/VoWV9kj9fUNE3Rdh0ePXqEum4gIHB2fo7JeIzz83MkSYLhYIAkST1NTUgBJeMA3Mn7K4XVeo3z8zNnwln517iJ5+Y7d6LRvWfFb8838msRo8n9ex1EGIPBZix1TyiMhkxdSUnwAxbGhtEQXna/w1X72x7fVRDyuc99Dt/85jd7P/vWt76FW7duASCS6pUrV/Df/tt/80HHfD7HF77wBfyNv/E3PpATFhFNx4IGshQSVkikSiFNFDohsK5aQBmUQmGnGEBDIKk20NbA6had6bDZLCEuEgzaISZTUj7M8gSz3SmqTQWWS9bGoGoadK6GaYwhhxWlkCkFUeTQRqOp3e9c5NnM55jPyT8lSROnmpqjLIn8x+WBRCknP04RLkOlTD4LD6olCXUrQD3xyte0440vEMLoPVTv7KIghzQ2dBSgcJBlXZDmkRCHJNgoy5OXFo8wOa37HyuC4mt8yAjS7p83eovRdzPF+RmMnzutNYR2MvpgXRHDXxqCMCHgnyqAjJ5sA98ovfU0B+8TQIg+FMqyyP6eWLdpiiDM1bYtTk5OeuPPmaJ088TrOTgGPHvZcBCSudKJlOQrQQEH1cZZiCnPc9yY3kReFEgShaIgcmFAiIzbOLRH9TYbciqt6xpnZ2fuZxXW6xVOT0/wta993c8jD7MrhTRJMdvdRV7kToo89ehfkqQeSSmKwpNm9/b2fAcG81VYWpwz01ix8pLumiUzLWOpPq9c90PTxt5BfQ+beL4KAZedlv5+tG3js3x+PZdn4k4XKUNZIt6ouq7pZfAA+fIwmTNz7ZQqSSBl6km8Qgi0HXVwcZl3NBxhNBzBWovbt2+5jTZ0pnQdcce4ls/+LFprxzXaoGmcrEDXYj5feBfq1WoJKciJlV139/cPcHh4gBdffNHNt9QHGG3b+G4yds1tHKLChOnlcoGqqnxHixDCo7lZnlF3irG9wEQIODL2xj0/nfsdqSDH9zYORrMsB5fQOAjhsQslqRpcMqvrGqsVEYuzLHP3SvX4D/R8USswBz4U2IVnWQggywoMBilWyzX++2/8JoQUrk1YYTQcekRwf38fZVEiy3PkRe7X/jiBK5zBYF3X+MoffQUPHj7Egwf3kWXE7eHSOqvYxtYKeZZhPB6iLHLPXaNrZ6NL2VsQm7rBerUmnymXaHNZrXUlrbbtMJ7sQKUJhEOYSfbBeWvZcC+cZmic433Px3cVhPydv/N38NnPfhY/93M/h7/0l/4Sfvd3fxe/+Iu/iF/8xV8EQNHk3/7bfxv/5J/8Ezz//PO+RffatWv4C3/hL3z/Z+sPjl7p377W7/5YCEBT1q4ShUxRp4u3DTMG1tkbUytl6hjllLHkWe6FdTiogNu0Y9U7XoiUkhCarLohBCy/1hG5AG5zFMjzAm3rDJak9A8KQfNkxxwL6fSzchu4Qe6IoeiwOfQ9Eygj4AXTZTFSQnDWZgJpkP4mHQj/fcbCCOG/WwgKBH22GWWoxlDpg70TttG6fqYLHyj1sJQnzOz3K/1cOvg6EPEGLgU5cFkGXVTvdxbuvdvOqNsb2fbvos++9JowRk3TPPm0o0ycz5tk6YmcVxbUkZMX5Dgccy+apvGLC9f62fWXHIonrv5OfKWYpU8ZWI35fI7zc+YftD57rGtakFm4i6TMtSP9Ui1+5/zMi7oFDRZCdGazmdc8YYv5uq4xHlNWH8vaA/BBmEdChACUSz8Clg1jaX7xs2SshZQGxrz/fBEiZOEc7FvboOvei8cUTNH4GetzQAKaaYwGd28BgYxIc10BkEgQvj/U/PuBEjsTU7A/dN8Z3Gx5HSL798Z1X1BgslotPbS/XtNYnp+foapqrFYrLJcLf2+VSnD9+nUcHR1hNpvh8PAAaZq60kgbEhKEebyN3vJ/Uxt757qDGKEw3oAtTpQY1aKft/4exAFHfJ3xveJWXA5CYpSSgxAO/OJSDr+XURTmojH6wq64/Hnx+xh55dfVde0l3o0j6g4GA0zGE98hORhQ52QZ2UsQcZVWzLIssTPdIVPNx8c4PT3BZrOOEHBeD6xfL/38U0GoMFpAwOuPiNZUCwrYu66DjoJpjuoNt+h2Oloz4d8bf24IRD6YAAT4LoOQH/qhH8Iv//Iv42d+5mfwsz/7s3j66afx8z//8/grf+Wv+Nf83b/7d7FarfDX//pfx/n5OT7/+c/jP//n//wBaYQAXIThhQRwj7u1kNZCGgvZaaDpIJRBqhQKqVCqBGWSQBigg4GBhe0aVOslhDVYXJyja1vnz7CDJFFYzOcU3BjtF2w+wgMRaop5HuBgICxADMvzpF4tl7QIuOxXOSQECIsTTzARb+TC9l7DrwtwdljYCKoMkDbB933EJN546RyDlXX8d7zAwlKZizNw3rAZ8+jLU6v3WNRDVhtH1zGUGkodvMjrJ3zW1oMRblF4hQXE1g858OhD4TGqEa7l/+RB56N6i40xQZum6zqsN2ukSYrlcoW4UyTPC98qzCWVcjBA4XREJpOJ2+wpCAn3O5Q8eA4ppXDjxg13D4yfG3VduXlgXbZZYbVchfkE67vdqNOL5j7xGeaIlTBZ/Go0IgSHuAljJEnqA3Au6SSJwng0QlkWKMsBptMJlCK3T6USDIcDjNy1p2nmkcRYa8P9I77ZEcQfoGl6ZuLuDuGCiMZ9BDurRiR1HZAS5kNwUJFlqXeg5Z9XVQWLIBIWt7Dy86sN8R0g4JMVIuWGZzWgnsJ/FkBt1Vp3jshKKMnBwYFPtGK0RgjhbQzyPHNrQHCqhSsTMoeG1jE6z8lkik984hM4PDzEw4cPcXZ25tZDeu45mLXWoq5qx7dpwJ1soTQW1i0uK/NQ8eu5E8cN5PaT459l7hbh+Ze7DrbhcIgsTYmDIeDKGIByQl/j0QhP3SSxv69+9ato29bzn5ivwSgZtfKy5YFE5tZqaywu5hdeAI9RwcQFNkwj6Jxyd1GWmE6mMIakH8gGovLGlyGIsk7XSvu1vCxKjJweUAiEQqVAOqTVuvnPiqlt13oEkbVGICU0AO04d9qayNmb1b6VT0wto8hPGInv5fiuFVN/8id/Ej/5kz/5nr8XQuBnf/Zn8bM/+7Pf14l9u8NvxP4nFIQobSAtILoWMApJCUAq5EqhSBSsATamRWcMdNei0wYwBovFnGrmgyF2JlMIC2RpDq0NavfgshIdBUCxy6SAlH0fijgCN0Z7MmDbdKjqja/dc/2NHxxejLxMtwi1UO6c4A2eFvOQfbJmQJpKvxjENtdPvH8iRPlMiopr2wxr+04FY6jspCPIGqCwztIi+aTN+0k1ej4PHr84q+LPoEzMom0vO0te+jzL+VXvFS4QiX4q3MMaeaA86XNJYvz/bCASM/X5D/MxOBjhTRMAjKEODkIOVBhTCCi3AIYNPvGdWzzupBa759vMZ7MZqbQeHVKnTzlwnh6p896Rfj4tFgs8fvzYtxRXVeVVYauq8iWds7NTLBYLNE3r9Da0z9558+R20/A8UXsmW9AfHR1iMplgd3cX169fd+gO8VBmsxn294kgO53uOG5L2uOaEYLnqSQwUVwSb/7x5szn0nXEG+F5SYJSwgfZHIRQO65yzzFL/pMfSkwir93GymRYGkcaa+ZCGGPQdNTRErogwvPF6wQfSiXODyU87xSItFuvU5HGSCxhD9/GGZ8r+wmF66TsXAjq6HnppZdw9epVvPnmm3j48GFPlkA6wuNms/G8JUbR+A8g/DlnWeoIrPQUM1eB16OYhMnjwcgJm/xxEKu1QZo2vuWYW2kZye0lbgBGwwGu37hO5fEkRdtSoDkej73IFyeSrbOHgPssVm5drVaYX1D5fb1e+/sM9zy3bty51b4oCozHE7cH0FWl0fPApci2DUmwRxmLHAPX8t8ZDeGMYjgAYbQabr5rrdG44Mm4IEO47j0hJQyCJoiyYe3hhJIUqV1iGM2ZD+L48HnHCAEuEPvNw4dlFhCkpCotdc4IrQHdIQEwzHNI3WFVdWiMJk8WRYyBtqY+/LZpoL2wTgJjMscN6QApwRLjLNVirIHRbg4J6UoSEUzpyhxKKaRZ5jaPiBQVbYAccACRxwXgDOMAGBPUX30WEVAHDkw6nQWEJfodoqBNOKt4grNDRk2LKLdWBvgyNsPK0owgVgd9GkZOsC0n3Ydf6efxzGXORJjUASqPORWx4dmTyiABChHRz7YDn0sBhaHgafszt/kuH8wRFtb3fdUWf8GXk3zJS0S/5zkQ+RLxXBEAOhBGZQ3Wa+XbgtMk8aU1EoCyyPPcGbddIM9ynJ+fOdGnbVE2bu1UpHuzWvmF2VrjW4vbtkVZlmjbFjs7O6i8w7RzKG7qiPRHWVxsukabeig9LJdLkOw3lR9ImGrkuyvG41FATlSCgZP6TpLIM6gsvJZFkqQQMrQWx+hiQDUSj4pwt0TikvHYQJBN/3jeAmz8Zi8FlNZaj2wAASF90lzlPyxICBhoHYL2gAbTs0z3TsBabmu+3K3D95qeeZpToc3X+M057iKig9EKQAhaV4bDIW7cuO4DxYODAx/A8Jix0NtisYDWnSPKspkatxG30fUyusx6IsSpYRJqQEX719S2jQu8tAt+iCujVOLRPcB1RmoTzT36zrwocHh4CN1p7O3tYTabQSmFxWLhz4nlzPk+pWkKMOLgNmtGMbg0yQghlaXCmqgSMsDz8y5GsV1iGuaCAZdlQgLKLfDSBR2BbiCFgBL0c/AcYo0SZ5AnpYS2Bq2mEg3cOUhG5aPv90Z8tGACVgSC6gdwfLiCEAEaLPa8uITOOwEzAAnoYWvaGgYaRapwNJmgMh0W9QabpkOSJ5BpCgiJ9WKBar3BZDTFdLyG0R1GgyEtMFb76NFYhxC4kkSnSe1USkmwpZTOvlsH2B9AmufIhIDVFmZADz1rgxhuHZQSaQSh9RckynrD5hxq0T3kRDlvhygIybKMVEBFKNlQEMKQJHNTMp89vmcZBfD28LrT5KOgDRpHDOMFiPk2/TptvwsobKL8fSTKIwRrQcDX95XK43jtPc+N5wRzFjjjsiD+gkXobgIEqCz85ODmgzriste3O7QOyA17V1zi4FgKAAFG3Qiq53KhsVxO0kALNEJis9n4z4nRQyEIMZFSUWzvEKKkJ4aVen4JcxX4bzIDzHBwcIjBoMRstuNtHEK5J5RXWDcnJlHO5xeoqgrHx8c+sFm7tmMKPjo8fPjIb9isWxFvmH6OOZh8MBiicBnwwcE+iqLAjRs3sLOzg+FwiKkTdDs8PKTa/M4UOzs77r7RfRkMBgAINWL0KHH3W2uDTpOSMpmuwdXVWyhXr6fx7PwzoTVlK2mW+Gx9vV4hlJjDs2Adp4z/W8u4TVWiyAu6r8yfsIyKWVRV45EILg/xZ7dt5z+DBcyYP5JlqVfM5Q2dUVL6DOkTFSZK7+/vQWuDzYZ8SaQMmiDMKVos5t5Lif9mxdTNZoPT0xOHpl1EisGVnx9cGurcOtnU2o83XRMhbPGaxYZ6VMIiPgaEQN1QSYr1VvI8R+J4S5/65A/g2pUr+MIXvoC6rvHgwQPcuXPXezORIm7tg+CiKN186WC0RqIUJo4wXpYDJElCwVbX0ni6uc/JpzGkmg3Ao+KMziJa20kskTWrEmR56oXGUpUgcyWoRlLfrBQKSiooioBhnSLzZrNB27WOYJyg6TqsqgqN7igZFwnSPEPqZO45YE1UCggFoS1gyMn+j28QAvhavicA9FAQuGw4aIgIayCMhoRErhQMLBII4o8AkI7CQ3W1SBVQk8FYitS7FIrou4URsO77Yx4IAPhOEzDxUXhFPYAiS0945XPny4sIWfSreAPrd5HEZRN+rTQCgMvknNIrBGVuIWoWXq1RCCLzUqaRQMr+tfR5E6F9TkqJTnaQ2sldI9yHbbIYbxJCMNHLuowtZPuBmOfuoGWFTH5NWEjfM1iw/gOIsyL7/BcrLYI4WXzr+6Z9H1Qwsh3IfWfoinV/uP4dwoYnITShNHN5voTppcN1+7db/x+i7egG22B+xdkY6z5kWeYhZuZzDMoS48nEScaTBgL7e3DmysEtL5plSa2fRcFwP10nk1UZipbOdZhRloAmhFIE/6Gs2pEzna9I7joThsMh2rZx3UGE3oxGI1RV7UshZVn2umk4CKnr2pMJOdjLU9dWbSgRISQEnsvAqGUIKPrjLhBaQbnmDsEbfFwy7HeghTKlccvc1txy9Xz2x7q8fsBdm4mu0/hgg0otwfQuft62n4tQqpI+qCzLwnNl+GcchIzHY++5w75am03lu3WyjIieWZZhuVyhbRpsqg3Yr4lFvDi5qx2Phjdp1tWIk7JQWpO9LquY0xSQEC7pEKo2251hb28PFxcXIYmJXh93StH9Cwlj3FQgJTneSiNheTwBL2LGiVL8PhG9rl+eDnwQzzXhMh2PC48N4ETjt4Jadx1JkkA5d23f/RgArzCn4nF3iKywjKB9cMeHKgjhDR0OygyLLGH51hVJrLEQuoU0EmkiYa2EMhZWaxhtMJQKTZqitSD3UikBlQHKYj1f4CQ5RpplGE3IV+b8/Axt0wBSgLsypStnGGWgTIDGOJI1klpcYy1/gsoJalRCEDLCk4zhQX69g2HjId/eMLkzx98dh9z7Pv0uqCVWm41f2LjLIBYdEwCyLPc1VYaoWcsi5qFQ7Vn1HjxeeHgR8A+TDS2OLD4VINWwsDIZLtSB+/352/oLTzpi9Mjzc5z3QvxwMfLEom/x4hVvBDER+fs9+pvB+z3E20EnefpAMCwbzSV3j5VUsMags9a/DwCVB0Wk0cCBOv3S/22jOSqk8psiQBuyz0S3BKSUkkidLPXbb7+FLMv8n4DkCMdDSZGmGQaD0pFJhz1lSymFc0od4uDg0HNjEC+kbt5wjZ65B9x22jQNFnNqNawdv4nnrdYa7777Lu7ff+A3UQA+6CrKwruccgBFsuClE2ajksP+/h4G5QCFI8kmCV0L8W0yakeNnp/UPT+sLiuEgEro2nJnkggIWDfvfClKkiImB/fxeANA1xICyzB+/FgIEZCYuKwiBJc6+m393NatlHIok/ZjHicVMVEyKLdeJoxr3W9dH4+GGA8H6DSVOpjfwGtC29beI6nrWrStRu08eBaLpSOCEuqqtUZdBZSEuXarFeum0DyYz+c4OzvFaDTCzZs3sb+/7wNka6nUzudfVRVt8EmKvCjxp/7U/wsvvvhR/M//+T+xds6zp6enPS4LC/NJSe3Vxmg/BlQ2oi4XFcm20x4Fb9NBASw9K1JJyEigkZ9J43g1y+UKu7u7eObpp3FwcIBnnn4aN2/cJAd37uABHCGVPktEY9x1Ldq6RiIV9vb2MB6PICVQVRvUTe3HhMYVaJsWptMQsEh4r4OEAZeH4zXk+zs+VEEIgN6GYq3LCFwAEpJA431llDXILJVpOk3qdYUUKCQ94FXXwgoFji7qzQaLizlG4zGy/T2/cXN5ZdsXgU2l4iiWH1xuTwNcMGKYQEiBVCJDe55VTGgLLqrWcvOr2yNEuEZeVPh84vphzMegN7QI9jz9Nsd4003TDImT3eaMNHMS3bxZBGluH4C7Barfzhqz9bn/n30Sghx3IL5S+SYBtTgKfx+C6VnQb3jvox+E8Dh4Ip5rb2R4PL7fzDCPj7hW//0c330A0ud8UCkptOvFh4zmXC8AQchgqJRjHNoRvz96kOgNIVCNNkUAvo7fO1vnwSOEQJLlfs6zVgqPAXfkZFmGgWP0HxwcYDgcYjQaeaGzw8NDL3jGREJ2cU1dyYjLe1prrFYrNE3r4X5qmzz1RFmG8tmfh3/HBoFt2+LCkWcZ+SGkj4IsLt1MJhMcHFDZ5ubNm5hMJphOp9jd3fWdR1mWYrozdYu7DIjOgDV/El+2IclrAYmw8fDItm1LEL2ADxZCp0rYVHyALMI86K9BcguFoZWEA6x4XsbrF38uP5fMHYk/OyAngc8RZPqlnzMcOOV5jkGRw1rScTHRHKR7pXpbm9YGjVsrOKiIA4DaOZKfnJxgPp+jqiosFvS609NT8uA5PfUB5O7urtfv4MCK182AtFHZJklTfPSjH8Wzzz6LR48e4Q/+4A9wfn6O4+NjbyDJ98cHbrrzQUiMtgghUIii59sTj2eiFJKsL+/OQ2WsgbAScDwqLqceHh7i6tWrODg4xN7ubkjQTKzh5At8gRPSkT+VFALj8Qij0QiA8G7y2pCshNer0dSIQeumhBAW1rFOCA354ErXH7IghCtR1v8fYF1ZhPM9C2ElpDGAFFBawzqWu+o6pNZiqFKYHFCG0AYNgVq7LKtpUVcVEtcLLl2WMJ1OyUq9q6kcEwUbvFE0bQNGJOh3qgelAxxQBBU8/p2IoTjbV1Xk0g5xGkxvcYkfeL5H/DDY6DvCHQz/iJEDAK4DKPAohBCuttwnuLImBX801577AU2KosjhM20EMi0T24CgfmiMQZZ10aKgfQASX2e/a6SPplhrqGtnK2DhayEou0+64/MQ8rJJH58bBXPwBDO+39vZaVwi4Ogx/kz/2RwwxvO6F1tw6BneT+QwRgDDuGljYOHIZVsLg7WgxSMqUz3x2EpstoOm936r31Gja0f/WhECGP49EfaMI74WOD4eIk0T3Lv3ruclsSQ1ayxkWTBHYy0HJjkHTggwGo28syqXcXhD5c2MA5Mu0j6JkbGgDpv6YJpfc//+PZyeniBNM09qJY6MwmA4wKAsyKXUoTzj8RhFXiDPqUtDJQplkUMlCTKnipskKcrhgEiUInTocGsnHyQOl7jEyw9wlAwE9Ig2Eo2269zLwroUI5Q01v0yC9CXIGBULASh1r8vKJuqS4EMB/pt26ICnXKn+4E9vZ42Nd5AjbHQUZmEx4GRQBIyo/kz29khTZuq6gnvLRZznJ0Rufrq1WsYDofY3d2NCO4cpIV2YH62OYB89tln8aM/+qM4PT3FwcEB5vM5VqsVNpuNL0sTUrltBwA33+n5rFkXyD0j7NPCXVNUtnFeV8b4dY94dsZ399x86iaee+55HB0dYTKhrho2AQwJJ60VSpGCMEn4t54jI6TwwT+rNVtrSR7ejbtQASUkJM7tKRaQUF55XEBhe835Xo4PVRASlm73R3Aosi3dRoZ2wgqkbUfCWdagExaQErMsQ5nlyDoN03VotEFTk+R2vd6g0wCEwGq1RurIWsWgwGK5wOPTx2RE5yYNTyJtNDabCtYaUrVkElIS2dTzZuYGlwOPOBL2cCtn672SQecfRAJWjLeHjjc6pRwPBf3NIIZ2rav/U4XHbWhd2Mi4Yya0sDroX8kguuOuizcLWqzos/I8R9cNe4sTK3byv2OkglsfrUWEggQYmt8Xmzyx7Dj37VtrYXVQTOQSQuxhwzV5Xox5Ee2Vphx6QP9PKpZ8Lryh8R/O/gBcCoqEFdA2kCg9asXtxwjBDY3Fk7tnOFuOiZjMrbnsz7MdiHB579LHchF564eh3PNtDwEIQVms8UhNuId8tG3QpmAC4aNHDy8FcTJ6BnjMM4ewFEXuBdCmU9IVmU6nyPMcs9nMe9js7u76Lhlf/vBzTvmFu6oom57P5x4Zoc6b2v9stVo7AmWF+XwOrTUePHgArTunErr0yA89B1Si+v+x9y+xtm3bVSDY+hjzs9bav3POPffd+y7mvefAP2EIQWaAQ4CUFSSUCiFTRKJgoACCArKQQEay+VhYFhQsCwqWoGTER6JEIVJpCkiRSsRPSEBEBplBgv2Mn99993c++7PWmnOOMXoWeu9jjDnXWnvvc+99jjxyjPfO3XvPNdf8jk/rrffeuq+Cd58+fYozFay6uJRCge+88w7W6xXONhucnZ3j7GyDr37wPbl2j6VerjcbvXeJwWm14Ji5X+o3V3Ng9pmIl3HWhLBna+8315aiumIsz8Zq3Y8szdYqwxKVAnPGvtTsYj2Ox3GaHWvW47jItdfHAlAC7tX9VwfUojJuYgakJU5oHI3+tSymLrOzy3lWvivMz3ot89vv+T3/HX7wB38An3zyKf7Vv/pX+Oyzz/Ctb30L3/nOd7Db7XKQbYhSr8fmSeaUA6/TXWGm55mDSXRZzkrhP6dxInZNW637841vfAPf8z3fg+/7vu/Dj/zIj+Ddd9/NFdtjjJmh6bteRDn1eDFG7Mch19e5vb2VmJenT3Gh6sr2jrwXg9mbUjcTOAowDxxBDDRwaMjBQwrFpt+MIMSauSmyC8IAiRmgLEGpAEDMIGa4lETIDEmkpsmhdQkNESKRhKeyBXaJRR1DKAGdFa1fT7D1omXggKvPHtVovgDWvzsAcKaAauh9TtfPvwMoEXdgpeeJy1iS+m+es/W2QMyDbkvu/kypD6VKZ/1c6iqdJlTlvQx05rIw5OemJ7fj2Gf1sepnYwFbzmm9FH1vmTWJCaEpxQHz8ZcDh+ZuvsJaHb6XY243u676ueVzVMesWa6D5kp6dz2wT/Uhs7iW25bN7vgAhSwAyKP76pFWXIZc9SfWsxolVK5ALLSHNVhkwRHJ8GEY0DRerb6Ua+fYomwW8zSJhTmOQ5bgrhVkLT7EJnrrn7awWdZKjAEm/GZ+exGganOsiS0oFueU5QGcZauIpo6j4sJoVFwqi2hpOfjEwGq1xoVWLW67TnVZ/DwbScG+r4CaxKI5TRt2msHjcuqlo3kfXoK+uk97dUvl+DttBriP9d+lK3jpxlwyrvU1lH2Qn6e4jGwuAAxE1McjKEujMz05zscBTHG2my3+5frn5y9zpKU4F0Pq8vISIQS8++67edF2TrLNVqtVzuAahv3sWW2321lWlOiM1MVGo2rZrFCr75ZYvBJ0+vz5c7z//vv4yrtfwdXVpbIY/iCOrWbXM3vOBtKkKnxSo7FV46t25dgx8jphi5nZ/GQcm4M4EL8cl8xbB0JKhy9AxPypKT8xgk/iH+MYQJwATmh1kln1Hs4T9nBYkQTiCRgRwIIQEUbR2u9CxNnVGfrNCvtxfxATYhMBIKmueQG0gWKdQv/lmMEH7tMml+KOAZh9+ZuL791+SocsNpExLbyYFAgoqX2zVrJa7HiFOSmTjIEfW4BN4huwCc3BuTu8evV6BiBMxdK22THM8rH9jMq2yPZ6PwlwlG57fn6mk45cXwwBk1GT+qxTSrkSsE0Ce43Mz/5ULjEhVvgwx2FAgoltku7a7ihomTFd+Z3NMziMDbDrc1rfoV4gjMK245S+zkCcu2ce6kRMyrLou5u3emJ/BOtx+iwAanVZPlCt1dlx8a2Hz2nvTADAlJmU169fwwKkTSW161p9TzJZei+1mnzToFcW5ezsHH3fo23b/F0JkG3UShYX0DvvvJNjQ+rxbuyjVUc2GtxiAIZBgvymccqqmbv9DpPKp3/66WeIMeC//Of/L0IMaLLIYIP1+kxdNcKi9n2Py6urGTuwWW+konIj6bFN0+Dq6koZFq2903Z4+vQZzs/O0SnQkUKBDWohM2bOImTeqaaE9WsAISXUmj7GeNaWPDOU4ahdhHPAYHpDdoza0DiMZ5MYMO8PXZjCppSUVbuebMSkerwJgFivV2pcxTwGzYDqOtPoQDZoxjHk36244nq9wfPnDr/7d//uLLw2DHsFH3cIYVIQMmjM26QM241UaVcFYQMr0xRyAUmZmyS9V8T8xtw3Rfr9fWzONvgdP/w78AM/+AN4+uQJvvGNb2DVr/JYMCAOIM8JMUWkKc1ib8ZhwO3tbZaRX63XUhNNhdNSEE8AJdHYEkNehrdL0iscVIuEAcne+03MhFivtuU2WYRINvhEPZWBXETNJYJXgNCwFOBpQGhI/jlocTVlQzgmCeQxkSINLquBAYC8QNZpW3KJ87iPTGHkdv/Lqy1nO559WyYBwasiU1wLgyVgKcB1BPXT0e2F5C3HK1ZORtVxbknUFKyxHvVxawXAti2ApH5eltpX3D/1OepJrVhtVkfD/g4hYBwGQK2ekgqdqliTJPEVOpnWgXSIQLJniSLGZn56C0wmopwFVb+fJXAAMAMiJcNn4fqheUVWAY7lexYwO+t3bj7ZL1sBnSQzysLV8wWIj9PnyvcOzIDNAd6gAyamXNd82zzmiWf71VV3bZ8YxmqcCdhdbSSL5fLySlVgxe1h2S4lGJYyuBGF2HXFQqyq9zVPjzcXwN3dLbY7qWr84sULjIMESt7e3WIYbEHa47PPPsV+v6vuxeV5xuqXrFYrXF1d5VLuALQ2yYUG7J5JIcDnz/HOO6J4u91uNV5CDJPz87PskjLjjKiunyLn987Bu/lz53D44mqFWAswz7FYlVVu76VY+CVWqJ4363FQzze2b81YGACUwNQBxoaZKFwdjM+MPA8RzY2pEuA7X/rsM5lHHLxHNU+t8ZWvfKVieLiqUBwzCKkDnq9fX2MYR+z3OwUuooNimib7/R5TmLDf7xAUkJjr7ezsDGdnZ/j617+Gq6sr/MAPfD9+6Ad/sPQJ5zDs95jGkv1V3wfrWlM/65AiRp3/mqbNTGIdpI8kBoTEe8jrL6sCAawsCDPqT75oe+tASH3LDLX2CDlOq+wn6qKeAUoAW4E5D7gg0rStI6zaVirwugkhAZHFEg7ThP1WOtnZcIa47tH4BpcXVxinEbe3glxrV42ojZJWik1gduWiDiZiXmw8TbvnnxWNypzgfaEY6+DMmALAptZ6igalvBZYqwNBC2WrLI8vLpNlVdGSwQKI0JhNcMW6t38mZy2LbpnUTeTIOZf1KIrvuYCWEoVP+bMsJQ5b2yiDEOfEOkhJ4ng4cbaAExf3TYxRGJNUwIKBlnqCTFxYCgMrMUVhXarPCiNWJucsI65j2CyXPCGzBsMmPjjnDBRW53qoMaoJiefbjxAUv0FNigMuQUj9JzNmfUgWE5rtK8C4uCDBUpgsB27q4jQOA8I0AczY3skELCXXPT777NMsomZMSB0Ma4GpvYqDmUvH2AoLys4igA7glLBZb6S+x8V5vobt9ocgqqFbEV5TgyfGhP1+1DElN1do+xJQyynh9vYWAPDZZ58BAL7167+eA3mtBs+TqyfYbM7Qdb1WCRZBNREY2+QaQ6uVpNp7J4ChSPM32JzJ921RNGbIalKJy4nByqaYkJixmgZ2BLyXd2pxbgfulcrgqgPjLXaszEtS90Xee3EnFbl76evOuRwvNcsWxBxwWP8Sd12br0lKC5SYK5vnndaaaZsiONe2rawtpiCdInb7IQeFGjuy20mWlmWkhDBhP+wRY8CdBtSaDkjf93j33XexXq/xwQcf4OLiIrMfAPIc4Z1UQwagomgVCwxGSBGT1o2xmJ7NmbgAWVnhaRiRJpWhZ8mBETaEQBpbKfDD4Ii4Y/g3qzumbtldtQAhIlYmf3gFBQxCo9od3kVEJnRdg3Xbgok04IYRE5A0T3633Urhn2FEnCIa1+Dy6grDMODm5joL7NgAaFoBIUChvzlVTEi9ChjULH/obvMBauCjwiB5PwDoOqVPM6KNmALNUG4+DpAHLhEdLEApK/MV2vaYpLUEhIrrh6jQ0XbttijYxGIDuTA1hb6vFVxt0jIwYnLLUleiq8BeoxZrN/f5ty1W/Uqiw91cuyVTtsw4Oz+bgTfkybFU/ExKVdbBrTFGDKMVZ5NUytp1YpSwxRRlCwxcBJMqutqurX6fxxiQzAboZ1aMqs4AmrU8DxXGEIkP9qnW9HtZle9Goyrr4nibsx5mxdtnZhmbMF8+llm/qWRJjeqv3+/2pd9XfbqcY3GNVKpcGzA5Pz/TGjVXePbsnZxG3LYtLi8vcHEhDMv5uTAWF5cXWGvtHenDlK+hpJwOePHZy+wuCErPf+c738k0vmlfvNKUYguKnFRcsU6r71Xvx1iJOrj1nXfewfPnz3NAb9apcKTqsu9itVrhgw9Ejv3Jkye5ynfXmfvDo2lkPjL19ykEqcNVvbNcg4ekUFxixqQpujaelgDEAILNQ3UsmB5Zx+7cUJL0Z9I5UI5Zp5TbmKrdnvW8I0ZNl+crAYFTFkw7OzuXlNrGo/EOISb4ptXjngMA2sajU1dxqjB/ubc5UxrChGHUopBxbtgVBlmywZqmwTAMWUCtbVuRfncOrca+TKmK7yC5hpBEmt1YGeaUmZYUE/a7Hcb9gDiJK8rcMAWAyO8uwxAZi4xSfuSLtrcKhBDUVzU36qq2oGwhjwssoIRYK+1ykkBVZjRQt4xzaFxCMDSjiNZS+sZxBAhofIPUSCfo2i7HgTCnImCmLgBDi0ZJUn1hn+vu7R6Xk2Zd6prlGrloNViw7SFLXv4w91FNOdv2utX0eB20aucuoOKUu8Dp9VbXweJUSyrRbhagqVDa85PJwqsyo4OVTc9ZD22LFIXWbHyTQYjzlXtIKXpvRUBsYiCrkVDVy4GwYgZEUkpoNK0uVoJLVhSqji+JIWbAYJZZnkxrkFCxKvlZ8Pzd5IVSwZSHpmr6I6OgmuikGqb2ZaEOUB00d6mTYOaRLS8iyuYsuqruVP1dvANHdjS8XvVN8AKw2AGU5ZG7qD6zZ1aVRK+edTnP8SDhMpEbkBaJJktLH4voDhrfYLtdo/Ee2+0dbm5M30Rq2Zyfn+fMnq7v4YjQtPN4rBBipvaNvWyaUjyt7zpMIeRA1hCCiH7FiDBNmELIMUqC/2WxsMwdoAQ8TtOE29ubLIteA/6+X+Uqrre3t9hsRCPlnXeeoWkMbDUw95H3Dis1BCzsvXYBmOHQtU2OwYDWzqr7vO1fa43kODtfXG7Wz7wnm6Jz37F5IhPPfCxzbK6rJONSNXRQxd9V12aMbUoRwfpSKnN+PaSkhlbKAGDev+Zg1+7X4mzQtLBBYUaczaVyL1HjZSygv4CzmZEHSJAyERKEMY0aFxeTKFubQQSWMgem3KrT7IGT5Qg8P/nJ52lvFQgBBIB4BSFOX7YFwskzNDl2e0QM1pTdJjoQM5o4gZHQR4fAQjGceQ8CgyMjJIARMUwjJo64ub1BAmNztsHl00u0TYOnl1dYNS12O/H5kSO0nbgMJEjJUG3lJ3Xm6//8928AwTpnrSRqwZxtZx1awYItoiyiNYnLIloGnAkSzYWMxN9bzl/TxHb+OtCrvs7qqlEPrvr4JmQm11H0Beqv16CmZkzkp1mssiB0bSkKBWDGnBiVvlqt0Gvqp018TdPAeQtGbEAEbGiTn7Nd7yxGgSUIzNw20zQhqfKrVSO1XP9jFYrr51gDgbygzACePgcQGm4kQPZEy882JYRkMvmLNHYqi4YVl/t8bTm5wnwlc55PJ7hsHYLB6bi0+BHfKpwvLF51o4C5wPIz0+wOC7asDmm6GHXmx+y6IQuSubDsuEFBJwHYbu9ARPj000/RmKWv/dE3Hl6FzkrtnVb2y3S+w9nZWtOIz3B2do6ubbMrxVKL+77H17/+dfiK6bMmfViK81kMxDSNORj29etr7HZ7bLe7nG58fX2txeTu8PHHH8/iuIwtEYapBFKLq8FcVa0KfnVYrSS48WyzwftffR+rvsf5xYXWUinukIuLC62EfImnT5+i7zpcPXmi8gWHmYA2Psvrrd3D1v8lhgVg7PYDRtWfsRRgW7il/EapdAsAq5Wo4sYYsdttNT6CwexAlJCSpdqX9HsJgi8KsYXlnY9LgDBNjB2bjpO5YavMI1+KkxLRzFXb9V0WUyRCnjOCCcOpcSXlEcqzS5xwd3dXroNKphjU7TOOI8ZpwqjPY7NeY7NeY9gPGIdR3DEhyLVWganGglTmfBmesOIoXxyIvF0gxMCGGl0z1KbW4xKjGRAhQIJVWVN1KcGD0YCVCSE0JnKmuiOJI5AIQZmQfqWWjPfomg6pFVdNSknihqsJaXbJbEiJ8gT98I0WNoLyNvvo2IuvFmpHs10iSRqbUzofCUgugcxVZNw8FeRtzdwschsFsMjfVpHTMmLMEjlixZMBkerZMOvAX9ZzSUceUQFftUupZm2891kO2Vqt9GpxIRJkJfV0WpWpBxEaPb7EtGhqsXOnhxkRUiXENY2TgJJR6PGYIvwoKaEgmk2qS4vLrDghKAoIqSccC5Ctn9+xlrfrpCRMwhJkFPfaLDh3wcLc346zXQRIrYwjH8hYZcUZVZ+2L842VJ9XzEnpg/V1cunGqMBQdWhj1PK2A6C8OL3+wSzGCQAIVltSPPVJNH5goU1i5/Neqs92bYvziwtcXFxivVrDKhkbZe+cg1cQY8Gx1pfF9XOlpenlhqdxxM3tDaZxwmq1wd3dHe7u7mDiggI2JSvDALBp6UgmkWhUjNOIGCJuNNjSXDUFhEjRwrVm6ozjiNV6hasrUZc1l6v3Htu7LXpNY2UWkTGv8TfyXAqIqwPO63dTGAs1OJw8QwAzYFbGgnWSpWS9/GuqQN/Ddz0fU/YdZgWwyibb9YgX3uYfzgYGoMUjGbMaXXZMZpbMTUPlhCwwNutM9gwMBDfz/sQMpFiCbZ0vyrMZ6KggZ2bnCVkLBMxIIWbXpTGLMh0v+3hZhWjZ779ge7tACIQFafQhJeKcGZPqyWX2DV3QIRohzIQmBTB5dDGCo1g4T7sWPXvs7raYph3QNGDyYIrY7reYUgARY7Pu4cjhrOuxbhrEYcRtSIBjpCmCfRKact3LZBuLIJhY+pRfIkEBVeWeKOCJqt951ifkMEq9MZUJ1gZbdQwAYGI0rgETl8yQJuUYBr1ARB3whe2YR0/PI+CpDMxkioGlLHgtdlQDkPkkI1ZIKdZ2fGGdbzsEMvljLgWhbCl1Co6IHLa7ncaZFAGkxjfCYmlasHMiNuWdx3q9qujqKkZGF4iaUhWavQUBGnBY4jfMsrSMAtGVSLleQ81oFTG0WL0DEZ3KzEni7DKo40csPiUDigqkNd7P3gHp58ysE7PG9VQMlxxXz6XvXLuyvruaMat+Vp/XrYYEzEuBQQ18y9embIlOjgKeq1RzrsdEDSAEwCZONsLqnpQXjOpG5r8yZ9Zm3h4JzBgSV8Qivc5xURDSEZJW3b67vcPLz16iaRp8+9d/XTPE2py9sLbieY2HI8su6+Abj816Da9BtGstztd2JQvNOxGcevrkCcDAV56/C4YA5WEs7iQi5IBcqy4bQ8Dr6+uc1bHbbSvQDK3vIplo//W//tdyTg38jlEKIppLtO1aiVNptWZQ0+Ds/Bxnmw1W6zXeefYMjcbMNN4YyXm6/uXlBS4vryQ9uV/BeafvWerArDerCsiIRtAmrnP3IL2eHKdydl4C95kzWAAk1T9Vc6OsL3KgWuSRo4J8mz9jERGEXocxWXUns/HH2lfAEKn+ajwBQNe2QNtilxhhihkMJ06F8QPBOdFICqOw3Y1v4EkCh0WobCfCdVG+t1qt0a/WuH51jd12hxQS+qYHAYhTxIgRcVIdEHJwXmLZ2JRshVeE1iZ/3Li4p71VIETYjOKO8TpfJHrYehPRsgQHglcXQ5sikKQI1Hnr0cDjky0jhAFwwpaACMO4xziNaBuPcXuBtmmw7ns03uHGvwZFATccIwAH3zo0XmIxAlQoK6PNEmds91SzNdA9iLiCIdq4/JKNXSBTfjbY7BjWvGqhMPhAZKxuIUaEVKSWa2RvCxNglCekMCsncLIgz1JzAvDVuebAgfKCNk9znd3qYhvz4bblfpEF9ddszbFWsw9mjdXKjDapCp3czVw6dbqxZUm0XSdusFZ+ir987nuu0xhrwGGgrU4/tErOpgRr8QLi0glIKNVujdK1YL78nrioTRJJ3ZxjTB0RwWnWjgXU1m6kFMWf7KjE1tQszjJ7KDMcJ0iOQnZwtfIrvV31Y/luybrCgjk6eeQ6nXn21kufy98/0Z+OYpA3adV1xgXLBwDTMJaryu/iMEh32d/bts1uxLaTxfnJkye4urzCer3G83ffRd/3+Mq77+JStUMuzi9ybErW39G+LNkxLmfXhBBy/3v58iV2O3HnvHjxIgfGjuOIly9f5sDYzz79VAK3p3k9puUcUgeaeu/x7J1nePrkKa6urvD1r38d/aqXGDsvcvUW8G+p1FYzpW1bnGu8TdsJWKO2Ebl8N3+GVi6pMGjyz5ND62XpszourjKaIrnZdTOjaN/oQTglMBUXFiCFMa1oqPcecJSZ8zIueTYGzBCsQYgxLWt91+N+hK774pZhB3gjOlWKgIAQVKV1lcQVycAwTtjtB5k3ogDzrl+h7XopGrgfwDGh860wI1NE4Cnft3MkIIQIUct6QJ0xXw4EectACAABEXBISEUVVbcnnXiWRBFlNkQXbZbgVIoRmEaQ92icQ+sIfeOx7jtE7xEsHkKtJ6lRsENsW3RtA69pouv1GhEJkYq1YBOZMcAHL6u2yMqGg3bU81I/D+8yJVu3pYW6HKDHGiuikw4o6oEh+Hydc1dMxTw5LXKkgEKUKOdZNXIvc/dJve3Inc//IkadonnqXutgsCNrjB7LPiuUry2mFqRnWUB1JdZa38T+7rou19KxwmeWbgwgL3y18FWJ/yigwM4hAbecU/hSktoRMqmHErk/TplpsQkzF+MLJdYnP5uqr81dQJV2QlUs0K7J9psB3IoqX4JI818z5n3EnjvZyIjzgNh8zMV1FiZkdqR7+vwSQtSsmc0FD7fHuL3snt7kWCf2eBBgm+vMFDsZgHOiUZGiKHROYULbtri5ucZms5GCgWtRXd1sNmhaYUiciqSt16scI2VZMnbeGgwb8Abk/a5WKzx9+hQhSDG5zJIqW2fgw45Rb7N09n4lwAcE3G3vcgxV3V8NIJn8/dOnT0X3pV/le1qtVuoOusyqso0qjZKOr37V6/hsMxti6dWWveaiQ/LzOlx5nHtho1AxjkROY1OKgZRSUfKtx8o89q6oz9Z9I4877deS1TUJq2NZM1VmlTAyRYG5Hq8gWQuDGjVWddjcs9LjkFVc7foy62PGBBESiZFPpIGuxthz+f2LtrcMhBA8CI3CjwRGBOCZMlQ9FV5HkMwYAsv+TIhhBO8SqGmwajy8a3CxavHUn2HPjFcxIoWIRIJEdrstXrx6hVXfY911aL1YE0+fPsEYJrze3SKkAGaS8ut6PqJTqHFpzb3h06CiPFrHG9TBjqz0nO13qjEYjn3O8rCFWCx2B+fKttxpiQD1fxsVbLEXs0FRXW99CbZoHEvVXF7qwxP5XEDKrOuT97sAaaZfUp9vv9/PgJRZHpQXZFFwXa83M4ahxKGUYNiLC5FbNo0Fm+AyPVwxMs6VYFjmeTCsMSjjIBbMFDQYNkw5bdeAyna7xU61bozZMGs1gz9G9cyQu6K9uxmjY2nYbg4sgaJ5YgtX/WzrZ5p94iHAagXlCTCzKXWWgo1ogjFqWROGSlxLqYB8wLnUb70wiI9BD19CWzJPx9oxlu8YKBGGSmOexhFEwN3dXe6P8srqWjlNBhC5qq8Ty9lcI7nOTi9Bm1dPJNbk/Pw8K3eenZ3BO4/n7zxfsH8SkF40NFxmU2KQKsd18bRxHPHy1UsMg9Tnubm5ATPj008/RYwRr169wm4rgf43Nzez95ozOgDxdjjC83ee4+pKBOgury5VfO45zjZnsKy4rutEb2O1xuXlBc4vLrBZb/D83edSPLBVBnQhEUAkgcZt28Lp7/Yabeqr358Ra/UYTZxK4Tgq78VAmzGUteGQ51BWlkIt2iLPr4G3KWYwI58RUmrluE4k+8dpwvXNDV5fX2OcJsA5KQ/hrCDhqHFCE1gDvBMzEhIigEgEJodo53RUUo8TEOkLMoba3jIQYjaQ/a+4M0jlUhf2M4B6qZfQVQdRTKWUAERZSJnhAbTOoWs8YlKmhC3c1eVSx9456QQsvsS265CIQQMV1qNiDcq1HHllNUP8JbSl9WTneGgipIoSt8EAlEVIjz63Virq0P7JZw+zLrNzP2JBeJN9Hp70a7aEFz8BwLQLlsedH9smFMvYsWPU7htJJ/ZFJySzKLUeioNzVgyPQFQrwQLOzYdp4z28nruZJGW4DW0WOjN2RG4IOUC2BiiAvHPmIsp2Xz/kxLkY37EAwpotKYFzPNun/n0JrOwc2c2DpFagFUWsQQjNQMjh0Do833Ls3cduPObz70Z7+JoAo/+FzSMwG4AUl580BYbqFqyZPHs/TdNgv9+haVoJIO17YXRjRNu1CCFgtVplQNn4RrNJbIE2GXjKC3edThsbycJrJ9MYEcYwJlM85czCGWjp2g6hFbavaRsRjdSYqsywGXNHku1igbchhsxC3K3vpC9Csk7CFLBer3F3d4eLuzup1aOshbm18jOiEofSti26vqQZkytCbTaOZ30yvxNNpU3zYplzdyAKu8HF4LMxVM9LJv1Qz1lLQUOwGg6k5UoggGIcpIBdqPSinAKRGIvLjFwR1jRXpvWmZEOMACZZOy0E4gQ5/UbtrQIhBMA7j843AEveMwD4hfXDR/5BPyEGfJKXPaUIQpI4kyDBVOdtg3dWHa7HEa+HQZgBCOsyhRF3eyCkCTe7MyRi+Mbj/NkV/H6P1+MWYZTJnJMotpqkKyGBqmv8MpotIOX5HC4EedJ/SGHTUK1a5V0nk3/XdbPOblUbTcArhJgD5uScEwAVTatS5GQxVWXTzCqI9XbKzTK7PNKLvP+JqJrig4fLA90m7hhRTeZ2AAMjdbbOHKxYcSw5xqEsuzEbn376WdZNsIm869rMhhT3Tj8DLUYdSx2dVlw+5HING/R2QwePYuaisUlOxLBCjjFJMWWLtWZKZv78JLonw1gWDzuHgYmImLFCrkxsLMmSDWCgVaEni2kBDkXZ7HN7J8XSLO8B/CasxglD4LvYHqvBshwDx++p9EOrXuycxnvZ4gxNC1WTqygVhxmDRyTMbolvatD4pqjAtiUGyrZl3Q8t6lcHjooeymoumtb32f3hGw/vPJ5cPYHzDh988IHEMnAR9stVfa0kQmIM45DjojKrp4yfjZlxkjpfIUosy8cff4y72zu8fv0aRJTrBPV9j67vclxJBk0k8TarfgXfeFyY0NzFhaZOl5iay8tLnJ2fYb1e4+nTZ+g60YTpu3727sr4Fba8NmBiLCUjmsYDbLF0xaCz52FGHjnKgK02mBJZeRGHXp+/FTIchgG//u1v49vf/jZub270ukTyf92vsN1u8emnn2IcR1ycn0NE3hwiMwISJidaTeRMlFKNTmYgSWLIbz4mRFGedx4uSZCNin+L28MoeC5F7QwHlENopUuWlF2ZOB1cTIBP6F2Ds67DlKRQseOEKCs7YgrgSa5jP43wU4tN26DfrBGJ4RoPhLmFbT5wymf/8hqziGkButBbjIErPsKl3//0wQBUrgc7Zv0TwGyREn2BYukX/6fE0pRAVouzEEl36LPI1/0l4bJy7ff58Is1YmzHKWaEqLZO55ZHXoe5CCLZJFov1CY7XdKYSylyCb7zCy2TPsuIiz5Dg5TO1N/NAMSvbTS4veu5a8fpWDh8sGY1moxzCAH96z5LSVugnqnFTqEU3ps0RsVaLSdvtHltcdsztonVGjPDWzHGg+daLLsapOTzVFla9v35u324j9zHOHyZDMibH+vw+g/7ZaleWscJFHesjn0LrlSdmGNtHI2pcrPvAZiJHc60dPRn/btzDk+eSIpu3/eaAdPi6slVdvOsN2v0XZ/TfM/OZCG3eyuAXWI4NpsNmBm73U4Kwr2+xuvXrxFCyH3TAMrNzQ0+/vhj7HdSs+fm5gafffYZPvrOR7P+ai4a78SllHWb1NjabDZZ9n61WuHJkyd49uxZLg7Y9z2ev/scT58+xcXFBQAS4OWa/NzsPIXl9Fh6myUrLqlhoaynk8xCc5fZM6lBCICZO9XeMTMD3kt1+L4TcAJx8Vy/fo2XL19iPwwASXpzr7ovUn7kFiFEdP1KmCdVgU5giXF0jOgAIhYWhMTvFIkflRDymPZ2gRAIAGl8g4gEH2XB0dcoyJ/L75mIwHx4E4vQmQPQQpQlo+bPN12DFTmsnMOm8XAABjhMCkSglrFJKZMnnF2cwTUiIEQkYmWTiudYVLXTWILEqqC9vKjP8zQWgMGYkNqyrOMUHnHA6pqKC6L+ndlVGSOFCVmv13lhtRoxbWsVbWv2APp7ASMPrR2n5/JDiv2heX++MCwzLmzSd4t9558vXTUGWOYuqbkrTsBOsfrNlSPZNFbADPBuKxOySmXLs11ltqlVH3bfyCRqaZC+sVThktJZl6HPLhIF62bBppSwWq2yMmyuV1LFkJglvdvuEFNRjzXQwomlboUxLmoxxVqMjDEDHLZf9SYW7wAAQcAKyvfFb73QlUmlpo+dc5m1I1+tWZW5G+5/3zYHxo9pBtAcHKSmmAJpPswy0m8cnOvoccuVwJ6VCAoWTRlTBCZXArRTkjnRALT3Dc50UZf0W+nPlxeXmV2pSzGQI6z6lWTGtF0uvGeL7zROmfW1Mdi1XS42uFqtEKaA58+fYz/ssd/tcbe9m7kpTBbfAC6AEnfCZWzU6rKffvopiAgfffQRyFEGT5vNBs+fPxeJfq3ObOPF5kHvPbq+y4znnD1qsFmvcfXkKjNQpqFirIpdo7iAJPB9s1kXsKnrHGC6JcKOffLpJ/jOxx/jV7/5TfzP/+E/4MMPP0TXtvjtv/2347d+7Wtold1+/eoVPvroIzQkdXPCFHB3d4dhnDCGMS9erBXtksY2JrBGZX45Y+etAiGEooqZkOAnGVBeB0xSZsRoIsY8gjcrq+rLbRjoIIqIw35A8gHtuscZCIE8LpsWHTncJsAlIDkJ0kkp4eXrlwCAbt3hHf8cvhFarm07xPAK+7AXpX2rweJEwVFSSNOX8/poLmtcT6jFMkJR0HugqTNiforFpChR9SKuFFXLom3bHAxmC1RdMMkWtlkGR7RALL2RB65suVYcWzwOF/8TR5tVpZ3fa20pm8Jm/RxK0az5NTMju17q64mVH9uYIZNZXsaaMDPiJM/PN03OYrAaOTZ5OefQ6ntfpjWK/7pTbYVLXFxczFxAuSps2xd/t06Y9cK8jOifpgnbu21mSaZJ9Ca22+1M+Gq/22dL1WIArM5OzWxkX3RlfZtVTxALobYu83bMQYq8C7Fuk8ZsGUAyOeoYRdEgxTBjVuQdp+8aEHkzN9Gb7FsZGElKrMsnyowYE8qEeGKxqBnBuklcQnFvy/MxFlXjxKq6TJa2/fLlyxJrlGMgrHZMYWVzgKwvqfDmxrFg2KZp0DYtmrbB1eUVul7Axqpf5bo9VpdHCu75zC5aM4Bi4wYAXr9+jeub61lftrlpt9vh1etXmEZRl5Wqt6/w4sULDKPUbLE+m1LS+kDnxZVKJSgXQL7P8/PznOp/cSk/nz55ivPzczx79gxf//rXsV6v8ZX3vpJruuQxq6mxYngQvG9VwRVIScC3uK7KO2Vm/Pq3voV/82//LX75l/8L/p//0/+ETz/9FP/n3/t78bt+9+/G1772NfSrHvvtDh9/8gm++c1v4ivvPMf3vP9VjES42+1wd3eHvWXMOWFAmCDSALD03AQ+kn7+edpbBUJk0VUfZpwkAMfEuhQXzgac9kmNWZ1HjjBrui/AJODFs+hMUAjwKaF3HgxgnxJGTiKWRPoKdOKqi4nNA8CW1rScmdVXz/YZQd0avtpLYzts0nXzCdgm0Yeo5bodq6Nw7Plme+mIK8aso5RzxdXfD/N9l8l9GQxntKJZTTWDUJiFL2qdOp0/HwNEzAWjKdXVfS6f64xtOvJc7FiHa85hevLyu/J9YOnukUBR2S+nZTLgvWgARHuWVisnNHm/qZnyc7d+aZO0WY5N06Abi4z9LI7DWIdFszgB+71pJY4gppgrva5WKwz7IW+TVMOxgE8FdrkyrLlEcchw2LPVJzl/sgsgUoPFXD2ZxWduoSCJcABCjrEix34eY04eDzLevC2PvRwj1rgac/n6uHym354dp85GOw3mjzXhSeZ9VD6pNYVKP1dxRgUi5q4tbiSx3i14Wxb3Kv7Jy2fGDhh7MgwD2q7Ffr/H5mwzS7m1ft9rBeCagbAMnXydjtC6Nj+r83CO0AeAgHEYM6CbpikH6VosnIGnJVCuU9wBZPeRZcs0XgJuzc1kFXO3u60Iz63XmkUnxoRzDuv1Cn0VVyJgU5SfhQEVscHtdodpGvHNb34Tv/Zrv4ZPPvkEALI76Stf+QpW/QqfffqZVO0dxlkQuYkVJkE4YrUzZ7FCpXMP+uAXbW8VCHFEWPcrXJ2dg8DY7bYQd4z6y6A2BUM0KwCAlHXQZ6icAYiAhhyIPAIRIiSkkvd7BE7ovce7qzVGZkzTjVh6RJgIIkLTtXCNw263xccff4y2kUqbTdNgd7fD2I5IISJMIkzk4UAemCYt6ZwSBqW8+77PZd6zeI1Gg1uamPn9iUh9d1WZapRc8ToWBFhMyvfMmWZFoYp4B0oRpdoNYW4FG/QxRtzdSYnxOhrcKlvasTINz1xR+lN1LzbRLzNwHgdMlq6VUy1GEQk7xrAsj1UDJXsexYVEB8dYnr98d1607MRZK3BWQMs8uLCAbjn+/L0DJV22bdssS5/F1rQ8fR38aoJQ3vvs3slUeRWzIrLbXsoXuFJozLJssttE33OtF2G/G0Ox3W6lpkUVm2ITswXOWh2eHAtSBVfXrEo9J2aLu2mB9tD9tnTH1OzX8p9ZvcbqWL99LEh+PJhmGMtQg49ZbA/ZQn/Y3yIv4r0ylhPQIH3QzfqJsV2H13vsmhciYBAwSURzl9vi+vPeLG5yIkKa6sBtYBwlFR4gvH59PZs/bM6zjBT7zPry2dlZDiatg2FzZosKnplgm73TppW05KZpcHlxifVGFv4nV09m4NaMwbrlvqx9M/flSVJx97s9QizAY9hLdso4jvjk408QY8SH3/kwx6VszjYgkLg/Y8ouLu99FmW7uLjA2fmZqK+qG/Xq8hKr1RqbzRoXl5fY7Xb4f/2v/ys+/exTfPvb38avfetbaJoG733wAf6bzQY/8t//9/jvfs/vwa9+85v4v/2P/yNev3qN169f4513nmPVdfkaYwxS00n7AqeIoAq7LgEOpWrMlwVF3ioQApC6Y1TeVylHB7J6tXNis1oo7O85LwF4IjCR/ATgQgRohO86rL2XtF2GpvPq9z2BIFSZId3UpUwNNl4iwZk4+70NRNZS6OM4ZWGvrMeg/vQpyGdNag6s6NqtUVdprQduPZBPBSnOniwRyJdAR5u05iDEUPMc7df6HDZB1IGS8rOksJp1Pk/TBKgSe1taoZb69tA9PGbiT8mBqEzQx1p9f8vnv2SHxEg4ft5joOLYuexYgiP46Od5v8XCe6rVAHQmg92UQENJ1dznTAaLFTHAYazJ0odvAKfv+8qypVlg3TEQYromt1qbZL/f5+wc51z221v/B0r/Iu0DOZakAiTH3pfFExQgefhMa0tw6aKpgwDr30+9z0MA+nim0gBD/i7KuDUQYp88zBguZ7kyft2iL59ivU7d032fLdnEY/vzEbbr/nb6/Jv1JoMOY+lWq9UsxbZtW1xpnR2bk/pe1EK7XmJP+tTP3EJtFcNRZwYRUe7L0zjlLMHrm+u8iBuQtpjBm+ubGZAdxzE/b+cc/CthgK5fiwvIxNAMIFlGjrl+zIh459k7ODs7w/n5OZ4+e4rb21v8z//L/4IPP/wQL1++xIsXn+HJ06f4Lb/1e/DO8+d499138e677+Jbv/Zr+NVf/VW8evkSFLWeT72mpFJHRk0sBSWUX8eXzf+9ZSBEfPGeCI1z6FwDB4hmBwRQtNQgEFeumULkHg42hqToEhqRhUOXIkLUSq5ThCfCuXMYmhY7tkJAJNGlMSKFgGkYpHRyjPAk0ccX5+dC6SWtYjsJ6LBODADr1SoHF3rvM31MIKxUzfCY1WbWQM0sHEPtZiUmnE7PzU+HAEKqgmiOuw5kW30OfbILqtgWq5o1KOxBfdzDrBNeZERkqvDRE/r9rV6wTjUiUl/yIaVd3+dj2ZfHNruuew+Z2ZDTTSYPxpRE3CooDW6LPVXW5X6/L6nC6u+vxedsEr64uKiE2PyBjLhzDn3Xo1Ng4nTxrAMl27YFGomfMabBAHVmS2KRAB/HMQe+pih/b7UCai0PnoXaphI0awBdgIuOA8zfvTEtS1Bh4Nn+mQZFLez20Huv2ZQlw1L/LfvO32hmG6pxXfZ/bH+rB6odFVKfE4dzxnIMl/tbghr5SVTmj6Vb6HT7ssYKzWKr3CC1VHa7XTbIpP86fPrppzlug1SfxwCHKctacKt3cxCy0vo9Xdflz9pmXqnb3OVt06K76gAGnj17BmbGfrfHbrfL/ZSZczwMEeVYppvbG4zDqLV6dpnpq6cfEyWMIeLFixd4/fo1mrbB6sMVxmnCNI5Yr9d49s4z/Ldn/y2ePH2KH/6dvwPnFxd4+fIl/uk//af45f/yX/Dhhx9iv9/j+dVTbDZrDNtdBk0GRLguTW8/a9Cv8SFfxvt8q0CIeEKkc7XOo3MeJd1WagKwl6dFKeTvZPLogEPSejIkIISI0EZC5wRQuJDQEOGMPMamhYsRQ5oQAYSUwBFI04RpHOCdQ4oR7L2kQLkGe79HHIOWdlf6eZKyylKEapUnN7PuiOU6Li4usF6vha7e7QsdjVITBKgmJi6/m989xnjgAz/5bIlg2X8GBuz45Tyygw0g848aYwIU14Glo8p3i/umTlO16pwGqO4DIyHEo/fwGL/8m/juZXKxRejQd55SvXh8ub7R6ioUsB13FxEI7oFbIhCmJIwCAFBQd1JlWdtzubm5AVDAAhGp1kABvW0r+gI1LW6UtwUrN02jwXXnyqb0+TOT2jawYsGzdXp3djdyUfzNDIqyhrd3t3j58uUsnXi324ls+TTh9vZWyitsd0hDypkzxX2T8j2Ye6WO5wIwW8SWri5rdQxEfuZHmJFlAcgaPBUwUpjSmuU47O+fv79lOMHzAuy1q5QqsDP/5vK8lQvQ2FD+7gX4HjbK808OoLarzdcxN97q7823SWuaJgPqru9mTIj3Hr3q9zx79gxXV1c5MLVtW1xdXWUJeVOhXW/WWhRQGIZW9Tkse6hpm8x0pZRwtxU28Ob6JtflefXqFYZxwM3NjWStDANev3qNKUy4vrnOLkKLs2lV4fa3/bbfhh/4oR/E06dP8UO//bejbVv80i/9Ev71v/pXePHiBT78zocgAF95+gzn52eY9vs8bsI0qWz7acqDc4jqfRza49tbBUJkjMqCLcizAUfAJ4fIMQ8uySiSYFOLE9FuiVKJaEEfQoXMmNFatcAkRYp68tg0HSImdDEiQKKTIxI4JqQYc/GiqHR027aIU8wBV0ARLvJOLE6bxKHXGNXyA1Sa20R5Gg/HrmSUVAqdM8pXqVViUb9z3ueqqPVAXVo2tNgqVnT+DcU9cphN4lUYRxYQZJBR3DeMlOwabfIqx7BJWX5n3X8OSGTb4ST3WLr7TUCIsWe1dbx0DZUJjg8Wizc71/Frrd0zxw5Xx4Tc15x38FyKCNrxjZA6tISr+6wYAzvXfr/Pi7GBBvPFW/0cs+RsEvfe56yGTHU7iSsx98/ys9ryz2NHAXjbtrg4v8jlBYwtMdXN7W6LGCJ2e6kAa777xAnTJD5vazXIqbcdYyqWmR91O+wf8+1LMGPv+BgIkZogfGgJw3iMh/t7Ga91/1GXp13nctBXTa7PGM/T3v/54v/dBCCHx7b7y3FIMxfVHHwswUj9/gqTDEw2r4JzrJsFew/NIEYJQYuZtri5uUHTNLi+vkbX9+iVOfHez5jslFJOT26aJgumea0xxeAMqMehBM72qz4bnOv1GuMwYtWv8tpgTJ/dEylr+eTJEzRNg2EY8cu//MtgZnz00UfYbrdIMeL8/BxgYFKNFYvPiiEqQ7bgfSuDqObGvhwI8paBEABIISFNAR6ETb9GGyfs4h4xRfGQaMC2E1iRERtwtCsr+OAcetUngo8OgRLcGNA4j6dNh1XfoB322EfGyFEpY0ZyEyZyICbsbreIfcDl+SU26zMQE7bbHeyVSjAXJGe+a7O4T9s2aBqPYRjx6tVLjTPZZV/9+fk5AGRr0Kj0upXJce4Lz8At/1w8hWoAS8+qQAdzQbzVpDyOk1qPBGaLNejy5FpPBDXNbsc1pgFApuKXrpd8/TO10nn7vCzIQ1+z73jfgDIzVABSDZTe5LhfWiMCOfcgDGldYZlyYxxcd/moiI5xmC+sbnIKkOeCSXUckmmUSBpxqcFh7sYsFmXpmF2pTdK2Lc4vznOsiRVbM1+/uYpWqxXeefbOQfbVcmEfpzFnMwhACbi9vcEwDrP0cWMlhmHIrtLra0njND9/zXrUuhj2fMw4qAGMPR/LRjrVjMWMScZdDPNqtOWdn2JHDt9iCOkgW602IpZzQA2sLNuDtWBkzXIaW2uMEgAEY3ArV+t3r5kRZMC0vgf7qXOgGkQAI0a5d2Pe8tHy/JIQE8CaREDjHKyU+YrQffSRJApUrEpOBKhYVEuvtf7S9z2ePnuaXZimlXJ+cZ7jVBovAbNn58KYXF5eqj5Qm92XpphqbJ4xK8yMnRYMHKcJ4zTi448/xv/9n/4SXr9+jd1uh0HXk69/7evglPDi40/w6UcfY9ztsb/bAozsqrXnrU9dnncFQRI4a3B90fbWgRBOwjwQpIZG4gRPDiZUTIpqTT//YY1StRggKbsOoh8CBkKUcNeOHJJv0LkGLTkkFhcQMQPGmMSkTIhUW/TO6b/5RGk0uFM2xOhoUcZMOVXSVPWAku1AjuDYzSYNwKzbcmxy4h+dT0Byr8cmsbytWlgtS6cGLvXkKueXAE/nRCrYAhKXLEGm2ZMoqep4rY7JeUKwbUtLtG5LC+fet3vi+/cBBmNBjKafX89hzZMvyn58nvaYM54KQDzFIB2z4murPEAWxbr+jB0vu3IWtTXM751dHApCpmlC30m9kmka0bQtYpL6IW3XodNAwr7v4bxD25TAQmMUchB0I1k99T1bYGsGIVoTZRj2ma2p41H2+30GIlb11e7B/gaw6MvpYIwds7qPGQzL506W9cKn39Fj4i5kgaqOS4vrg7DID48ddWRXBoMBofpcxdi4f0x9eY2P/i7MTVk8rdCkXJcAKmA+d9TXW7Nu9vfh+ZDTicGlFAajPAtzWXtXgvKtHw/jkJm/tpEYlIutZO5s1iLsNk0TQMhpyRZrYn3IAG0dfGtVtsk5iQ3RPn93e4uPPvoIL1+8UHDhivs7Jc3U3CEMEmcCKlW/j927bFEl6ZN7vHl7q0AIM2M/jrjb7dA2Hl3Xi1JpWAGOwHHCFCcBEkS5EwpyMwqp0IsqBAdAQAXIKvI6jIkxDSPgPDbdBivfITYR102HJgbcxQkhSt0ZRw6UErbbO4zjiFXfo+tWiJzQdC2YgNVmnVmFhCS53TARK5E17/seX/va1wAAu90e41gsOaPHXVbYVHnlmjpORtgGOY9VPT2YHRaTm2GQIDVfgELBZ1SsoC5V5odTehIMjGNRMwRBy8JLPRGbyEQPpZzfED1lus/pZHJYJK+eIO7pIY8CJikdj7UoxyiW3UNMSm15/YY1A4MnoIhR1AfbgBlYtZa3cZmgczzPkvEhHLXsC2jVoG5IKjkRIVAorIlm0ViF4sY3me3o+1J7pG0aSQeushPM6luv1zN3j03YdWqxUd4GVogIl5eXcO5q1p9qd4uxGnUgocWe1OAkJalQfHt7m91B9tNo9WU5+/pchyBbJ36bgywYtquecwUiH+rjKS1cOtV7rFnNOQspJ5GU/9LHJVlinoYLFPbENv3vgMOPjs2l+0y2AQDNQGdmhXK2DuMwc+cYUE+wUKBjLFMBbpgJx03ThM8++2zGjljfJSpAYxaHojFV9bO2+XyzWUvgbL/C2fkZYox4oRWK9/sBOxUUHPcD+q4TozYEXL96jesXIiy3u90ijCIlESFj1rF4BZL+Lz+/vJYakDUA+sVhyFsHQqYwYT8OcG6Ftm3gkqhGJjAGTqAwgUgyZQgSE2LEdcoAxHzdAMAglsq6YMmIdyAgAT4GwCUBJs5j5xqsnVQqbVRF1SUtoJcY437A5AKGi1Gi+ZnRtA1AhK7vEWKUV8sxW9h1wNpqtcLz58/RNA1ub+6w20nA0N3tHZilvoGBkDpzZubK4ISQjB6eW+v3WezMLEFJiogzze68ln7mmSWUj+fmg5uciWhFORaQLdb69El1BuRY1dtQC6UGO8cmluP38PAEvXwuxz6vf9bNqOkZfe0cFobud70Vy+vIZw+BsBltvQAj1e95gbTFiFN+/jaJ1vuaC6GA4UPKvz5/vQDaRCYKmw6tFf+qQIi5Neo4FFPXXPWrHBhrPy8uLrA525RaJm2rwYOlQGDtTqrHVO1SMTBi6Zh3d2JovH79Gi9evMj+eVOSNdBhP1+9enXgclzGncjzqdLqXWF6Zu/ika1+B/U5621zF1JhLotgXLGGl6c24C2/H72CR1/rd6vNn1eZW0p207EF9HHMag1W6v5bfz8zguaKjxF327sDpmzZ6rRsU6Ot1ZYt5u7i4gLrlfT7i8sLhBjxySefYLvbIgRhAPtVj3fffRdt10m8R0zYb7d4/eoVUoxonMhccBL1U0uBLzVhqnef7ZovH22+VSAEkMq3+zChSQ0mFm7Btw1aYrQc0cRJwId2Dq8P1pEAkmXXs07i2H4yXEpaV0Y0SGKIiMMEH4FN0wHk0A5b+BjAMSGMI5gc0HiQZwzDgO1upx1JtEaathHLxlwRSn0xJ+z3O+x2MkAuLy/BzDkfXCR7HUKWxhaWI2iAndFjpB3Wk0dHHRicdUiszSeT0sFsYDgi2IpagIG6m6gs8gdLDBFc48Gsi7ICwHqn4sYo5zycV+eWRdm/1GZZ7jv7NgMp0cG25b73W23HJtey7RiVfgwcHUzc+t97YCAAq3PhcOz+5sc7NYktn2v9HFEFJHL1aXWNFVgogasESkBWwbI1iMt4Yv0uOUmfP3Jh8qMCb0sXVz6wuiIsqJRICo2N45jBApETI8SsR81eMHZks9mgX5W6IgJMzvV3j0Ytz8yWeK/l6YsmRAkilYWayGG1WkuRQd9kGlwAGGeNk5RMAyjg+vpGUy4TYkyZMTFXkaVthlAk5mMqAKEGeMaGLF2VzPN02xl7lVnIUmNG5sMSICvDrYCQGRA/AuzTUVDEZaEy1qZib+q++Pnb/Qv48Va7F8oWueX82+OvgMsQOXwGOl+yMWuQom88r5O0/O4M/Nu1cFVVWqmI+ranSda5lKRIYUpJBNImE/qLCOOU6/lkVm8c8/GYa+F1eU6REyiRpuiWPmTXxPWfXxLWfKtACDNjH0bcjnu4zmOVJsARmr6D61uMlDCmgJCS1OBg8QV6kCj2Qbsc6WTMyw5KcDGBOKAlhzU1iAxs9xNC3KNrGzztz9DHCZ9sb7DHiGEK2MUAeAfXdaCmwe3dHSKA1WqFq6sr+NajX3VILHVW2q7VTrPNVSBvb29xeXmJy8tLbDabXJVSJuOvYhgH/Ndf+zWtfRByJ7TiT3W6Y99LoJKkdVkal00sJSJ/tkCxxnaQM7QBADldK6UiVa/sZhm6Tkp/A1ongggpRBBNwMyyLAt27ZtdDuZjgkaHcRyHfu2aoajvsez28CRWPjrNHNXnNat2/vnhBNW4hxVThcFzD+4HAnh5bQcTvlxIXgwMPOpzsXdZzyREBdo4Z24bDbqLQEylMCSAAkyr6zKxvsNLptlQswW+FrqrNTisxLulGJd7XD5bLjEnropDWYjlOeeyMmzbtFpUzEq0NyITrvoR77zzDrquRb9a5SKAZ2dnkHo8EjRooKWOfbG+Jvciqry73U6zckwdOGZNht1uK1Lb44ibm1tMQWqaGKNyc3tTavAsau/k1NRUxWlVAaTmUrNUa7tGrl7YymmROFSBvTxXNOZ0CLLHacJkQZxUnRPF2U2g4go6wRa8aTvJHlTj/ug+vEi1V0ZX+m86Ot/c1+5npXQxjwkG2iXi8A2ZLLBYzXaEBUu53+8x7PcC/KkYQzWwTzFgHIdy/gwOdYzp74Ri1ASLcymxCiWAwSZ+FBDHOD2XPra9VSAEUGsXLJVvWdJqoZOn02BQZnGrsLlZ9CWIfUnQ7FM9IDB72vklMZwWwkNK4BhB3qMhQkMOrW/Q+xYTq8wtZGJ3KrY0hQltbGGBYBZAV0ce26Js/4zStZTHWjq7RYv1Zo2YIoas+V86trkJrBWK2VV0a1kga1+wc0msgnRkoBxhEmYxBxW4m1kIaoHZdrMgHmfF5G4/u58v2syf+th2yue8fM72fI/tC+gkpA//1FSULUj3GOpdn88xC2qxWz0BynXI3qeCU0+1PExYn4u91COX9JhnvHSF2EIKlOdWX19tlXN+jqUfuySLrTF/ddxUfY4cW6I6JVOYJBtHXUBSo0OqoK7Wq+yjt4DEaZyyIWGuInPt5CwJCHjznrJ/P6WEFHvEFOHIYQqT1kORmiRt2yGEgPVqnUFI18s2S9usrV6LObGKtvo0AIioVeJ59pKBQAMuFrtVgxBAiuExVTFBy7HPDO8dmOdLBzuu1KEL2DfguwQh5R0Dy7Fzn6vxywoCz1dzcgi8KduyOH51rW8CQI63mn84Zrgtxks1fjg+xqCDGpUV5WHHs3Gdabb6bo7Pe2/a3ioQIiwGgckhJMZO6VnXesARvG9yHnWYAgKSuFNgcSGk6O/w8RVjmQGOIGI4ksJANI7AJMGrXdcDzuErl1c443N85+YVbm9egb1Dih4RDBoHRAeQI5yHC0k17FqsnMM47HF9/TpbOBYbsdlswMz41re+Be89Pv74Y2w2G1xcXOC9995D13X4vu/7PjRti9vbW9xopceXL19mpTsR9EqqtAiQExljATt2e6miC0vaLLNUcI0xGMzN/xIk6wi2AMQoljSRgH0ikAmZKSCU85MEOxKJmhzKpGN05TH9j/sW9Pm2wx5iwEoi4pcD9suZwOomADLcM5lBmaQkksjHPq8GdghBrRt9jrZY1NduVu8J68/u13uncRaFDXLuyOJ+5IrL/cUZs3MYQ3K4gKQjE9+xVtwBrNdW4qTMkp9Z8PKtig4WizErsqLoiZQ4JcAyFgxI1MJkNqnmlEcvQMR0fCxF0oIEa3dPltJWzYe+71XoqpkJteWCgWpUPH32NGdPkKMZuKrTc4dhmLlvpjDlNP3dfifibbe32N5J7ZK7u7s8r5iQoAXUmo5KzTxlRdk6K06NJgNV2fnK5bPVapWzkayZC6kshGXxNQBe965UVbANcTrok8dcTsttdT+6nwkpi3h9TQUcfffmhy+vLccpHfyeK3jXtkENhLj+eMGGP3jaYwbqFwcgwBuCkBgj/upf/av4+3//7+M73/kOPvjgA/zxP/7H8ZM/+ZMzK+av/JW/gr/7d/8uXr16hd//+38/fuEXfgHf//3f/6VcMKsVllj8qM4DTeuVCfFomwZIDA8HXT5Rhg808ndxzIO/dCAyS8GeqNUgY4RnRgPCebeCd4yXuzuAK9qSSAb3RJhin9XsnHdoncMw7DAM+1n9F/NNxxhxc3MDZvF/W/T906eSX/706VNcXF7i9evX6LsO2+1Wiz+p28QmXVUxbVupRJmS4QmzIguNOxvcKYFV6MyU3uWZERISHB1TDKWCjquJgEjk9alaUK2V7BTWuJjlWz62qB5OEAceicWkYsZ6Of5pOnfZHssSFLfPw/udOm4NQmbREfbsFvKoohHijgCC5XHzp7NntaR2F9+a9xUuf8+ugYqgW31MZmQr/L7GiYs09OK66mPX7IJ9RosFJbsTwECcP2tZdAswqQOLZZwNFQtTau0QlUJpBiBIFX5N5+Ty8lKAibIq680G6/UaXdfi7EzcPE+ePJH4FA2i9a6It9k/G//1/dcaJuOkIETLPoQYcqCsFSIbhkFK0au+iWX03N3dFVl8zOvx2LOKKWbgmMeu6r4kqt6lDkNxZ3Wzd2cMzal+VbuBAGS1U4lxmxsiNRBdZjEd7UsVQD69X338w7lidoNvSVuOsdpoOdi3YsIAZEPt9P3e9xyLS+ZLIELeDIT8jb/xN/ALv/AL+MVf/EX88A//MP7tv/23+BN/4k/g6uoKf+7P/TkAwN/8m38Tf+tv/S384i/+Ir73e78XP/VTP4U/9If+EP7jf/yPWK1WX+xq7fkSEGLEdtjDNx4Xq1YtmwRAsle6xsMBoBQQtP8LMBFooolohZar3kVeXvV8LRESHCZmxGGAaxz6pgV5j03b4KzrMBGwI4bmv4CIsZ8GvHz9KhdRWq/WYC6VY7d3t6rIJ4OeIeWTWdUdmRkvXrxASgn9qsf17Q3Ozs/RqnXWdh2++tWv5qCkQS2gnQoxpRQVbHBe+DP7UcUyZFl1ANGLzon5eJNOHkX6WorUJebqmZH+XliQTDcBwqLYs2WLfbVMBHow6+WxDGyZtIq1JK6SOiiW84Jz37FlQtP7uKc553GPFlVlGfLM3XVIc8vWGA8nZHNZkzIiyVAlarfG4aRkQbpz+tV8yEev9gAszQFILQJVfNFlUZ+DhJONMLvH5SNWB4H0u0UMUW31Hrn6/JkxDcxA46uAWtRWMNA0Uh+ozpiyz0OMcNrnDVhN45TLu+92uwJaHKFTESrJ0pF04/Oz85zZY66Zs7MzNG2TQYgFuRrTUoOfDK64pO46cpk5NRGsGCL2g4x7YzxCCBhGUY3d7XcIk7iJLY14vxdjaNgPGEZhSox9MRAwjMO89knifL+cSppvSvMqx/W7rokGE0Mzd4+5m+u+Z+8AqCUIqiyeam4B5sAjx8rMWJTFJRXPwv/RTrZDlvO71d4IhPyLf/Ev8KM/+qP4H/6H/wEA8I1vfAP/6B/9I/ybf/NvAEjH+fmf/3n85E/+JH70R38UAPD3/t7fw3vvvYd/8k/+Cf7oH/2jB8c0gSBr19fX91+EMiFjDNhPe1FavLzQAav7MNA3raTOhgirdJ3gkKBy67Ywla/MfxIDJFkZHTl4cthxwjDsQNFjfdai8w0u2g4Xqx57TtghICEgQia23bjHMEhsx5Onz3BxeZEzYsZhwDjskVKE9w5N63Wik6uQiosS3fztb38bTdPg17/9ITabDX7Lb/kt+MY3voHVqsdX338fbdtiGEQJcrff48Wrl7mOhk0qMQjsynoBKrJmEzDASK7JMu9FX0C/VwGTaJS3WvCyfs4Xr5QSktV7mS06Av6MDV/W3zj92h9GIsIqzcuyE3FmgqhSgXxc3MLDjIj3mKkwnry2GB8EW2ItLjOaymRKRJmNMvXCWgivBhtiTZdAz3lq8YlFfLYIA8uFYX4eO470gFNA6P57XWyk8tOOk1MTLW7BFrLqPgvPWba5xqHBcZeBsZDGFjrnsvuitr5T4MziTWNNJVXsC5dgzro2UtOUwn+NL6DCqYvUNwI4ulaAyNWVVHo9P5cMntVqhYvLixnTcnFxgasnV1KjZ1XqkHRtNxeJ00Dd+n0aGBnGIacP391qvZJbqU2y3+9zXZ79bp/nkJeq4rzdiiR+iAEpinjdOI0zXZLZ68ydseo7XgCmub+cI/imVDJefrcGIczV3JQZzrlwnAGsJZsyv7S6Ts7JLvp/tKPzxJfPFL0RCPl9v+/34e/8nb+D//Sf/hN+4Ad+AP/hP/wH/PN//s/xcz/3cwCAX/mVX8F3vvMd/ME/+Afzd66urvAjP/Ij+Jf/8l8eBSE/+7M/i7/21/7ao68h+yiBDGktEBTMVeeWIFVTQTVpJ4vnpYoFAU7gPp2I1W2b03eRNBiRGa0jrJoGKUW4GOT4BKHQk9HBESFKMTEGa9E6qSeQksiwGz0og1WtK5So7pQEuAAC1D777DP0qx7Moh9iueRjlkjnPPGlxHCuAh9i3hZAYoOb0gyE5AVwQc87239hORsYYVZ3ll/Q+pBA4nrgPwYQkNFfj2pLX2kCLVJeH8us2PV93sbzG33UsSybof6uZbLYguiOMhk1zVqr5QqwFVZkDlSWbNB8EXmMm2lJZ+s90MPCKbPwNgWqs+dDuo9WfM0BcidcUDVQO9UsSNfcPPX+OQYiM1fID2bpTrQmwl7VGEkMzkJ7hZWJXoJRx2mEI4cQQwYoVm4+xoimbbHb7dD3Pfq+x932rrAjvsHt7S1u7yTlcr1awzfi2ulX/cylY6Clvs98rcpkGPuSdVg6UfS0uWTYK1DZ3okORQiSAqrxdlbNdW+uZUsNrWvfLOYSY1Tr+WQJXGsjpv5Zg3HrH9pJZu+ujiGyf4fZa9XYmh2/BuCH+/7/Wzu4tryIVdTT8js4fX/lPfzGuqTeCIT8xE/8BK6vr/FDP/RDWc74Z37mZ/DH/tgfAwB85zvfAQC89957s84aHoUAAGieSURBVO+99957+bNl+0t/6S/hz//5P5//vr6+xm/9rb/1+AWwFHmbYoR3Dm3TwTnC7W6L3bjH2XqNzXoNxwC3HSIIMUy5aFVUi8nPDwkAMPfY7G8hQ0CU4JEQGeiTHMeFCTEQLrzHu2fnuJ4GvLzbI6aE1hGa1iMGU10k3NxcgwD0XYvzizOEqUOYBuz3raZbDYgpasEiRtf28L5BCCHXDdhu73B7d4fr62v8yjd/Rd08l2jbDpvNRijgpsVqs8oApG27mZMk5/gzS9YPA+aiCeOEGEKerPJPnv8eYhA3Dxi1e4e51JWQ3xf7p1hZJcU9BBxbtOrF5nh3OBwsjJSsaJ5NQg5ExUVT/p065pfdbHGEir6dntiIqLgsq4m6aDfIm0ycQGleVVheZ9IJWY5l+hV2/gI6aLatZk/KtbiDbWUhUFr8gDmxDLWHmaHZMZVezzEeyniI8F4p0pUnWTcHrwcLlD0/qo5XHT9nznBhZKyoZN3PMwg5ct2WqeJQpVQrWMkLMEochhkj9TO1jBwzPAAVgiOCbxp0XVHRtGJnVoXYXDub9SYHv242m1zJuO97NG0zcwEZ62LuoYsLYZDfffdd1acp12bjP2uZpFIDarfbFdn7KODj9evXEn8yBQEmIWZht3EaM1P78uVLTKoEbTEvMU2zsZlVorkAOWHy9DHPUpExA1sGxOr+cSz4fenuiVFkzMVdXqoeP5ap/Y1vxejIv8/SPq3RoYX9G4sxHmxvBEL+8T/+x/gH/+Af4B/+w3+IH/7hH8a///f/Hj/+4z+ODz74AD/2Yz/2uS7AUP9jmw1wr1r44nEJiImw6vvcIb1zgOpeSGAla4YMa3G7uiCPtOzNsc7OikJYGBQPYUOgcQycEloSJmTgiAZF9tYCYO16p2nCOOzRNELVQhmRWvbZUL0FhpU6MpIxMQ0BIQYMwx4hCGDZ78QldXl5KUXB+h7kqYrGV2bFfLEVY4FsbRRg4iqKecmAFOuFFjQpI6n/PSUgsabmVgxIqoCAxSTIT3cwQTyefTjMn5d0Y8sCsfovh8Gvv/EWTpkJ7ru/IpBVLOyDSOqk75HqxZerCckW53Kf9WQ1DyYt1PRye77yarGfXRuWFuTD93fqsSxdKiCA0uFxHgx4tWusjnfM2sv3kbiMO3PlHWF3Tp3nWPCsARBjRxLSrP6MXU8IAY2XKqpxkVGUXTrkcnVhc7k45zLbsdlssNlI3ZFcCPD8PAOT1VqE2qScxCoLrKWUcHZ+BhAyG5NlxN0c4Nk8YO6q7XarAmycA1JfvHiB25tbjNMo9UhCwM31TXa377QgpwXMTqPGpqSIaaqAWzXHLN/3wTaaM2A5oFbfx7K0xfL91Z85Zy4cl4F7fR0P9YVle+wYOMYCfZ62ZDFnv/PiWpYECh2Ok2PX991qbwRC/sJf+Av4iZ/4iexW+Z2/83fiV3/1V/GzP/uz+LEf+zG8//77AICPPvoIX/3qV/P3PvroI/yu3/W7vpQLNndM5ASkAEeERsvIWylkx0DX9mDfSj0HyOBPJJK0CQmmfc9c1Uqg+v1YFSiAYwAIaJjRQYJPediDELFpHWLXwoHxtO/RRof9NGF/fQ2AQCzQZ3t7gzgJ09CqT9voUJusQghIe0XgKQFac8JAWqciZOM4YRzFNWNKeCFMuL5+LRbUJyt4L5VtTR2yb/vZhCnF82ywCoXZOC/gDYA3voiQJ/Ns5UUJsjAquqQbV24cFDW+sKgyWlvR02S+eNhKOaMMy8BYBmxWfWI2EbmDRVGSloqoEwB4f4ppOSb+c7wn1j9O7pF3e8zSNr9u+7l0b5Anje6tAUa1vzPr8X5LLsc06H1SzlYhZY8WC7YeP8YiwV+fm1ldnVyOr4c7Hayqn2XLtQJE9fs6xjCfAhfHT7Nwh9l5Xd0PRCmS1fA41uwtevKgNNfgsObIoaF5Qb18/uq4BnzA8p3c+7laGMASaOqKUUBEGPwAIsJ2u83l3rOc/aqSuG9aOO9yWm3TNhl0XJxfoGlF1qDrJbZks9nkujXe+1xksF7gTSfFqiY75/D8ned49vRZnhOYOQushSDumxACbm9vs9S9zV37/TYbahZkb1k95gIahj32mpY8jiNiShiHUdmLeqzPqxvXxz3lypP9pWq298jGX73fEuzU4+Ygy1DnSGaeAboZM6OGX9T6WgfuyarHHW/3gYP7Pjs8Hi/H629weyMQst1uD9QcTYgHAL73e78X77//Pv7ZP/tnGXRcX1/jX//rf40/82f+zJdywaz/okZLO+dkwSSSjjlOaJ3Hqu3gAOz8Fh6y6HspLoum4kLEap9XBpRGFV2bwAjwzGjBcEhI4wAgYu1XcE0PAuOq7+GDw7jfYhwHON+g6dcgMPbbLcZhgANj3XVo2iYPeKM8x3HEftCU2yid0yowgggr1YbY7/dwW5pFuN/daX0BkgWKiFQV0qPvVjhbb3QC0QJfXVulB4pVdbZeo2kUrFRVUeVvyjV4UAMGnWS2pPViOKmGSDHgYz04Zyl3jGGYME1BQI3tM1uIzWUkGijlu4XBsUmBFEkaiJiDlrLI1kJW+W0vJgq7r9MpgnbOqmMu9rPreax1ffw8h5ODMFv34h/dL+Znc9/5DsHWsYmqbLsX2ADqwizPMy+2R/cvAMTiYQpQ9Lmey3H3VH2vD0ygx4AQHXm2oAXDdHi91teW9XPqa5nFlwCAAxy7g0fLOlby3zg8d0wRSCJC9hj3gKkoHxvH9fWttGDger1GvxJG+upSAl/XWiDt4vwCT58+ndXlefbOMzx79kzcSW0jJegvSxpy13eZrclshDKrFjQ6jEMGInd3t4ix1NvZ7Xa4vr7ONXr2+z1ev36FV69eZukC+Z6wK3U6cx2YmuPkVGfF7h2YB3Rnw6xS2CWi7C4DUFRotXZX0aHhnG5cj6VpFJbHa4XxDFZRasGklMATH33nZaW7r31ZoGFuzPxGg5E3AiF/+A//YfzMz/wMvva1r+GHf/iH8e/+3b/Dz/3cz+FP/sk/CUAu/sd//Mfx1//6X8f3f//35xTdDz74AH/kj/yRL3yx1TBXspUUkDCQEkKMCBThQKBWFk3n1ddLymvrBOkIIKaZ4uqxMyp2FUCgLhliRkgJnCJ8jHAhoGXGeduBnMPtOOAuMUjKNWhEBgMVawDSfPteqoKGSYLVttvtDNXnADq7IhaXiUXaW8cPIRTGQSl5eSySEmxKrJOeZxwbNM0wi9of9nv0XScWjlo9TdNI+XXdRlBp8bqjMqNrGrAV1YO4upK6XQyYHAMhRB5tI+JnlnoaVQxtbm0AQF1vRFis5SJbxzvUmTBCuQp7sKTPDxvN9ju2IOVtPH83i+5TLCimg/oRxzrdEjwdWPCoSIF7aFRU+8y/v6SlbRI+eQjdrwDC0+eSn0etzqR3s8QByj4Q0YHK59H7ouPP5FET5xuw3SePJ0NLfj3S7+rts2McYXLs7+Xs81jAerJVboqkhcls3rPrSilhjz0cOcQUMU5jrj1iFVybpsHrteiQmDHkG4+rT6+kHIVt8x5nmzPJ+vFeBNuczzV7lnL6dn77F8IE5pTnm/V6DeccYowyN4aAZ+88xfbuKxmkhBiw3w25PlZdtbiuyxNjzJoq9eI/Sy3OsXEL1pPVFW5MBQsgtOu3YxgAqftl7RYyAJ4/gwATqzKd5zNz4elasewHZW6wjD8+2u+ONc60LOFwIKgbAEtW+DemvREI+dt/+2/jp37qp/Bn/+yfxccff4wPPvgAf/pP/2n85b/8l/M+f/Ev/kXc3d3hT/2pP4VXr17hD/yBP4Bf+qVf+uIaIdZIC3yRQARmwhQTgrD8QEygtodfn6FR1cO260RaPYxgcI6TSKxS7keY9Qwc8r+Ut0aILr+bGOxHJE9A4/DB2QX2APa7AbfhFkScA1xZ/03jhJubG5wlGbQXFxcSqb5aS6rc9g7YQ0ovZ5pcOrf9bWl+gLh0AKnnEKYJIUUMWqTIBtiwH7DfivumTPJyl+UnoWvEqrF4EhFgWmtp9Ra9BshttFiYIxEy802D85UwLdABF8GYzF3Dx2lLo56ZpZJjtmaqCUMGuA14mzCSLnTzOhrO0QHDUd6mtTp2QrcsGJPaIrDrXO5nf+cjH2FCZsfn+ycJvbKs8XBfO2Ttjjfr5wfXcrBf+/C16XN+qHFMpXT94jNS5uEg9qOyTmW/8nf271OxXB+TEn3s+o/FBhxr9+qcUGFD3ggsHGFd7Fz1/dlCdKwdt5gX+yws81NgjZmx3+2VBa7YKFeyapy8sCLepgyLpRDXLprz83PJ2KlUZc/Pz9H1HVZa7dVSka3goGQHNTg72+SKyV3X5TRlc/14ZR+cX7hBosTS1IzwbrfLDMswDJimKYu5bbdbbLdbEXZ79SpXR5ZYlYDdbj8DMtvtFtvbLQArLIk8RxkIsWdKoMwCAUDjmwK2eK5147uSQm0icbP+lH/MY74K41PV9rG5xY5xisGjGmAd6xPLvvkFgfAbtDcCIRcXF/j5n/95/PzP//zJfYgIP/3TP42f/umf/qLXdnhs+y+JD5apRKMDQs9HyEtnuRiQST+byXrUGGXQke3Fmyv7OGh6JAheB4NLSZRUHaEnkY/vvUfvPJhcdkkkQ9qK0uvy3lY4a5qknoRQfxJjMUPKVUddTtzeFvhI8L5U3RTptEWa2jEwDCCFCO+mnI1jtG6MEamNgG7zDDQaxe+I0DIjtZ0e2gAiDk5SW2Impa0vEslV/lIUyri4WmwhKZHrQMkQKZPoEVNz0QoAmrtzlg9nbpEfWh35ftTAODbpz9xFywCxI9c1U6g8td/itk67XA6Zh1PtoXMaK/fgInifZcY4TIRiFCYkHRY3zH50tehLOvub0cZvSjEf2/8xAObznKv+zjK+5PMcZ+laPNWOubWAoIsq8lBI+h4shmy32+UsFAErwuCuVivJ4lEXzfn5mYKQNTabDbquyzWx1qt1lrkPMaBpisR9jHFWkBMgjVNpqnuiPBBCCFiv15k5sWrGBkb6vsc4jjMQ0nVd1kHZ7/cYxwnb7W4GaNpGAoKZObMZJomfxdvMSFQQ0qpyYXa9pAiKNJu3DVzXxskh23kIKIismvPiMz3G8erG1U64rw8v563ynYMjPXIcPLa9VbVjQIBvPJq2lSJ2KIXjiIGQIkAJjWsQUoJzSWq20Bl43GMbJe0rsIRNMieteQJ4okxW5W7OxY0ip5cE3whGTBLcmqaAQJKtQJGxgsP3nD/BqulxGwM+GfYIkZEgFv2YtLbDNOHDDz/E9fU13n33XXz1g6/iyfYJuq7Dfr/HJ598iuvrmzxQAKBpG7hjFUp10hDQIAJA5t6QIKhSWtrASUyiqIq8rfgmQ5QAWSKSOBan7hi1jlrfSBqhTkBt2+J8cyZWVCPAjx2BG4nVsWAc750qWRafrHMezsl+rmngADRdi/kYMMZBQIgwJGUSCGHS7AITXjuutGgxJDGGWQR8cTWYC2g+6Z5aFTIT8ogxaazO8QOVX82ytOMf7qrXXbkEOFPtdk/ymbmk6m8LYJmfeMmWHJyRrQ5NAW+nWiIN+2atN1QxTwcsyPw0xZiogsWjlkww9x9VbFdtwT+GHVnGcQAnJtQH3ufSEHjIHfaYFtOXlwqaXQEKaPIzzz/k/bRN+yCbU1vXdi/Wl+vnP06jvAN7jwS0bQNnqcVtB+81tdgYalOX3fRF2E3dMRcXFzNWZb1ZYa2ZPpu1MCer1QZ9J981N48F5BqL0vc9nj59mvexxd/cMpaxM44Tdtu9ZOtoPEcMsajLatrx9fW1pB5PI7Z3W5HQvxNgE1PMLNR+t8+ud8t+HKdxVuTPPn9oUbfrtmcEYJZRau8zZ2UdfY9AbXgx80zPZanpUkpr3Ns7HtrhUe3tAiGQBc6ZxLkheU2zi/pQYoy5yq5rGnTeYeIoi3MEAF2YjCYDAOYcv2HbCJgxJOaicQCalJDg4EOE10XVJyA5wtN+Dd+v0O62eDWMMsGQgIDIjKhqpa9evcI4jnj+7nNcXZmsu5Zp1shvoweZGStaozlG6epC6Ug0IpwvVF8GH8zV4GMgRqkdkRJIi9AxSzohok7+zJgwlmwH/ed10TMQ0rUdhs1OJoJGXDLUNqCulUWjbUHeZbn5ekJoSGrVEJXAxJqGJ2VbvJew2NpNY4NbQIhpMaTZJJMUbAlYKWl4km1jbrI69qSwIzUgONmqZ3NyF55n5hweQvrvfbEQxoJZHBShXgxzT1h8twTp1ldZtpXrOW35z9mU2j11bH9iZJE6aPE7c/ktz7V0g9kCJvc6b2TfI8wWvzcBIKbJsdx+0oV27B5R+kcdpPrQue9r99Hon+d4dcxTHadwLH7gwMW4AJnLa7OxVQNqIpI4N6BKRebqc6f/KL9HYzpEObYoylqgrMWc2Laz840wK12Hq0tx6VxcXGKzkW0WNHtxcYHVqtTmsZpbfd/ndGbLJLLrlvgRUYlNqodS33MIATc3NxjHEZ999lkJlr1+jWma8PLFy+zW2e62mKYJ168lsHYYhpx8UM9LNifY9lPvtQbOMuf6PFeWeMHCujzUj2aAIxYtlHwdUVnHk+xq1Ve+JELkLQMhyAuYWPASaJj/p5RUiFLuHonR+AZd02JqWnRNC0ciYJY4iabHfH4+woRU59YPiYAGAmJCZHhO4hoaJ4AJF51EjaeUcNG1aALhdZwwcUTbdjhb93DeI44jdsx48dkLbNZrtG2HqydXuKIn6FYrvPfVO7x69Qq//uvfzvSiLbKc/Yw2QatuCquIGBhR781cATbRO+J8n+IyqizXJQWIssgRSGVTZL+kC8wUA273W/FrewfyBHYOaMQ95doG5E6AkKaFV/9pHbxWK986J/EqZsXYP5nInJYW5xkImTMhc4AhE8+kk0JaTA7GnBwunseaPf+H2r0Dmo8vBsuV2JZmq2UidMgcFNRMx32L22MmmVPfu+8zhS1gMNwRDZhjzfplrU1jKrFHQY+BFfWDMUPZqweumwWgP+p6Djbaj/mz/jyul6PX9nm/e8R9Ux/vlJuHQDlWASj97ZglXYOYpavMJPStr+VFMx9rHotAVIARg5FixDTJ96SOlstBpfVc0PcdVmsRcFyv11nx1er1WFDs+fl5Bh+WrXNxcZH3Wa1WaNs21+rJxg4IRH52nwaSwKJFBSCDnJQS3g/vI8UkwGPU7EZNKb67u8tVjy07Z7ffISmDG2LILqJlwGxheEOer2ybpT3XrjQDw4/qL8ZGEjKQMbBXA9B7mVttabPB4D2+KIf3VoEQYfblgVGSqPqUUs7JTonBKWpxqT3iFHF1cY51vwKniF3XYwpOJIdTFEYDwHyg6LlQxuwsP4WARMJoTGCEKWGUWRDNagQlYLVegzfnaEF4ubvD7TTg7naPNOyxWq3w7MkTJGZc391he3eLbzuHu7s7vPf+e/g9/83vxcXlhfAtRPjww+/g//P//t9we3eHb3/r27i9uVWXRMjMDIhV90MGkU0Io6ilAaadAcCp3obTejjMjOgdkBLiFEoZdpssgDxx2IrLMTsFADCmMOFuv5MFSFMBEwFRv+w1Qt5S3uqMHAMhNTCpKVWzmDarPtfjcM7qchS/tOiDlBTGubtlbvWZeqNZATbga+ZELKLxQETqoE8CyzXgZLuPVTkAIfdMKjFGjCHAXBz37fdluAoO9z39Pecd6AgxcZJxqKoyG518dJu9RwMg+l2gqi9Tux6OnD+1CT7OL+5U6vCx78/u04yhR7THLBAPMm7AUbBq7NBD7VjMgUnin2JF6u8eY5KICI1vAHWbpZRyQT87hwH8OogzXwNLlmGIc+bBvjM/f3lXOiuVgNkszOgyI9JUBo9J09fg5MmTJ8qmCKjYbM7w5Oppjs9rGlGbXa1XaJsWZ+ciBPfO83dyfMtms5m5gkIImMYqS0erE5uyrMWa7Pd7TOOUU5FDCBnI7HY73GphU8vq+fTTT0Vpdpqw07iV3W6HcRrLe2PImviIvpZBly9B0ctMnseAkHB5jpdt85sLhFjL3bhiKgq5LBZPihGJHIgBD4KHQ+M8mBIaIkTQrITdqVj3ebcvA96TfKeBiJiBGT4GUJAFHcxYeYeL1QrkHVb7LbaTk6qcYVJAAGVmpIPudkLnNW2DXmnGzdkZnj1/jn69xm67R+NbhDBhGgftfOI2sQJlQKXYiDK5GQhJTj6LMSE5J4xQlOwUxAS4I5Uw58x9NsBZf2fSwNKKRk8oNU+QIogdzGFmqqxEDikB3qfZYLYgyAJCRPO28T6nXEuufiuBx652mxxO0suJz3L/axBiuf/GnJj7ZJ5RUWJOauBKi0n82ETwkNW8XKTvYyokLuJQBTbfvW6XferznnAxVF+qjzm/3EUnOLr20b2g7Oj9m7SwAQgdGMbcZRfUEoQw5yDYwpY84PZQ9dL5xtNg7L4gUU7Hg4gPFvsFG3WKcj96jgcWlBqAHHO1PNh0HBPN3UrL6zUQUG+bFUTMLjJkplgOBIDmAePmOp6Djnl/P+YCAgGU5v3bmrk7LK3XXDjHDJ5WqxeP44S2bXF3t1UQssF+N8xByKrPv5+fn6NtW2y328y2nJ+dz4TdTMeFWWIGpe+q+i3kvDavtE2b5Q9ijFjvRaZhv9/j7PwMwQJkQ0Df9zg7O9Nsnh1iDDkLqGaGx2kU0MNcaoAtMhJTkirLdf+ZuewqEGLA8VS/orZ9VJ2oh9rbBUIYoJRkkY8JCLL42yQkwZINiAnTfgBcADZnaBPQw+HMtQiekNwKnXOYOGBkAQQRAios07duHg6eSGtWyMJLTuZOR0BLQEJE2N2Cpwaub0Ce8JVVh/U3voa7GJC+meBfiET7i29/KGmtT5+gWa8wpoBXr15gihPw7xzOzs7xvd/3/Xjv/a/i8tkz/Mhv+RrCFPDhr30bt69vcX39Gq9fvkQME4bdLVIMCGGUOjma4sqVemliiUMByoITYgmiGjUlbWx2mAaNs5ikhoxVbBXVFdVlIYCJ0TQO7FuAgMZ1AnJsAQfQkC0eqhsSI8YYQCB4F9THOcziP4B64isTYNNIpk5jvmTv0WlQWtM08E6C2M42m9kkacwJEbJf2vzCMihN2Gie/lsGLnIwbEoihmfgJaWYqxEzl9oaNtiXfTcP2MwslY+PLl51/R6UCVrYoqbsV740e8fMhKaZa3scZSPsGFyCSIuei31eQAA5k62r31k1RnG4mC3bzKL26ioxwFwxIZ4L27B0UdmvYrXNJ8xjLcQAno5QnovrsnTZOv7E3A52b1OawFOV3grKLGAd22PqmLNjadDoEkQQVWCrusHabXJv+nD1YJbP3sBXpvCpMAn5a9V583UQYCJ/IhhYxiNAlpGPlIPnUp5ryjPVoHlCHouljwLM/gDAH/SdarjYR5Kea8aCBVgOIBrzHMD5WXAe/zZ+iKzasc8Mic0jzju0TVGGbVtRnj07O5vX6vFSq8eCatu2RdM2uHryJGf/9F2vgbRa08vLOVebFZ48e5Kvq/QRGV8GCIZhxDSOCDZXVwG1yebxpHooU8B+GLDf7TCFgNubm6JQGwLCOGG33c5iQ8yNVLt56jgRm39qpdfECeOTNV63LXYP98h729sFQrQRo8Qv2D8YonMgFt+Zc5Kx4pQN6ciDHKNzHnCNuCBYa7zAFtuDs8ngUQQvPxhM8r3OAQwSGz9qrMk0gqYR602P/uICG464XK/wsm0Rd3sMd1s0XQf/jNC3DcZhxDCOABE++vhjrDd3eOf9r+LJNGFzfon33v+qVL/kBneXt3j52WdoXYNpGrC/bRHCiHHYYRr3qho7Vj51YSSiWZE6s0nl4YAYAhxkIqcYQUmpUB3UTLGMeiLYERhAUvqOnAO1MnBSCOAIhSwyccSo6cJVzrxloESiLBV/X3NatMw3BYTYpJED2lZrtI25duYqiCLKJfdh3zUQAr3GOo6kbrECbM55pBQxTQHRCvNFASO1NsMx2twWkDzx0/1WOGvl40gxswG2vycH4wnKuSy2p/x+aHXOr0sAhoKGvPgbqCiphfLSCwuUzejqfuw7hGLdPtSy9Y2qdkzFhDzUbIFhvr8P2aL6UBYKZWNDQQEJ6CtBwXJNiVMGalawz6GA6ZqVTDHNAYqtqBWoOXhW9tgfwaQ81AxE2u/1seq06xkTwtCUchv75cLyez5ggRYXX223fWvG1s5rwlu27bH3yBxylzRQs3QhmKv1ob40Z0zmgbJiLMnP9WYtcSVNOwuGNcCxWq3Qr1Z47733sN5ssNmss0aKFQy0AoJd32FdBcqaK9qMK9lWgNRSlE3mpJDl76Vg4HRUD0XSkEeMw4C721ukWHSZTCY/G1eqyxR1XrN5MQf7m05Tv3pUjNVD7a0DIY5IJmDyaEgDQkkmh4YBn4Th9WA4JoRxwv5uB+aEvmnRkENoRrgk/EdMThVGWe38eb0wy4bJNLOuwA4yuFrFQAniyUjMCNudWAPMwPkGnff4be98Bc8vrvDhp5/iV379Q0QA6fYWu/0e1LY4a1sQAfu7O4RpxC//5/+Mz168xLNnz/Hppy/R+AZxH5BCwn4YpCAfEfq+Q9d6bNY9LNuHF4PY7syYCrPQ6s7FKWHcD4haWMpUCW/u7jCMA4Zxwl5R+KCMi+mgkD5rUE5UqgoGFqqWnBfLtpp8HT1s2zELcwO9VnPVhCmIGqO6Y7Z3W9zd3lbxJQTvS6XSEuQmokhzxsTP/pb95XtNQ5k5EfBSFocUI4JWGY2VhkmtyGjWhAVezgb1SSG3qs8vQFrihJhCnuqXfnpYP8X8WKcm4syCeGQ2hNkr7jgdM0BHjqGmQOUmPT35PwgyHrEWEREaHGa9HGtG1z/YKrCe0x+XJQNYU9xBGSRSnDMhdixAAF7ergDNas/ULEl9Dfm6FXAu4y3q66zZMr3wDHYc5hVy62d3cOuVQWeBvwcXtNjXjnXf8erzLd0uyz7/kFifNTFG7l/CmHlWWuShVo9F+1uMJXnHUxhxc3OtIEHiUFa9BLta5WPfNDhT942wI40G1K7y/NM0LdbrVc4C6lQAslcg45z87r3HarWuxOFqaQMJ2q+Z5L7vcoXklBLef//9PB8JII4a3CpstxlYFiM3hUkZ3zGnJ0+qSrvf7zFOY459uX5G+Oj8Aq8e9WRPt7cLhCgt6skBjsFaettDJkyfpK6LYxHvckwIw4Q9dmibBqtVh+QYUzOCEoM5IsCJwJmeYhkbQot/UGrVM/IkDcj82yQJWr2722Hc7UHMcBdn6NYr/MDz9+DON/jf2m9i9+I1dtOIl9e3GDlh9fQp1psNJmbc3t0i3gHXdztQ0+HZs+f4+JPPsOrXeOfyGdb9GuM4gFmsq77v4YglJa1t4BuPtusX7g3JWmEuin9myRABTuXY4zghhYhhGHB7e4txHPHxp5/g9u4Or2+u8dmrlwghAvs9QoyYYsQUVURKnxZD3D/5mZH5g6nQjnWbWdinWkKcYmYtbOKeK2zKNTiUIDqzZpYWjqXv2e/GjMik4asMHuggL1H0BmgMtMQQMGoKdb7a7K5JswDYGGOOjs8DvUovtu/axEegxXs07hsIsVooifKzPubWqX8/Sr8fabWb54A9McCkvwMlBdwkwq2dgpiJjy8KZoXn7z4CiLjGlYKL97THLEY1gKwXohlIBNSNZ8eqwXYZc3JOl7NF8iJMh1Vil2Ckfvfk5G+n8U9AJTSWKkCs11MvSgVQ+9nftWVrbfae6fi7OwaSrT1Gg+WY2+UYCHkMC9Z1spjf147d57FWux9MA6W+Lvt7GPa5eKi9d+dsThBQkCkhotl4bhp5B+K6EffP5eWlAo2VxqP02V0sGT8N3nnnHTx9+lQrJW/QNC0uLy+wWq3R9xIgW2cB9f0qZwtZUG7dDzqNiRvHMceH2HMfxiGzI8a2bO8kQPb6+hrb3RbjOGK33eGT8wn/7uI1gAFfpL1VIIQgNHTjVBRH6WoLMCVikRJnzu6AlMQ10+hkQCxpu9FHNNELoGEZcFbWrs79qBdTuwY1MvOiJ4nCuhAqG+OZgSkA272UXj8f4ZsWl77Fb3n6DrbjAHd7g12cQN4DMcET0GpxssQy0Y3DgOvr1xi6AZ4J+26Hcb/HuNsBnEApgMDouxZ918J5j66vQYgOjqYBDIRYjQ64HGdBBCAKexOiFMIjPdY6iTsnMGOcJjA5jGECjRMYIT8UmxTt2QC6zdiOiq63dp+lPHv3RFlGOh9q7hWYHW85kRGVqqxJM6i895imCc45TNNUVSMVkSUDKBYca8Ftzhmr4nO8CFALsNVKr/M6GSkmtG2LlBKatsm0Z10Mq64xU8di5CwRcNaCqe+v7qMnHmLuy/Ze9CXN9rFts/dUg5nq71R2KCCkFOA93RizhSg/LwWy2T1zYjGc39f9+yyDtO89VLX4zBZKsoVeWVMiMNsEvnSpWH+X8bdcUHM9l/r6KzByAEL4MF5kuYgvh9GSkcnXwMj38piF/tjzmR1vsf0x38/9r7r++u/HMxePd009dH0G8BiHAHG5X9M0iyGTTVTZzsatl/sjIoQgExYzI0wBKUYQiTtvGPbwvkHfd9jtdjMmZBgG3Fxfo2nbLNh2dnaGvrd041UGIWJg9bmmj4GRLIngPXoVPLMSEcYc2/yTOFXV2UMWXtvtdlkKP4SQ04W/aHvrQEjnG6ybHtFFTK5Z0GcRQIKDZMA4iKLpEBMa79D6TrJR+ojGiZR7CBNCCogpIFTnsU4EBRmujGHxuWspeF+Rz5ykHLeSJQg3A4b0GajrgEDwF3t8Y3WG7/0d/yfcDQP+47d/Da+2t/gsjHi5H9E2Hu1mheQcthB8ub27xjd/dQvvGpyvz9E2HcIwIuwHWUyHPZgj+q7LVXPF1WD57y77HwHkjpMFwTJDQFh1PTqNeDZf38XlE5xfMJ7GiPeCUHLf/ug72O22uL29w92duG0GtfhJE2wAqJvLysmQPjd9wnmtk0KAp944KdpoGw9Ufv+8EC4mA4vCt0ksFwzM37KJARW9WViSesCalkDTNhmgSOVRASNNI5k6FofSK6XqlU3ROyidSs9tKeUhlrTgGXMSJaXPWKvRgoVDQIgBLknBuSQr+QGMm4GT5RNVIFI/v7z/A5R9XiiqwFFjA2ZMyCPWD7PkZ//qtOoZy/PwYnNqkamDWR05wFfA7kSTRWa+SJrSsF1b+b4F8yLvr5srxmR+f/W+y7oimaEEcgDwrAKuuViouFiWbJmN7boZULZ3bgyLfacGgssnuHy+NRBZMm11WzJzNZO4ZJnq7z92YWO+v6Lz8lruazbu6/Mv+z4RYbVag2gDQDPl2GLdOANxhtTLAnNmTMt9Jgx7Kdi32xJurl/Lc9J5yFxMtesFkDWHnBRktfmquJz9DISYgWTqswZGuq5DqzEpIgDZqDtJsm9qxsw0ROr1Nbvw1fV8nRjT9MWVft8qEAKoO6ZOO2UR5WKw+jBZ2QkLkCtRvWZdePJonGRUSHyJy98p4KM+a5m4808GjCex2Ae1keCZxV0TEkhF02g3As2AVb/G+eYcq6bF09UGHCN2nHATRs22cUjOYWRGAER4bQoCKiLQNK2AkGFEigHDfg9OEV3fomul1kGr+hkSZV3ki4HCENRiYLYAx1VE7HuJDFdFQSlF7dGQA/kWzEDXdgghoGlGNH4EmDGyDhQWH/SxiZ718xKEWAbu0bdNxUh3S2o+z/WHE0Y539LaMmBSUnAtBsTr4K71SlKKElPSNlJHopE0PGFLpN5F4xuwVg21QUtE4GZeGCwvJCxp0gDgk58N7pRSTvWbwpRZEpvo7DguOaCyZhmHE/ipxSEvDAfvpgSGLheOwlLoY8+BownMArxdkvgsJDxOe4PLe7F7y31GT2Tj9bHt6L42aOv9QJkNOHocWDxEtWiD5n2aS987eObVvfGRBf6Axai2yX4KQmC1wg+BITvOLhq4skguj3vA7HDZ1x1xj86ByOHzOQn2mB98V0sX0fKal9vua2/C5LwJS2PHll+q+cXAX8UakOUMC+UuQyozwTQDieW6zRCJitXV9CVJvbRsPgDZoIohIoYgTKZuM20kIjOmfAYh9TxmIGS9llo9bdNIpXTNCJKA/hXOz89zMCwRZcPr+MOXe9h1hBgdDgtCvVl7y0AI0JBH51oRKvNCj04WdDONkp0CB+9Is2LkEXECxv0oLzaV46ybFaY0YUyTKqQKWq3BCFU/bY4sfmvkqcK7FkK3JVBKCIngJoBThHt5g7QbMe4m3A0TJgDPqMF6c5HFdgYkvAoJU0xIjUPjHZL3CKTI2EnNlpGEQXAAqG3A7MEpYdoPGAFs78rQgbljNO4DRLnjyqC3CQDYrDdYKViZ3TvL90AOMSbs9luJDUkJq75H8B4wsKfD1iK5Z0g6BARNkWR7wvXDPNFsQtbLX3xy3JKr5yfSe2aJvMzPpD6egRTOAYfANI0AaMaOWMR6tkTIUu5KqrAxT86JpH0WYGtkf6++YQN/mYFxhUExy3n2/LgwKOM0zHROYv27/rRCXnXmTmJNs6MCAEOIMMVRIsrB3kv3TlRrD3mCVUsdAMyKlOHzcNNz1bEWR4NzH7HOPDaGID/XEwetmR67RvvpnMt/L0FBHbQ6Y04ANFSmWAMBOf6nYoNkh+p2T1xnSZesP5sDcXt3me1cAg29fhcP2ZRjC/Z9a/ibgsRj7MmbAIr6WKe0cj5vM6ApFzZnzOp0eYujsM+y0m+1KEgwsTUZWwZevHNA22YD4uAqiPIzJyJQS6poqheGAmbKz4jb2zt4v6uOUeJQGnMpk6sC7lspveGdVP11lKv/EukYR/l9xr6BMHx1jZf/lx8A8M4Xeu5vFQgh0pgQrVYL0gWUJXo5hAhwgGOSei7QLBZmcGRM41QiismhcSLpThFoycsipHY6w2JNqimnGGkAm4Ui/3Xk0CpYMM0CnwgUWADCzRZpN2AaA1IIQNvg8uIM530Hdg7UeNyGEbvdraBq34k2iW/AbQeGA7gonwb1OxqFmH11MWIMk9Ljcv25s9O8QBogE6LUegA26zVW/WqeI67/nCqyGmWY08naBt4ROEWhJHX0yOKn+hm2iGpwJnMRjTLhrftbHeiq7+TAyjAr5mTvyd/1vlpwZgtBmdxlcQ4KbspkXqf+OqPLqQQO2nMx14xZIn3fo+1aKSOQo95XM32BAnLcrHR9TZsTkagvDrvsorGgVwt4NTfObr/PKo1B6xCFEBA5qqU2BzjE1YKk/WpGPqVSKqCe6MSq1uefWPXzTq8ORvcurXTrGzOKPj1ugXoMLX8KgBxbFOtrBZCZLNN6qRffpWupjmcwoFkf29xxdj3HmAoBGvMsjdm/2bUef0YGjA2Q1C4dmafiHKy4ZR2ePNs92I67cubP0O6jbp8HgNi1vQH+eZOjzgEFMHun8VH6oMp8wuYX3bp4D3bs+96hfMcfsFy1GrJdXwhTOX8eW9oX1T0kTfpjo+6YmEpBQgMhlulXM2bmojGGPL26xP7mq/hNBULAaqVEFkrYEcCSsksOIN/ANZId0ySIayBF1RQBUkiAh7hiyCG5BtG3IACd6yDynxJsWbgQcd84LelsmR8MHI5PTcNzTPAonS4RiXZJjMAU4IYRHBOo8aC2gY8TuhjRx4R1kswbz0ALQfoxMpjMJ60uqVZiPHTMoCXC5L26b7zkeifO1XQjF24kT36QQSIdnDU/XCWUdWDYYu+yN0Sq8kZOMgnkAVqAgliOJExOYqBphKHKSp/Fqs8++/smFC5goSB0CKsDscihf9ettgyPHnY2AR6fxO2c8hzK9+qFJrvjbLsuJDbAnXPY7XdofJNjdpx3uY5FLTtdfL2uMC0qe5/dRJaiyxZ1bwG1Un3YFrnVeo1pHBFTmoOQGHK/4JQwaiqesC/S8/N9qMsspSTVkQ3QWh9R5gQGCI0oobkb4ZQ1XjMg9b45LqNieuv4jrrleIfF5+XdqeVvmgaVlXuMRbF+Wbunli6qY9di+/hq0Tja96iyunlx/OraavCSr2sWN1PGRf09+/fQ4i841DLaEiiV4G07Juh4TZ5TY+qkK69aRB/THhq7cqxHHepRbXZd+n5AgNM4NAOfjwFNCikqNvrw2R/0Jz6YvsrFHLlGW1vqazJWRI5t7G/p85nk4fn4sz5oBuvh/ej6WWX6iLHxmzAwFQA4JPAUpVhbI1kdjZPiO03rwGglAyaKZZemEZxEQCuMAY138E2HzrVwHnAtMFGL4CM6nrBLA4gHRCQERb2yeDSSaaOVQVMqRbaAPF5BYLQsAaFEHuQbMAG7lDCFiIQ9IjO48eLnazw6l3BGCS4l7CMwgTAwITAhJsaorAeYwUxg8sB6I5O/d2AijGHCFCKmGLCr9DymGBBiwmDpZykhQQRnogIqaqQDxhQxTinzO4Qlc6L0fRSRoBQmBPVlkrfaAzJsGkfgxsvAaMQNElNCMIXSKhskPFTGnJG1TGbNLPLZtuIqAHBgeZxqBrbK3/dXZ62VYa1QoH1/wHA4iVbApG2lunDf9WhaBSat6Jb4prBMudS5sinGmvjGi7vHS1BZ0zRoWokJoopFqS1zY0cmzfOPs21T/mlVRXe7nZQy19gU0uC7bIVV74KIwBbQdkSwq449sAU8M2IpHbAY5v6qgcyMGl9MfLMqoNWztr8zONC+XAOQ/X5/kIlhANmUTev7rBdT+16+X9AsHqZmOupmACT/pBIQmK//Pgai+nxWZ8fcdRZLVH/lvsUzHi72GYTUnHD1DvO7rdLkH+MOetxYfFxl5PRIluzRrR7HNO+3BkIeVdgtz5F2bYf3fNAniI7ud2r/Y+nQGZCePoqkdCuQTbMx4hZnpzyHZmMxzj4Fa/jDF21vHQghRkkBVPSXLWNYMKbWUkkMwCEn7CoazNQ+iu5IQx6JEjy5jH6tAouKLM8WKtLtOTXXJiGdWuw7lr7rdSgr3iwTOovIWgtCBNDrd8AEl4BAAFMCM5XKqc5VdTPstswa9Ui+QXQJ4CQpy6TWLSdQ1JouDLAuouWeiqWVB0VN6ZlrJ1P4LAFyypSASIRSMjVrx2JF+qS+0gR2ToKFnYN7IB2PT43NPEkuN1LuJJySyK1+jnZswjywKFH60pLWr383K9Zq1BjL0kSJI8nCa/4QhDBzro9hsSUJEsRKWGiLVJQquWItFTBpDE11DU0DToypkTTlEERa31w8JmDUNFIZOip4mS30eh6HsnAffX4La/3Uc68X9tmDfmB/s/DLWNcvUdmv/p4xTtZSSjlVc+YSs++qlWwptsv4kOV12XXXgIipYlmwOL5d673UYMWOVM+zBrpfaHGurWaYW/e4Nb8EYsCcQcwB1fcwG0uW5DFAZfndz9se40J68B0vty2e1UPXeD/bc3h9p/d/6FnQLM2T7Pg0v0NW41SoGXv/i+u6DyS/YXv7QAjE3ZGCCFgxyiLlSDJVPAgNAeQBbsTm8M6hcQI4iEUbRPb1gAP6phPNkCAUZUSC54BEgISf62JDWgOBHCwuxMBMQ438lSJcioBTSgyMzhGcA1zfwG/WYO8R1z2S9+gpYQ3GnhN8IIyccBcJQ0qYkLBPAmBCVP0QIiSSrj7pxOid+OV7RzhrWjABoeuRIDEZQxJ1zv00IqSEMU4YFK1bepnlrhtrAQDBsltJwQUKFVxqbKgFSAq7SDJQwhQUfCzjG9S37hhAc69sOwNqdWudF0CAUW1h1qNE74UVRCUinRTKRG9uiEXHuneCnO1YNalX5B4c/0QkVSsVrMQUkQZJybWFCFSYG+999tk27VxGWgTpil4JEQkTYgJsGvW+Wq2xWqvSorNgWJ8t1K7r4MihX/VofJPlmGufs/0LIUhlUI0vsdTn/V6qeg5arjyGKOOSi6sjBFH6TSkpk8gHlpw8y7myp6UCSj8w98DxZ2uR/LNJ21wUlZqoBU8bBb3ZbDIjkb+vh8gBhxXLkF0djkCJZt+x/ex3AFJmwM1ro9QslUNhEu7rO7PfGRpYjKyVxOBcRdUCGc2lMGvHWJYT64lZ1zGF6u9DcH3qei3OoAYZtaZO3deXIOVhcPHY/R44ygIALX/PLJn1JXvW9w54A9C/sc2yZe7dB1BLvoyFU3FX8u5OH4u9l+yvz3/JAN5CEALWZ8haswM6hkiLI+UAMu0EzkNxhi6aSjvpl0wSuXEexECggEQNAick0sJrjBx0KS+F4MiDCkciGTkkRZ3UW6vgSCOjdXJtvBYfazxi2yB5YWoAhk8RI3uMSXxuLjG8LpiJpQ5OSsKKiSKKolmSyY70X9M2wpaoq2ZixsARMSU0njDFiCYQXNC6MlGDSoNEw8giXRYSmfwJoMLAgJB/Fx+hTTYCRlJIOYdcAqs0C4TEenfaeb0T2/lYT7ZNiQgxOVh8giA7ocQMycsXFmAEtggZAPGFyUl1qUKZrGeXcBKQzLcbA3Cf5XlAdS8Gfr3w1QGQdbBgTW+LDkkzu5RGmRPL+/fe4/ziAufn5+ru0c80DoXIoVVNgs16k2Xsl2DMfjcXTUopyzjvdjvc3kqBrNvbW0yTyDlPmAfIgouK7DRNMt6qgM36XEsXzIFo1eIx1+DtWEvqfqyBQba4QTl7qV6Y7fy1DP8y86gGEylaQHvF8iij6OFnzIT9NIbgsa2wlQVY5KiDinExl1h1M+U8BkBmw+T+JSSmAMTivlp+7z4gUuITyncsY67OOFsyWZnRuvd56M19SW3GpKEakzW4rNoxIDK/5vsX8MP9v1h7bF8iIBeMtGtILmXl3dnxKvbw2PGTK0VNv0h7u0CI0qtGh1qBJfkvVKPCgN7cSs7AgxNSiIjMqnYpCnEcxM9NiUEs+TFUr292RLX2PTWyUJCqruoqxgpuEsRaSaxAqXGAJ7TrDmcXG8B7pLZFcg4ejJYZQ0rwvsGUEs4SY8/AGCO2ISAmxj4GBLAwGUnySwbWPJMECU4ICS4B7AjRkzA5+i8ygyOjZUld9uSQkDBAwFbTeCQnFSkjFxCSEmvBPgtiKxOgAS0Qo8phQUICcwSYkJhAxLN3cYziXbb8XkmC/ZxZkJYux5pirA9eSBALqLTj15Ngqo666Fh2orJzdRW26TBIL6e73mcxpCOfLw9PmE1qeUGrUjFtwg4hYJzGfE3AfFLfKSOy3W7x6tUr+Crrpu97NKYno8qwZ+dnshj7eeZTLd5WX6pJ4Vuti5QSrq6upJ5Q5Fz0yoJhLc4kZ/BwVcuiTtGN81TkZYaMLaDL3+26l82AW3lOZdFk5nkZcp6n2trfNeCwd2BMjh07X7cyPfWx6piI4jIrGhCHC9HpxYsU4GfAmsdZCdg2N5Ld/+zF6X0eW/xOuyWafD1LF9zsHR0BI8cWLktTrUGjsSM1U/mYbCeyeffefQ4zUh7az8Y0M2dLz7ErjNeDAIRBDih+ZHteh+f8soDIfe7N2TkBXa8qAM+uMGs2RxvwoOPvEdCirl8CDny7QAgAx+KOYfup2xnC7lMCrPQ0eC49Tdqp4jSBgwRixjCpxRVkkUopgxmnFlSojQd1LbS+gacGjZd/KZnkrSAXdkAEY2JN1216UOvQb3pcPrkAeY/kPBgOa2YMDEwp4XyaBHAwMDEwTAG3w4gQE+6mASNHDDFgP0lg6cDCkqQmITkCOwKPAUzA6IDgpH5F0zZIYHhKiGD0IIzOQxOGBMi0LeBIg1aVSlcWJqaEwBGJodsEuGSyvH5GJmSlE7IE3zkte191cvvpgPt7s+S5A24GQiSdtiwqkvGhfaJKjZOuMLdej7ZHDOLld5m0mvCRgbq0Og/u6gEKui54t9wubori8ijuLpcVXO2Yto1I6lZ4q6Wj7p71Zp1jUCy1eHO2mVX87PseF+fnOZPHAmpbdYMYI9S4Bo1rZkzIMA5adjzlolivr18X944CFEsnHsdR6lpUQm2ZleDi0jFw0qCZp6Au3kcdowBUQcXVJGqgr2Y9lu/EXAcAcv0hoIAQC1qcASmrzlyJy9X6FscWpnt6DIy1s6wWB1cqXzkBJpbi/VB7zKLFSPAWI7cAHDUIWaYT1+eo/zYQYs3excP3ftgeA0JqMcb7mqUyExVROoawBOZCzfdyTwibOf4cUcYgdrtC4B6Czi8LiNT99lQTNexFzFX1CK3f2mf3xqssArc/b3vrQAgAzUIpOfv2srMfTi1iBuCSlTYvi0JktexTygsaaUaLs9o0EOVTogRHrCm7SpOTU7VVqyvSwDk5JnGCT40ukOICAWkJ+raFb1x2FTEDIC24p1RLB4ljAIAGBO8Y8C0CJbiWMVHE6Bx65xCZMbKwOoEYkYBIjMASOwIwHAtQIJL4lkQqcqa8hQGQaFYWERIcAsyqkniU6AiUnAbVOQEmYFiR88QVOyH+FnGFMQCrQ0wKBInyT1ll8ttZvGgcBKUKC2tWqWxLrOwXW/QHkBSMsjIk1ddQcSyP7nOnWj1hHfnw/rYkZbhYJ4+dmA4mCT6e8goDYAB8jHDkMPkpuyKapkHbNBjbEb7xCDHMCvt1XYcUo+ynWTpN00hGji7O5Bxa36JrurxA2XXUBdRSSjg7O8s1dEyyftWvJEOrAiHDXkTZTOJ+WWjMgn2pZha4ei/VIriUBwcLy5IoHSyWx4DhgVvNFt3qf/ZebXLO1jWXfsKVxXls4T418csuc1bFrPIvk9qft3nAqZ3bzjdTCT5xT9YXlgbAcr/aJfIogPSIfWqQc1+z6tz5Gqs+NDsXn34/1oyfN9CxZMLK9QOPU/Z7XHusG4v15KfuY+lCu78/fvH29oEQHYiNc+i0gmIu3KmVLVmtMLDIpxMk9sE0PgKLY0GYEs3u8B5e/e9MEhvRckAEA2kEIYCch2saePJYdz0a16JpWrRNi0SyKDMYY5owpYCJA1zYA46wutig6VusVj0oaYSpsiSOCR0DiQkN66Ku8u2JPCbfCRDYyNemlDBEOVsgYSRuhwG7acAQAm6GnaToJsYEic3YU0IixqQumugJwcl3R/JIxGCN+YhgTCAkPX4EIxBh0kkveAMurLEpCVOm0NVFQhqTwoQUZOJNqfhWzY2TorAuZVvVSNU7AWS9AiIFH+b6QQZAjgGnUui1CFktQAYApCXrH+pm/EgBrHhfirGd5sg4psUNWyzIbNDT4UJIKIGY7iAl9HDiJSAHGtM4zpgCiVOax5wIqFBtEuezjP+ZVve0qsLClIjwWtf3aLzHerXBZr2B1wKAzkngq0lES0Ctw9WTq1msS+2OmcKEGOIsDmUcR4QYME0ThkGAyTiMiEmAyn7YS/DsfhAgM0iF4vxcuMjj230yGOM4ZvdAnUlkz6b+Wf/OzBiHUUZ8dg8eLp72DMr70QDrhcrqfVZsWQi123KR/ncaK8U0j9lInO61ZHO/fWAhIVf6WM2u2c+aXToG+paMSX3+YyDEOZeB5n3NgNxDCyGzMNQPAQcrZ3/AANDifnGctbRWZ2Mxln1nvq/0x/uv/02alKC4P7VZe68CkcP7mMVjWRzMiWu0ukhftL11IETWLpk0cg0ZfeHMKTMApaAQ1FKQxUqEy5LGfVhxNSg7IZNutvahzAY7uKT1ZbR2jf1rzI9OADmbZGA8PSaKgIPQ3VpcSEZOUiDCcCwmv3AxGtgqKy6SI3RqwbITRmHihDEmMAHRSR9pADSQeI8AQmBhOzyzELaa6UMQl00kQkMSu+KJJN5Df0YIMEqQAn1Rfzr93BN0P2FghIlgJP1OYoIEsTaFeUpA5IiQDQoCjGHSxfOwOwtbIVaFvktBJHO6naBsjCRkM5O8AxJKyLkjltVD1C+zBN5+SRYZtB/WYOTAtcN8UHelztzIgXuu0KlW+4bNcktFjdaajYVTLSzcF3LsEjAIkv673+1QalYQ2raZVetsfIOzzR7T2QjvRd9kWX/CalP0fT+rUmzPCMBMBdZAyDBKWfFpmrLbxtw5d80dQMgViK3CJ4XT7zgDn2WqcXXP9fNY/l5/9z6thDoFmBVBRAK4AqDLa1i2sqgX5qVe7OzZvak7w6z9+1q96Nb0fel/BkzcAbAS1ksMgiUDYM9iyaosXWcnr4sAsREeNz7fhFnMQKQaZzb2ag2e0wd51Kkedz14zB3qvnQinogP/8zd5tR98CPntS+hvXUgJMUgMR0xIOmiTE4L+UAWS4ZMlOJOkIFEzLnAGoEKCwIDNkblsnH7onoKQptIVG+DsheOkXhE8kkWaOcAtRrZEXrq0KBF74BNcw44Qrvq4BovVtM0AVwyeGJikBolJiDGIglrCXzCAHgPkINnRqPBohFeF/4Exwk95D4DgCExAkshvJEEVAVdoCORulwIQVmPKUq8RwRjlIBpTCyZOAHChCQCghOXkbh/1AUEiTlJcAJGmBCjiJVFBRAhRUTNJIjqIwvJS/wJii5Ldu1AwWW2HrVKj5gYmtJJ5V8yt5m9VJK0WA1g5uqjejGRn6naR4CMAd48WTNOLDgPzzrFhrq/5T5ofwPZ72R93FLriCzzaB7B3jgZ1ubfPXqeambKz3RxHYwS8DjxhG0saowAckAokdXBocKEqIKrcw5tVzJ32qbVzJ1zEWtrGrRdO2NO6n9WjLFVxnGlxbaMPVi6aIxNsTiUGCOmUbJ1jC3JLqCYMqCxYyVOUuKci5sopZQzYO59x7T8m8BIamtwpvmBEsOzzJw55p7Jx1IW+ODzDOzn3z1wK1RfSZxAbr6YLhmA+r7KuCgAQtpxFrCwFAJo65Obm2LZ7Jk0jUiVHzzu+vkyEOKhKFt9/se0mrWZs4cFbNm12c+cSl4Bwfn+dNzI4UUPYuRyByevn2TtOnY3M2CX/3PcmKu3Fa6j6h8VwK37k4FoeS/Cgtq502aN28Z/YYfS2wVCWKsPhklYCu20OdVLdUBY1UoZKfdbIglkJa4quKoVDkPu9jeURdBJv1XZ/RSVwqSERD4LPqXGg8jDuwbwDt47tN7Bdw2aTS+IWg827PbY7e9AzCo2RUBkUNQAU9XCkIVTgzedDc4W5D1alrgPJkIivUtO8MzoWRJ+AyCVeBMLcNCCShZkGxIUhAggSSDspogxJEQGRggIGTPjQRjJgQmYGmFoIkksiQATuZ5ITliSRJicsBPRqYpg8gi6gAaN6o8QwTaufgZVczVAkjhKYKIGakqMA4Gd6rI4D4vD41gNXgCgheolCuslXcpcGOHAkhOhmcpaY5zIqX/AasMjQQgD4AyjFgfRlYA0e0C1G5xLsPRnK1Zlk0bOPrln8Tw6WdcgSH8PIWBK02wb17+zgKJVv8JqJdokc8amyF8753BxcZHZkF5VXy8uLnIQbNd1WK1WePbsGZq2yYDFQEs9AVsp87pWSp2Ns73bIoSA7XaLYRwwjiN22x1CCLi5ucnsijErmX3hIQMQq680s9rrUutH1h15ZRIgXS9ypsRq17t0XyxdF+Uch4GYM8vdXCPmikyFrYkL6rwwFQkHC2x1TmN6aoDHPM8cyt89GfxJufse3hMdBNE6L7IKx57BbNs05GduIKlux/r2sbFr92Q1v+5rc/aH7vnnZ4zJEgTqqWfGQ75GLJmKOR+yZFTtWuxe1OSan0i3iAEmW+ug4lOMIDPgfZVZV9UiCusVdt5hwhdrbxcIAZDBA8oL4kTZ1ZKcAYlC6REgbhhA38ARyDjrI6ylvPU4EHLEtC1IVVbNJZP1G7wX+fJWwAj5IoVrxcEa59D5BmCuao5IgCyxSLfLWuNy10tR1T+ZgSBqlyK/TgjGcIyjZv0EUJjgU0KThB1JJGOaIQGwTKU+TYK4ZhjCGHTkEQkYWdgRASEOgRijEv0jAzEJAIlCQAigUWYkETAlBqnHKbL8FBE5ATyN7Q9WBgWIymMEy/gBy7ZEcBxLYKG+Rxt4lOsIqf+a81vLroV5F1pM5OBqEFs3EReQ+foKMLG+UpgVXs4IfAhLalblYPtsw+GEdJxj1c+ZIXopQKq0WmQCKYHXpw9Q/8rHP8iXVhYOm+yylm5eDFSQipDFvGpfOghaydNjChPaocV+2KPxDcZRgmK7tsvAY7vblowcL4X++lU/m/DbmVBbNwM/FmtBjiQexRc12hQTVqtSsNFiUfbDHilKHIrJ1o/DOAuiNaaoBg0W61HHRtSxKHVg7Nw9UYolHnvep97DfGP9KxnyzUyWcap5UUysae/z6sCzY2tfp1RtVwBCTAeL1rGLqjdzGTDzc9Sswhs060ezYy/P9QbbTpauX7RT7rn7zjP7Pqj8pMP+IMZTpZkCPogfq5HKsedKWLzH/MNkBkqmVx2zNIt/UbBhY8sUnO1zNiP6C7a3EoSUl6wLgaJ5SZVUkOBF2VQmf1QTeRWUMz9qfkmZIdGfxBq3AQ3UI4++aeHbBr5tRXehkeA88h6ub+G6FpEjRi005shLerFr0a9ETjyMUmmWIoN0ckMQlVFTWrTMAJncZSIbQ8AQRtUOSYjqdok6KTRJFvNWYW+CAAOGsBKszEVwyopAAlLJd6CmFfcLa9AqWANVE0YkBDB2KSBwQvACRowJSSRulkSEITK2UyouIEjWDCubkpzL6a0mChftp77jCEaACKlNwQq3sYAaVBoFgkIgCc+21lssCQEHIARZnMf6B1Fxedj2Y1RpqbuAbBHGpeV6BISY1P1hb57vS0c0DQ4MKCpbzdJmnlvaGYAdnPHzNXI0m6QLG1JcWPZ3rWGSGSSz9jU+YLvbzjJmlhY9kWSUrVYreOezLknXd9hogGzTiOT9arWSbY3HeiV1ds7OzrDerHPtHedc/l5NMWc9FA3AtSBYE2WzgMW7u7vMpkzThN1+h91W1GLHadTU4gHjOOQ0Y2NVrDbPMjahjjUwsGQTfW1xnwIvdcsA2Y4LAruybRYcK8FTRxfwpUsHQJaxX7qKlu6ex7hAjE354k2YZOcXY+WR17HcJ6UkBSAf+O4STNo2+2nbogq8FVXp8g4shZqZC4p3h0BuCfrrc9p36/eSvweafR/AHGwS5/41M6DpUBhxua0+5tR397Bfj29vIQiBzPJswMGqUYrVqqVVYGmhxXgtzMYMMXKhqWpwg5o+NOt4YV2TFevSTzOwYWSV09xhnYIipeqYhCFgpQk4SlYPx6JQynocDqo9YAJPYUKcrDqqCq+hWOQWdEvOASRxMUlv0ilo0CtWh5XcoHMiZZ8ATLrVASUwFRLwyizAIqQSGGtpwfY3GAh6XXbM6g2o8Bk0bdhiTOSNRmbNNrIcfYC8xJoEJ0qyiS3AD1miXQa6BWlqxM8Rntw0yzI7Ub9D6xdQNmpmyUGDj+U5slIBaRFQQbMjzbrQwX6H2x6GDXzwl1mlCsZVP8Ud8xF8zpZrpSwsNAFwcuX5ini+KC2LrGW3QQ3eeMnEyGS93+1nWg9932MYhsx6OOewXq8zizKsBnjvhd2IIWt5LK3cWpTN4lfMNdL3vbAeIaok/YC2bRGCHG+cRnS7Dm3T5s8lULbFMLSIMaBpmsya2DM5lkEinyWkmjU6RtFXAOTUQrm0ZJfPMj/zCqwsj2cxT/XCZ0zFMWvfgMh98UfHru+x7fQxCahq8Mw+eeAcn+c6Th0nj4WD9zMHDfb8xJWsa1f9jOs16Z5rqxmpPHUvdq8ZrdnPxXRoYNcAfR3aUCvZHlO1lWM+rjjoQ+3tAiFU/ytAJFUvGkygFBEmoZ0ojyPW1QcgXXodiuuRtONQxYQwQfUwZGGVYnAF3DBDgthoBKYR23EPJmAfJkwpwrcN2nUP3zS4vLhA0/ciphYZKUTsb7Yicz2NImecGMFkofUaEitAAeSaIAFZIQZEresgKa4FFKkQOpyXzjdjQuQRwTv7nUtoWRxBFHO2DQPo9PsRCRMEHIyZvZDMGQFUGhvCTpgQBrbOq6qrSs0zI3KSINggP5N3YK9xJzC3TAEhQV000ZeYFgM3EQqIoC4hZkzJCRiyt0kGUgpIkxvX12wZSsnPJg9wyZxitokLuegfO51gnEdDC9lvXswLLHR4Igkuss8K81Za5CRB0LMjLmHHkZlnBgLUMmM63O1IO+ZjXjZOLIHZ9Y586OhpmpLtksGH6bWAS2n0yoJaugzqZmmT9nMYBuz2OxCVQn1NK26amkXpuk6ARdsIm6KaJ42XmBLL6jk7O0PbiDun60X/xPZv21bO4SjHrqw363z9JrxlTEeYJkxhzEJtMUaJQ9FYEwuUlWBYyfSZJmFb7u62s31SSgcMisQt2aOv+lttMEGCles6PAQN0LZFRBfvmWV74v3X8QKz95W7QFlsl9b6stWMz5JFme9YAOlJUM6Sdv5YVuWYC6W+rrpa+LFj2ndq9qhmQpbgMsZKLDFPKcUArkGp3mi5VypjcgkEjFlxrWjjOFpo5Oi15v0sfqVyUXo/P6Z9p97/mMrsErTOKj9/gfZ2gRBrleXJajWX2VD9ZxwLMwGAOAFqjzuYUJfAQqO3KYMQO3b1D7aIUbbOmaFaEuI6GFJE5ISbuztshz369QoXT5+g6zucrzagVi8hMTgkTPsRw36fJ6OksR7mI86dVC/J8vWjugBkQR+VERIQ4qCF9IjkPp0yDhDA4SCAhJIwH0yAR5J74wCBAArFCNl9EsHoIMAsegd2sthzKkwGk2TQRAdMIGxIwMAO0CwdCaiNzBhiVF0VqRAcCXonsl/U9N0AliJJjQM7YWICTKdEgMnI4oqaEgOajit3gnIfxoyYOWAPhQxMlAhxe/naLeT7NsFQASRksz9XsST6H/uubdS8nrxaCFCpQI/+FjVDo7KlZvucGBCz8VCOZ0zFA5YhjluUs31Y9FYetjKryRxVbASOL1Jk/ztyXBsHdRvHEW6YT8g2WdeLnH22zL6x+JLVeiXBsOcXOc6k73usVis8ffoUXdfh7OxMtvUrrM5XWefEe4/NZoPz83OAxSiQYnsBKZWMnZQSttttlq038HF7e6PF//bY7/cYxxGvXl1jmibc3d1hGCR4tg6GrYNWj7r1qgVQxBOVXnc+L2o1SCMiOO8WNP0hi7LU7LjXHXTk53IfYerKvGbs2Gz/I8zLQSNkl+rBRycWz4fuoV5kj7nNTvVRey/13yYLUD+PXGNIx0PipPF+J67TGWjw+dkZOGhbiW/yroD+msUyl0/t8gSpenZzP3g4dZ/20z53zn0pTOtbB0JMjZMNRVfoEcqE1H9mq5RcVWsmRwzUR9b/ZgePLmB2zPm/lBgIESkBKUiMwpQkfiHFlMFGChHJKyAiB6QEjkAKjDhJxdGg/2qkTNX/ilVgOeq6wBChYdMsLUyIldETGXtW9wvbeikYzul6yNaPbLWt7HOS4FT7GQ2EGEvkKH8lQcBKQ6pBoig9QjqZFN3T7BkiDKTxH46Q1IUzaeBrQNLMGwMhQEiU3T7mKpIYEog2CoveRaPvbGJkBijqa05WDdnQl90uqwYDLRZL3ZaSubuQU4BtIiHQQRXgZbqrdchc/C+D4wXoBTQI1wJzbXIuVqO8lvmEOJuIK+vyy7BSHtNmdH6KCKGymHKXPrR2zTXjsNCGqC57GbdQ33sNDO3vXDBP5bZjFL2QSDELlQ3jIC4dL+6ezHq0Dbq2w4sXLzIj0rYturaTuBLvcoDs2dkZLi4uioUJgvNFt+XYgtb3PZg7dF2b2RL5F7HfD5klMaNkv9/n/YwZMaE2C2Q1JqXeJrFjutgpsA4x5Gee3WDZuClWtfNzS7gGPbXbIWe0VM+eucye9y3YdhzrH+bqO+buOdmHWf6zzNC9bwE91Y7FXBz7/hKcHPtcj4i6NpBtzwrfOigMhMwYknoNqETiDFQcjH2UMWCAcxnPYWwJZYP7/mdybO54LOP0edpbB0LUJyILqlqyOELjOltgnUVyVK4ZTvq3mcPzNl8aBDxInIUs9MyEGJLoY6Qo4ANagRaMFIN4iwIjDgERsso61dDgiZEmxjREjPuAUScdsdx8npjl5MVSrS0/kIIMNHnQG/xyZndb568W0bz+FtewZgJBshkO1gqFbFRs8kBKsefrKxxSdE4AhPeYGo9EhMkJ8GCtbZMATNQgkTAWIbMeqYARFrXWCbLw72JCjMBEJRNHroMwsuiYREBcRQAmrd1T66Ewu9xfiOU9QpmiWMUtWIaDBMXKexZWpThJWAGCcx7eUjV5tn4uHqQ7BCe6f36OzHCmVcExFxFcFnCr00PrIm/m779PPOu713SxC7V2g06i1cS5pHRZ+5J9lp+j/t60koZ9jAHIDEs8Xm3Xno8p2tbp1Usa2n6vi/fVlmirRf/MjXNxcYGrqysJhl1bMOwGK1WHtW3n5+foe2FZzs7OlEVZa/HAOiBQ0o5rQJEDZNVFc3d3h+vr6xwgK26cuxw0u9tJoOztzR32+wFTmERBVuXv6wycWj/F4m2M6TEGyTmX2Qp5kSjuHWMHdKG0Ehj3EWp1HEQ+Jlfv8cgib+c7diwXCSndrxBas8oPtfv2sWszTZmZq2MBDASA2L95y24WZXqsb+YSIswzRgPADHxYn9SHkMUJyWlpEC+V5A2E2Hs0EJNSVCXh+0HFKdDx3TBs3joQYgshUKzYYzvxPeOhdGqx/m2RZ1Tfyb/IVomzqI5YWZwHA0fhiiiqSoE7gnaYINVFQ7DYDzuZ+eDqs9gNLmi6vIW0sqyxPaRHKhc5i4mx7zFKsOryuIcGa3nesIW4XkTm+xESHKneLDmwk0KAiQpQkZRhUVqdSFRdE7GmETMaNubEWBQS4AdGA3PHEILeuwMhQsCGV3bEQ7J0ApBBiEUE2T9hJhyYgUhJwVZC0oqZzAmkMQzEsh2ApoMLiHVE8DbpUHneB92S66108CPXP3JiGTqrPsxSKdVSIkE8m2TM8izgiEXKm05bdoftuIX3eazK5T5ybwSYBVwzP0cs59pSrq7u1FUXcLa89sVYBTR4ctnpF805V7QzqGyzwL1u6HLga0oJvvHY74VNGYb9AQiZpgmr1Qp932OaJjRNg5Qi2rbJuifOe/SdGDuFznc5W8OkzM3NE7WGT4wx66qYuyeEiFW/FhBSqctut1tMYZotprut6KHUsQXL7IiUUs7CyHNeNe/Zc65B8PL514tm/X5YUbi4KasOU79DWrzL+vvk1No83Yz9qq/lGJi191z/vdyndssswet8rOg8fmLBrlkkp+wsCGAnAMSk+GtmsO6PGbjpdebvKBNoRQ1rVWA7Tsrfq8boI8d5/ezKO/3iDMlbBUIY8hAnYxMrDQdbcPMyzsaAFJbA+qupYXJGMfYt+Zt0M+sAaEiCLuHsiCiuDDg0ziZXU2n18J5xtj7HO8+eixXFDuPdHru7LW6vrxFDxBQTyDVoWgendXBI41siA8ITUHXvcmKxnD1I66nUsSxWATh/SbdnzUJ1pTCXoNw8/pkX37XnlZEMGIRGJ4f5MmEWkVxNcubGkBgR2QZTs9fgU3GhWGpuUHYlKZAoiqzAQObOIQSShU2UXkmPIf8mMpE1VqVXFvcNS0aPZN84MGuGEixlWNIQxYWjMT7BaRCsZuLA6gMVQJYSI02hmhhKf2QumUKRozIEBBjYtAlWn2uWsSftV/nxzoPhZFFsZ9syY1ItEI8p3iULkgm1HVk45nvrd+z3Qu+eOLrsxQzYBLYEubqNiXN8wpL+z/vZteUxURaPmYW4aAZ+PPljpOnBvjbh1wv2MIx67luAgJvra7x4+UL87sZeOnkexipYNo/pmJiM/fnFGdpWYlP6rkfbdbi8uESjarKmzXB+fj47lvceF+cXOV26jhGwZ5T7YIIwIcOAFBO2u212/8QgkvefvfgM4zjOYlAO045HKSLI6haK6eh7zNVXURbLJaABI4umHY1BIgHgBrKrbjQDmjZPQ2UPHmq1G6j+G0AGdzWzkRf3RcApM5cSA/f0H+kzpxfn2oVoz8X6qOMCRO2+62dVj3FjZAyohRBmgNJYvBwDRC7XAqr7Tv2vHm/H5o5lvNAXhyBvGQgBRN0zOgUQupjm8vDQxNwMIJSVIEPOqJgBKHOQOQVYnIjTxTC7IDRVM9k2W4Dz4mHHsDgBgSNN12G12aBpG1FdjBHDNOFuGMBmNXgHeKc1T2zxYnAKkt1wtNkkLJHucsMKRHR+0E26X3Uv+h0Lc6kxMdl/ON+SDt55V3PVRGNNlxsBOwYmklDtUdNZOWqWDplLheGJJC4EQKPXlbQabnIllqTJgETF1UgL6pHEmRyCEAWsYM3qASYNIA3wSHCaFiz3YgkzSbOGkoI1l1LeZgCqfp4pRExIagkq1Qz1nes7sD6aTACvzlwQDfrMXFgvkgW+SgFXcJM4STBao5E/latmOWEiygM/xSToC0aJeSp9C2RM0cEX9P+6FFD1nSMt7/MAjUsAeCEIynXvtMuaPSvZYiqs91yGVsnG/c9Cj29pUaxlAESrR9PkOQLMGGPAfhpnk3JSVd/8JEkCCE2AbbVazUCIBcJ2XY+nT55lsNI0DdabDUKKeZv34vZZda1+vs4ZP33fzxYVC0w1l47plVjtnWmasN/tcfHxJfb7Pe7u7rDb7bDf7/H61WtMQcDIOI2ikByCZGxF1edZBFQCFQip2AF2pHl6As4E5OscWQHwMgfruPFOVFNRAQhQtXjLMUUT6GEQkt+tgRBULk6dlyxNVd6j3kt1n6cCgq3NPmOAEJGOsW7V5c5dTTZh61xu69qStck/s0WdQUxK8rsjqXVGRLk4qIQlkKh5t62sibYGEHIsUBkeJdh+ZhTUpifNvvC521sFQvYbj//H//Wr+M73rGEraLbuMWdCypRa/67/8nOrGIT8E7mjVO+jAh3z320/s4zt9wSgX/W4uLrMtBgzYxwG7HfPZ9ZEsSzlp6Hc/1975xoTxdXG8f/swq6AAkXkskUQqNW2IlFaN6SpbQrhElJp9W2tJVFbq9Via6s1hCZK64dCJNGkjaH9oGJiY1sTL6m9BVS01hUVJVZtiRCEtgKmGmAV6S67z/thd4cddtld5DJ7eX7Jwu45Z2aeZ/5nznnmzJmZ4c9i7coKttAC4n/BWUWy84lg7ewhzbONFA2tW9KGW7DbW04sEwYtIWsHbwvebNuy7B/bqMfgfBOzLfizemMLWAiWERObzbZlLJd4YH18vXVuh+0/WUc1AHH0wmTtPC1BjkJcVhpwQrw122h91ot94En2ugsAmSzPk4Ct88fgmQQweMlr8BHqg528pW8WJBpII0JbnRTEdVoacIXl7ge77Tjdtpkswa4LCGS5w4skG4b49uJhlrFZN3wpO3eE4euLiOBuVEUs6LBFsyBYHvLmZknPLk1hcCTE/vkmZrOkkyCFEgNKhcQesr/Lw9q5klIJhULAgFIJY5DljoYHKpX1LoXBSzJd1jcPWx7AZekoQkPNUCiMCFLaLs+YoFIZJPNWlEFKBCmDAEGwPhcGUAiDj+233bkj3n1nsry/aWDACH2SAQNGMwwGJYxGNYwDSvQ/sD6wzWiEyWS5bGy0vmlYfD+PddTNbs+K7bB9sCieaVvPzsXOH/Zn9/aTJS3rkoxKiI28bSuScQG3QaVEV7GVtLuUYbLMwbIPZMVRCLI9/oEk7fVQHGwg67HnwjYx8LIdG7bjGDTYH9DI66xlfwrigxbtR0osdcPyWhHYRu4wqI+9L2T3xnNpmzSIKVwFgybMI/tc4VNBSF9YEH7533TUvpIgSR9mHz0kzkT3dM0k+eZ4rdBJpfK0YvsZDt652cWe7g1X5QbzPNOT7P56yrClH0bOoWYOjQXHYhsuFvRkdWNVxsLYHMHjg9QLS4DrTgRB8lX8ZdcmCHaZgv0yAiDADAiW+8WGlnX227XZQ1oUGuzgLbOxlNbvYZLlBs+4h/PRHd6sKTD8QeW5j77QUgsufrk423C7Ugr2wyemip10739O820TDRmGYXwJZ226L3RgjO8zbvVsaDdt7bc9HcEBvDAI0ev1li/Td8prCMMwDMMwI0av1yMiIsKjsgKNJGSZAMxmM27dugUiQmJiIv766y+Eh4fLbda409vbi+nTpweMv0Dg+Rxo/gKB5zP76/8Ems8j8ZeIoNfrodFoPH65ndeNhCgUCiQkJKC3txcAEB4eHhBC2wg0f4HA8znQ/AUCz2f21/8JNJ899dfTERAbo59VwjAMwzAM8xBwEMIwDMMwjCx4bRCiVqtRVlYGtVottykTQqD5CwSez4HmLxB4PrO//k+g+Tze/nrdxFSGYRiGYQIDrx0JYRiGYRjGv+EghGEYhmEYWeAghGEYhmEYWeAghGEYhmEYWeAghGEYhmEYWfDKIGTXrl2YMWMGJk2aBK1Wi/Pnz8tt0phQXl6OZ555BlOmTEFMTAxefvllNDU1Scq88MIL4tt3bZ+1a9fKZPHo+eSTTxz8mT17tpjf39+P4uJiTJ06FZMnT8aSJUvQ1dUlo8WjY8aMGQ7+CoKA4uJiAP6h7+nTp/HSSy9Bo9FAEAQcOXJEkk9E2Lp1K+Lj4xESEoLs7GzcuHFDUubu3bsoKipCeHg4IiMjsWrVKty7d28CvfAcV/4ajUaUlJQgLS0NYWFh0Gg0WL58OW7duiVZh7N6UVFRMcGeeI47jVeuXOngT15enqSMv2gMwOkxLQgCKisrxTK+pLEnfZEnbXN7ezsKCgoQGhqKmJgYbN68GQMDI3vFrNcFId9++y02btyIsrIyXLp0Cenp6cjNzcXt27flNm3UnDp1CsXFxTh37hxqampgNBqRk5OD+/fvS8qtXr0aHR0d4mf79u0yWTw2PPXUUxJ/zpw5I+Z9+OGH+P7773Hw4EGcOnUKt27dwuLFi2W0dnRcuHBB4mtNTQ0A4NVXXxXL+Lq+9+/fR3p6Onbt2uU0f/v27fj888/x5Zdfor6+HmFhYcjNzUV/f79YpqioCNeuXUNNTQ2OHTuG06dPY82aNRPlwohw5W9fXx8uXbqELVu24NKlSzh06BCampqwaNEih7Lbtm2T6P7ee+9NhPkPhTuNASAvL0/iz4EDByT5/qIxAImfHR0d2LNnDwRBwJIlSyTlfEVjT/oid22zyWRCQUEBDAYDzp49i3379qG6uhpbt24dmTHkZSxYsICKi4vF3yaTiTQaDZWXl8to1fhw+/ZtAkCnTp0S055//nnasGGDfEaNMWVlZZSenu40r7u7m4KDg+ngwYNi2h9//EEASKfTTZCF48uGDRsoNTWVzGYzEfmfvgDo8OHD4m+z2UxxcXFUWVkppnV3d5NaraYDBw4QEdH169cJAF24cEEs89NPP5EgCPTPP/9MmO0Pw1B/nXH+/HkCQG1tbWJaUlIS7dy5c3yNGyec+bxixQoqLCwcdhl/17iwsJBefPFFSZovazy0L/Kkbf7xxx9JoVBQZ2enWKaqqorCw8Ppv//+83jbXjUSYjAY0NDQgOzsbDFNoVAgOzsbOp1ORsvGh56eHgBAVFSUJP3rr79GdHQ05syZg9LSUvT19clh3phx48YNaDQapKSkoKioCO3t7QCAhoYGGI1Gid6zZ89GYmKiX+htMBiwf/9+vPXWWxAEQUz3N33taW1tRWdnp0TTiIgIaLVaUVOdTofIyEg8/fTTYpns7GwoFArU19dPuM1jTU9PDwRBQGRkpCS9oqICU6dOxbx581BZWTniYWtvo66uDjExMZg1axbWrVuHO3fuiHn+rHFXVxd++OEHrFq1yiHPVzUe2hd50jbrdDqkpaUhNjZWLJObm4ve3l5cu3bN42171Vt0//33X5hMJolTABAbG4s///xTJqvGB7PZjA8++ADPPvss5syZI6a/8cYbSEpKgkajwZUrV1BSUoKmpiYcOnRIRmsfHq1Wi+rqasyaNQsdHR349NNP8dxzz+Hq1avo7OyESqVyaKxjY2PR2dkpj8FjyJEjR9Dd3Y2VK1eKaf6m71Bsujk7hm15nZ2diImJkeQHBQUhKirK53Xv7+9HSUkJli1bJnnj6Pvvv4/58+cjKioKZ8+eRWlpKTo6OrBjxw4ZrX148vLysHjxYiQnJ6OlpQUff/wx8vPzodPpoFQq/Vrjffv2YcqUKQ6XjX1VY2d9kSdtc2dnp9Pj3JbnKV4VhAQSxcXFuHr1qmR+BADJNdO0tDTEx8cjKysLLS0tSE1NnWgzR01+fr74fe7cudBqtUhKSsJ3332HkJAQGS0bf3bv3o38/HxoNBoxzd/0ZQYxGo147bXXQESoqqqS5G3cuFH8PnfuXKhUKrzzzjsoLy/3yXeQvP766+L3tLQ0zJ07F6mpqairq0NWVpaMlo0/e/bsQVFRESZNmiRJ91WNh+uLJgqvuhwTHR0NpVLpMAO3q6sLcXFxMlk19qxfvx7Hjh3DyZMnkZCQ4LKsVqsFADQ3N0+EaeNOZGQkHn/8cTQ3NyMuLg4GgwHd3d2SMv6gd1tbG2pra/H222+7LOdv+tp0c3UMx8XFOUw0HxgYwN27d31Wd1sA0tbWhpqaGskoiDO0Wi0GBgZw8+bNiTFwnElJSUF0dLRYj/1RYwD49ddf0dTU5Pa4BnxD4+H6Ik/a5ri4OKfHuS3PU7wqCFGpVMjIyMDx48fFNLPZjOPHjyMzM1NGy8YGIsL69etx+PBhnDhxAsnJyW6XaWxsBADEx8ePs3UTw71799DS0oL4+HhkZGQgODhYondTUxPa29t9Xu+9e/ciJiYGBQUFLsv5m77JycmIi4uTaNrb24v6+npR08zMTHR3d6OhoUEsc+LECZjNZjEo8yVsAciNGzdQW1uLqVOnul2msbERCoXC4ZKFr/L333/jzp07Yj32N41t7N69GxkZGUhPT3db1ps1dtcXedI2Z2Zm4vfff5cEm7YA/MknnxyRMV7FN998Q2q1mqqrq+n69eu0Zs0aioyMlMzA9VXWrVtHERERVFdXRx0dHeKnr6+PiIiam5tp27ZtdPHiRWptbaWjR49SSkoKLVy4UGbLH55NmzZRXV0dtba20m+//UbZ2dkUHR1Nt2/fJiKitWvXUmJiIp04cYIuXrxImZmZlJmZKbPVo8NkMlFiYiKVlJRI0v1FX71eT5cvX6bLly8TANqxYwddvnxZvBukoqKCIiMj6ejRo3TlyhUqLCyk5ORkevDggbiOvLw8mjdvHtXX19OZM2do5syZtGzZMrlccokrfw0GAy1atIgSEhKosbFRclzb7hA4e/Ys7dy5kxobG6mlpYX2799P06ZNo+XLl8vs2fC48lmv19NHH31EOp2OWltbqba2lubPn08zZ86k/v5+cR3+orGNnp4eCg0NpaqqKoflfU1jd30Rkfu2eWBggObMmUM5OTnU2NhIP//8M02bNo1KS0tHZIvXBSFERF988QUlJiaSSqWiBQsW0Llz5+Q2aUwA4PSzd+9eIiJqb2+nhQsXUlRUFKnVanrsscdo8+bN1NPTI6/ho2Dp0qUUHx9PKpWKHn30UVq6dCk1NzeL+Q8ePKB3332XHnnkEQoNDaVXXnmFOjo6ZLR49Pzyyy8EgJqamiTp/qLvyZMnndbjFStWEJHlNt0tW7ZQbGwsqdVqysrKctgXd+7coWXLltHkyZMpPDyc3nzzTdLr9TJ44x5X/ra2tg57XJ88eZKIiBoaGkir1VJERARNmjSJnnjiCfrss88kHba34crnvr4+ysnJoWnTplFwcDAlJSXR6tWrHU4U/UVjG1999RWFhIRQd3e3w/K+prG7vojIs7b55s2blJ+fTyEhIRQdHU2bNm0io9E4IlsEq0EMwzAMwzATilfNCWEYhmEYJnDgIIRhGIZhGFngIIRhGIZhGFngIIRhGIZhGFngIIRhGIZhGFngIIRhGIZhGFngIIRhGIZhGFngIIRhGIZhGFngIIRhGIZhGFngIIRhGIZhGFngIIRhGIZhGFn4PzzPSmP4nEaFAAAAAElFTkSuQmCC", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Apply ROI filtering and OCR\n", + "for idx, box in enumerate(boxes):\n", + " print(box)\n", + " roi = box*[height, width, height, width]\n", + " print(roi)\n", + " region = image[int(roi[0]):int(roi[2]),int(roi[1]):int(roi[3])]\n", + " reader = easyocr.Reader(['en'])\n", + " ocr_result = reader.readtext(region)\n", + " print(ocr_result)\n", + " plt.imshow(cv2.cvtColor(region, cv2.COLOR_BGR2RGB))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# OCR Filtering" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": {}, + "outputs": [], + "source": [ + "region_threshold = 0.05" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": {}, + "outputs": [], + "source": [ + "def filter_text(region, ocr_result, region_threshold):\n", + " rectangle_size = region.shape[0]*region.shape[1]\n", + " \n", + " plate = [] \n", + " for result in ocr_result:\n", + " length = np.sum(np.subtract(result[0][1], result[0][0]))\n", + " height = np.sum(np.subtract(result[0][2], result[0][1]))\n", + " \n", + " if length*height / rectangle_size > region_threshold:\n", + " plate.append(result[1])\n", + " return plate" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['Go4o20']" + ] + }, + "execution_count": 65, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "filter_text(region, ocr_result, region_threshold)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Bring it Together" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": {}, + "outputs": [], + "source": [ + "region_threshold = 0.6" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": {}, + "outputs": [], + "source": [ + "def ocr_it(image, detections, detection_threshold, region_threshold):\n", + " \n", + " # Scores, boxes and classes above threhold\n", + " scores = list(filter(lambda x: x> detection_threshold, detections['detection_scores']))\n", + " boxes = detections['detection_boxes'][:len(scores)]\n", + " classes = detections['detection_classes'][:len(scores)]\n", + " \n", + " # Full image dimensions\n", + " width = image.shape[1]\n", + " height = image.shape[0]\n", + " \n", + " # Apply ROI filtering and OCR\n", + " for idx, box in enumerate(boxes):\n", + " roi = box*[height, width, height, width]\n", + " region = image[int(roi[0]):int(roi[2]),int(roi[1]):int(roi[3])]\n", + " reader = easyocr.Reader(['en'])\n", + " ocr_result = reader.readtext(region)\n", + " \n", + " text = filter_text(region, ocr_result, region_threshold)\n", + " \n", + " plt.imshow(cv2.cvtColor(region, cv2.COLOR_BGR2RGB))\n", + " plt.show()\n", + " print(text)\n", + " return text, region" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[]\n" + ] + } + ], + "source": [ + "text, region = ocr_it(image_np_with_detections, detections, detection_threshold, region_threshold)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Save Results" + ] + }, + { + "cell_type": "code", + "execution_count": 73, + "metadata": {}, + "outputs": [], + "source": [ + "import csv\n", + "import uuid" + ] + }, + { + "cell_type": "code", + "execution_count": 74, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'b12bb9a6-0485-11ee-8f12-b48c9d2e161f.jpg'" + ] + }, + "execution_count": 74, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "'{}.jpg'.format(uuid.uuid1())" + ] + }, + { + "cell_type": "code", + "execution_count": 75, + "metadata": {}, + "outputs": [], + "source": [ + "def save_results(text, region, csv_filename, folder_path):\n", + " img_name = '{}.jpg'.format(uuid.uuid1())\n", + " \n", + " cv2.imwrite(os.path.join(folder_path, img_name), region)\n", + " \n", + " with open(csv_filename, mode='a', newline='') as f:\n", + " csv_writer = csv.writer(f, delimiter=',', quotechar='\"', quoting=csv.QUOTE_MINIMAL)\n", + " csv_writer.writerow([img_name, text])" + ] + }, + { + "cell_type": "code", + "execution_count": 76, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[[127, 255, 0],\n", + " [127, 255, 0],\n", + " [127, 255, 0],\n", + " ...,\n", + " [127, 255, 0],\n", + " [127, 255, 0],\n", + " [127, 255, 0]],\n", + "\n", + " [[127, 255, 0],\n", + " [127, 255, 0],\n", + " [127, 255, 0],\n", + " ...,\n", + " [127, 255, 0],\n", + " [127, 255, 0],\n", + " [127, 255, 0]],\n", + "\n", + " [[127, 255, 0],\n", + " [127, 255, 0],\n", + " [127, 255, 0],\n", + " ...,\n", + " [ 42, 1, 251],\n", + " [127, 255, 0],\n", + " [127, 255, 0]],\n", + "\n", + " ...,\n", + "\n", + " [[127, 255, 0],\n", + " [127, 255, 0],\n", + " [127, 255, 0],\n", + " ...,\n", + " [ 49, 49, 49],\n", + " [127, 255, 0],\n", + " [127, 255, 0]],\n", + "\n", + " [[127, 255, 0],\n", + " [127, 255, 0],\n", + " [127, 255, 0],\n", + " ...,\n", + " [ 44, 44, 44],\n", + " [127, 255, 0],\n", + " [127, 255, 0]],\n", + "\n", + " [[127, 255, 0],\n", + " [127, 255, 0],\n", + " [127, 255, 0],\n", + " ...,\n", + " [127, 255, 0],\n", + " [127, 255, 0],\n", + " [127, 255, 0]]], dtype=uint8)" + ] + }, + "execution_count": 76, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "region" + ] + }, + { + "cell_type": "code", + "execution_count": 77, + "metadata": {}, + "outputs": [], + "source": [ + "save_results(text, region, 'detection_results.csv', 'Detection_Images')" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "IsNAaYAo0WVL" + }, + "source": [ + "# 10. Real Time Detections from your Webcam" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Collecting opencv-python==3.4.11.43\n", + " Downloading opencv-python-3.4.11.43.tar.gz (87.4 MB)\n", + " 0.0/87.4 MB ? eta -:--:--\n", + " 0.1/87.4 MB 4.3 MB/s eta 0:00:21\n", + " 0.5/87.4 MB 7.6 MB/s eta 0:00:12\n", + " 1.1/87.4 MB 10.2 MB/s eta 0:00:09\n", + " 1.9/87.4 MB 12.3 MB/s eta 0:00:07\n", + " 2.1/87.4 MB 12.1 MB/s eta 0:00:08\n", + " 2.1/87.4 MB 12.1 MB/s eta 0:00:08\n", + " 2.1/87.4 MB 12.1 MB/s eta 0:00:08\n", + " - 2.2/87.4 MB 6.3 MB/s eta 0:00:14\n", + " - 2.9/87.4 MB 7.5 MB/s eta 0:00:12\n", + " - 3.8/87.4 MB 8.7 MB/s eta 0:00:10\n", + " -- 4.8/87.4 MB 10.0 MB/s eta 0:00:09\n", + " -- 6.0/87.4 MB 11.3 MB/s eta 0:00:08\n", + " --- 6.9/87.4 MB 11.9 MB/s eta 0:00:07\n", + " --- 8.4/87.4 MB 13.4 MB/s eta 0:00:06\n", + " ---- 9.6/87.4 MB 14.3 MB/s eta 0:00:06\n", + " ---- 10.5/87.4 MB 15.6 MB/s eta 0:00:05\n", + " ---- 10.5/87.4 MB 15.6 MB/s eta 0:00:05\n", + " ---- 10.5/87.4 MB 15.6 MB/s eta 0:00:05\n", + " ---- 10.5/87.4 MB 15.6 MB/s eta 0:00:05\n", + " ---- 10.5/87.4 MB 15.6 MB/s eta 0:00:05\n", + " ---- 10.5/87.4 MB 15.6 MB/s eta 0:00:05\n", + " ---- 10.5/87.4 MB 15.6 MB/s eta 0:00:05\n", + " ----- 11.4/87.4 MB 11.1 MB/s eta 0:00:07\n", + " ----- 12.0/87.4 MB 10.7 MB/s eta 0:00:08\n", + " ----- 13.0/87.4 MB 13.6 MB/s eta 0:00:06\n", + " ------ 14.5/87.4 MB 14.2 MB/s eta 0:00:06\n", + " ------- 16.2/87.4 MB 14.6 MB/s eta 0:00:05\n", + " ------- 16.8/87.4 MB 14.9 MB/s eta 0:00:05\n", + " ------- 16.8/87.4 MB 14.9 MB/s eta 0:00:05\n", + " ------- 16.8/87.4 MB 14.9 MB/s eta 0:00:05\n", + " ------- 16.8/87.4 MB 14.9 MB/s eta 0:00:05\n", + " ------- 17.8/87.4 MB 11.9 MB/s eta 0:00:06\n", + " ------- 17.8/87.4 MB 11.9 MB/s eta 0:00:06\n", + " ------- 17.8/87.4 MB 11.9 MB/s eta 0:00:06\n", + " ------- 17.8/87.4 MB 11.9 MB/s eta 0:00:06\n", + " ------- 17.8/87.4 MB 11.9 MB/s eta 0:00:06\n", + " -------- 17.9/87.4 MB 9.4 MB/s eta 0:00:08\n", + " --------- 19.7/87.4 MB 9.5 MB/s eta 0:00:08\n", + " --------- 21.7/87.4 MB 13.9 MB/s eta 0:00:05\n", + " ---------- 23.9/87.4 MB 15.2 MB/s eta 0:00:05\n", + " ----------- 26.0/87.4 MB 15.2 MB/s eta 0:00:05\n", + " ------------ 28.1/87.4 MB 40.9 MB/s eta 0:00:02\n", + " ------------- 30.1/87.4 MB 43.7 MB/s eta 0:00:02\n", + " -------------- 31.5/87.4 MB 43.7 MB/s eta 0:00:02\n", + " -------------- 31.5/87.4 MB 43.7 MB/s eta 0:00:02\n", + " -------------- 31.5/87.4 MB 43.7 MB/s eta 0:00:02\n", + " -------------- 31.5/87.4 MB 43.7 MB/s eta 0:00:02\n", + " -------------- 31.5/87.4 MB 43.7 MB/s eta 0:00:02\n", + " -------------- 33.5/87.4 MB 24.2 MB/s eta 0:00:03\n", + " -------------- 33.5/87.4 MB 24.2 MB/s eta 0:00:03\n", + " -------------- 33.5/87.4 MB 24.2 MB/s eta 0:00:03\n", + " -------------- 33.5/87.4 MB 24.2 MB/s eta 0:00:03\n", + " -------------- 33.5/87.4 MB 24.2 MB/s eta 0:00:03\n", + " -------------- 33.5/87.4 MB 24.2 MB/s eta 0:00:03\n", + " -------------- 33.5/87.4 MB 24.2 MB/s eta 0:00:03\n", + " -------------- 33.5/87.4 MB 24.2 MB/s eta 0:00:03\n", + " --------------- 34.3/87.4 MB 12.8 MB/s eta 0:00:05\n", + " ---------------- 35.9/87.4 MB 12.6 MB/s eta 0:00:05\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ---------------- 37.7/87.4 MB 12.6 MB/s eta 0:00:04\n", + " ----------------- 38.8/87.4 MB 7.7 MB/s eta 0:00:07\n", + " ----------------- 38.8/87.4 MB 7.7 MB/s eta 0:00:07\n", + " ----------------- 38.8/87.4 MB 7.7 MB/s eta 0:00:07\n", + " ----------------- 38.8/87.4 MB 7.7 MB/s eta 0:00:07\n", + " ----------------- 38.8/87.4 MB 7.7 MB/s eta 0:00:07\n", + " ----------------- 38.8/87.4 MB 7.7 MB/s eta 0:00:07\n", + " ------------------ 39.8/87.4 MB 6.4 MB/s eta 0:00:08\n", + " ------------------ 39.8/87.4 MB 6.4 MB/s eta 0:00:08\n", + " ------------------ 39.8/87.4 MB 6.4 MB/s eta 0:00:08\n", + " ------------------ 39.8/87.4 MB 6.4 MB/s eta 0:00:08\n", + " ------------------ 39.8/87.4 MB 6.4 MB/s eta 0:00:08\n", + " ------------------ 41.1/87.4 MB 5.7 MB/s eta 0:00:09\n", + " ------------------- 43.0/87.4 MB 6.4 MB/s eta 0:00:07\n", + " ------------------- 43.0/87.4 MB 6.4 MB/s eta 0:00:07\n", + " ------------------- 43.0/87.4 MB 6.4 MB/s eta 0:00:07\n", + " ------------------- 43.0/87.4 MB 6.4 MB/s eta 0:00:07\n", + " ------------------- 43.0/87.4 MB 6.4 MB/s eta 0:00:07\n", + " ------------------- 43.0/87.4 MB 6.4 MB/s eta 0:00:07\n", + " ------------------- 43.0/87.4 MB 6.4 MB/s eta 0:00:07\n", + " ------------------- 43.0/87.4 MB 6.4 MB/s eta 0:00:07\n", + " ------------------- 43.7/87.4 MB 5.2 MB/s eta 0:00:09\n", + " -------------------- 45.6/87.4 MB 6.4 MB/s eta 0:00:07\n", + " --------------------- 47.7/87.4 MB 6.3 MB/s eta 0:00:07\n", + " ---------------------- 49.0/87.4 MB 9.4 MB/s eta 0:00:05\n", + " --------------------- 49.3/87.4 MB 12.3 MB/s eta 0:00:04\n", + " --------------------- 49.3/87.4 MB 12.3 MB/s eta 0:00:04\n", + " ---------------------- 50.1/87.4 MB 13.9 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ---------------------- 51.4/87.4 MB 14.2 MB/s eta 0:00:03\n", + " ----------------------- 51.7/87.4 MB 5.1 MB/s eta 0:00:08\n", + " ------------------------ 54.1/87.4 MB 6.2 MB/s eta 0:00:06\n", + " ------------------------- 55.6/87.4 MB 6.2 MB/s eta 0:00:06\n", + " ------------------------- 56.6/87.4 MB 6.2 MB/s eta 0:00:05\n", + " -------------------------- 58.7/87.4 MB 6.2 MB/s eta 0:00:05\n", + " -------------------------- 58.7/87.4 MB 6.2 MB/s eta 0:00:05\n", + " -------------------------- 58.7/87.4 MB 6.2 MB/s eta 0:00:05\n", + " -------------------------- 58.7/87.4 MB 6.2 MB/s eta 0:00:05\n", + " -------------------------- 58.7/87.4 MB 6.2 MB/s eta 0:00:05\n", + " -------------------------- 58.7/87.4 MB 6.2 MB/s eta 0:00:05\n", + " --------------------------- 59.6/87.4 MB 5.7 MB/s eta 0:00:05\n", + " ---------------------------- 61.6/87.4 MB 5.6 MB/s eta 0:00:05\n", + " ---------------------------- 63.4/87.4 MB 19.2 MB/s eta 0:00:02\n", + " ---------------------------- 64.9/87.4 MB 19.3 MB/s eta 0:00:02\n", + " ----------------------------- 65.8/87.4 MB 18.7 MB/s eta 0:00:02\n", + " ----------------------------- 66.7/87.4 MB 17.2 MB/s eta 0:00:02\n", + " ----------------------------- 67.1/87.4 MB 17.7 MB/s eta 0:00:02\n", + " ------------------------------ 68.3/87.4 MB 16.0 MB/s eta 0:00:02\n", + " ------------------------------- 70.1/87.4 MB 28.4 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " ------------------------------- 70.2/87.4 MB 27.3 MB/s eta 0:00:01\n", + " -------------------------------- 70.7/87.4 MB 8.2 MB/s eta 0:00:03\n", + " -------------------------------- 71.3/87.4 MB 8.2 MB/s eta 0:00:02\n", + " -------------------------------- 71.3/87.4 MB 8.2 MB/s eta 0:00:02\n", + " -------------------------------- 71.3/87.4 MB 8.2 MB/s eta 0:00:02\n", + " -------------------------------- 71.3/87.4 MB 8.2 MB/s eta 0:00:02\n", + " --------------------------------- 72.3/87.4 MB 7.1 MB/s eta 0:00:03\n", + " --------------------------------- 72.3/87.4 MB 7.1 MB/s eta 0:00:03\n", + " --------------------------------- 72.3/87.4 MB 7.1 MB/s eta 0:00:03\n", + " --------------------------------- 72.3/87.4 MB 7.1 MB/s eta 0:00:03\n", + " --------------------------------- 72.3/87.4 MB 7.1 MB/s eta 0:00:03\n", + " --------------------------------- 72.3/87.4 MB 7.1 MB/s eta 0:00:03\n", + " --------------------------------- 72.3/87.4 MB 7.1 MB/s eta 0:00:03\n", + " --------------------------------- 72.3/87.4 MB 7.1 MB/s eta 0:00:03\n", + " --------------------------------- 72.3/87.4 MB 7.1 MB/s eta 0:00:03\n", + " --------------------------------- 73.1/87.4 MB 5.6 MB/s eta 0:00:03\n", + " ---------------------------------- 76.2/87.4 MB 5.8 MB/s eta 0:00:02\n", + " ----------------------------------- 77.8/87.4 MB 6.0 MB/s eta 0:00:02\n", + " ----------------------------------- 78.7/87.4 MB 6.0 MB/s eta 0:00:02\n", + " ------------------------------------ 80.9/87.4 MB 11.9 MB/s eta 0:00:01\n", + " ------------------------------------ 81.8/87.4 MB 16.0 MB/s eta 0:00:01\n", + " ------------------------------------ 81.8/87.4 MB 16.0 MB/s eta 0:00:01\n", + " ------------------------------------ 81.8/87.4 MB 16.0 MB/s eta 0:00:01\n", + " ------------------------------------ 81.8/87.4 MB 16.0 MB/s eta 0:00:01\n", + " ------------------------------------ 81.8/87.4 MB 16.0 MB/s eta 0:00:01\n", + " ------------------------------------ 81.8/87.4 MB 16.0 MB/s eta 0:00:01\n", + " ------------------------------------ 81.8/87.4 MB 16.0 MB/s eta 0:00:01\n", + " ------------------------------------ 81.8/87.4 MB 16.0 MB/s eta 0:00:01\n", + " ------------------------------------ 81.8/87.4 MB 16.0 MB/s eta 0:00:01\n", + " ------------------------------------- 83.1/87.4 MB 15.2 MB/s eta 0:00:01\n", + " ------------------------------------- 83.9/87.4 MB 15.2 MB/s eta 0:00:01\n", + " ------------------------------------- 83.9/87.4 MB 15.2 MB/s eta 0:00:01\n", + " ------------------------------------- 83.9/87.4 MB 15.2 MB/s eta 0:00:01\n", + " ------------------------------------- 83.9/87.4 MB 15.2 MB/s eta 0:00:01\n", + " ------------------------------------- 84.5/87.4 MB 11.7 MB/s eta 0:00:01\n", + " ------------------------------------- 84.9/87.4 MB 11.7 MB/s eta 0:00:01\n", + " ------------------------------------- 84.9/87.4 MB 11.7 MB/s eta 0:00:01\n", + " ------------------------------------- 84.9/87.4 MB 11.7 MB/s eta 0:00:01\n", + " ------------------------------------- 84.9/87.4 MB 11.7 MB/s eta 0:00:01\n", + " ------------------------------------- 84.9/87.4 MB 11.7 MB/s eta 0:00:01\n", + " ------------------------------------- 84.9/87.4 MB 11.7 MB/s eta 0:00:01\n", + " ------------------------------------- 84.9/87.4 MB 11.7 MB/s eta 0:00:01\n", + " ------------------------------------- 84.9/87.4 MB 11.7 MB/s eta 0:00:01\n", + " --------------------------------------- 86.1/87.4 MB 8.1 MB/s eta 0:00:01\n", + " --------------------------------------- 87.4/87.4 MB 8.3 MB/s eta 0:00:01\n", + " --------------------------------------- 87.4/87.4 MB 8.3 MB/s eta 0:00:01\n", + " --------------------------------------- 87.4/87.4 MB 8.3 MB/s eta 0:00:01\n", + " --------------------------------------- 87.4/87.4 MB 8.3 MB/s eta 0:00:01\n", + " --------------------------------------- 87.4/87.4 MB 8.3 MB/s eta 0:00:01\n", + " --------------------------------------- 87.4/87.4 MB 8.3 MB/s eta 0:00:01\n", + " ---------------------------------------- 87.4/87.4 MB 6.5 MB/s eta 0:00:00\n", + " Installing build dependencies: started\n", + " Installing build dependencies: still running...\n", + " Installing build dependencies: still running...\n", + " Installing build dependencies: still running...\n", + " Installing build dependencies: finished with status 'done'\n", + " Getting requirements to build wheel: started\n", + " Getting requirements to build wheel: finished with status 'done'\n", + " Preparing metadata (pyproject.toml): started\n", + " Preparing metadata (pyproject.toml): finished with status 'done'\n", + "Requirement already satisfied: numpy>=1.17.3 in c:\\users\\saurav\\tfodcourse\\tfod\\lib\\site-packages (from opencv-python==3.4.11.43) (1.23.5)\n", + "Building wheels for collected packages: opencv-python\n", + " Building wheel for opencv-python (pyproject.toml): started\n", + " Building wheel for opencv-python (pyproject.toml): finished with status 'error'\n", + "Failed to build opencv-python\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + " error: subprocess-exited-with-error\n", + " \n", + " Building wheel for opencv-python (pyproject.toml) did not run successfully.\n", + " exit code: 1\n", + " \n", + " [210 lines of output]\n", + " \n", + " \n", + " --------------------------------------------------------------------------------\n", + " -- Trying 'Ninja (Visual Studio 17 2022 x64 v143)' generator\n", + " --------------------------------\n", + " ---------------------------\n", + " ----------------------\n", + " -----------------\n", + " ------------\n", + " -------\n", + " --\n", + " Not searching for unused variables given on the command line.\n", + " CMake Error at CMakeLists.txt:2 (PROJECT):\n", + " Running\n", + " \n", + " 'C:/Users/SAURAV/TFODCourse/tfod/Scripts/ninja.exe' '--version'\n", + " \n", + " failed with:\n", + " \n", + " Traceback (most recent call last):\n", + " File \"C:\\Users\\SAURAV\\anaconda3\\lib\\runpy.py\", line 197, in _run_module_as_main\n", + " return _run_code(code, main_globals, None,\n", + " File \"C:\\Users\\SAURAV\\anaconda3\\lib\\runpy.py\", line 87, in _run_code\n", + " exec(code, run_globals)\n", + " File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\Scripts\\ninja.exe\\__main__.py\", line 4, in \n", + " \n", + " ModuleNotFoundError: No module named 'ninja'\n", + " \n", + " \n", + " \n", + " -- Configuring incomplete, errors occurred!\n", + " --\n", + " -------\n", + " ------------\n", + " -----------------\n", + " ----------------------\n", + " ---------------------------\n", + " --------------------------------\n", + " -- Trying 'Ninja (Visual Studio 17 2022 x64 v143)' generator - failure\n", + " --------------------------------------------------------------------------------\n", + " \n", + " \n", + " \n", + " --------------------------------------------------------------------------------\n", + " -- Trying 'Visual Studio 17 2022 x64 v143' generator\n", + " --------------------------------\n", + " ---------------------------\n", + " ----------------------\n", + " -----------------\n", + " ------------\n", + " -------\n", + " --\n", + " Not searching for unused variables given on the command line.\n", + " -- Selecting Windows SDK version 10.0.22000.0 to target Windows 10.0.22621.\n", + " -- The C compiler identification is MSVC 19.35.32216.1\n", + " -- Detecting C compiler ABI info\n", + " -- Detecting C compiler ABI info - done\n", + " -- Check for working C compiler: C:/Program Files (x86)/Microsoft Visual Studio/2022/BuildTools/VC/Tools/MSVC/14.35.32215/bin/Hostx64/x64/cl.exe - skipped\n", + " -- Detecting C compile features\n", + " -- Detecting C compile features - done\n", + " -- The CXX compiler identification is MSVC 19.35.32216.1\n", + " CMake Warning (dev) at C:/Users/SAURAV/AppData/Local/Temp/pip-build-env-xnrggfin/overlay/Lib/site-packages/cmake/data/share/cmake-3.26/Modules/CMakeDetermineCXXCompiler.cmake:168 (if):\n", + " Policy CMP0054 is not set: Only interpret if() arguments as variables or\n", + " keywords when unquoted. Run \"cmake --help-policy CMP0054\" for policy\n", + " details. Use the cmake_policy command to set the policy and suppress this\n", + " warning.\n", + " \n", + " Quoted variables like \"MSVC\" will no longer be dereferenced when the policy\n", + " is set to NEW. Since the policy is not set the OLD behavior will be used.\n", + " Call Stack (most recent call first):\n", + " CMakeLists.txt:4 (ENABLE_LANGUAGE)\n", + " This warning is for project developers. Use -Wno-dev to suppress it.\n", + " \n", + " CMake Warning (dev) at C:/Users/SAURAV/AppData/Local/Temp/pip-build-env-xnrggfin/overlay/Lib/site-packages/cmake/data/share/cmake-3.26/Modules/CMakeDetermineCXXCompiler.cmake:189 (elseif):\n", + " Policy CMP0054 is not set: Only interpret if() arguments as variables or\n", + " keywords when unquoted. Run \"cmake --help-policy CMP0054\" for policy\n", + " details. Use the cmake_policy command to set the policy and suppress this\n", + " warning.\n", + " \n", + " Quoted variables like \"MSVC\" will no longer be dereferenced when the policy\n", + " is set to NEW. Since the policy is not set the OLD behavior will be used.\n", + " Call Stack (most recent call first):\n", + " CMakeLists.txt:4 (ENABLE_LANGUAGE)\n", + " This warning is for project developers. Use -Wno-dev to suppress it.\n", + " \n", + " -- Detecting CXX compiler ABI info\n", + " -- Detecting CXX compiler ABI info - done\n", + " -- Check for working CXX compiler: C:/Program Files (x86)/Microsoft Visual Studio/2022/BuildTools/VC/Tools/MSVC/14.35.32215/bin/Hostx64/x64/cl.exe - skipped\n", + " -- Detecting CXX compile features\n", + " -- Detecting CXX compile features - done\n", + " -- Configuring done (10.5s)\n", + " -- Generating done (0.0s)\n", + " -- Build files have been written to: C:/Users/SAURAV/AppData/Local/Temp/pip-install-a7g7tqzu/opencv-python_d80a738241c04d159aae0db0c6fb8ae2/_cmake_test_compile/build\n", + " --\n", + " -------\n", + " ------------\n", + " -----------------\n", + " ----------------------\n", + " ---------------------------\n", + " --------------------------------\n", + " -- Trying 'Visual Studio 17 2022 x64 v143' generator - success\n", + " --------------------------------------------------------------------------------\n", + " \n", + " Configuring Project\n", + " Working directory:\n", + " C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\n", + " Command:\n", + " 'C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-build-env-xnrggfin\\overlay\\Lib\\site-packages\\cmake\\data\\bin/cmake.exe' 'C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\opencv' -G 'Visual Studio 17 2022' --no-warn-unused-cli '-DCMAKE_INSTALL_PREFIX:PATH=C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-install' -DPYTHON_VERSION_STRING:STRING=3.9.13 -DSKBUILD:INTERNAL=TRUE '-DCMAKE_MODULE_PATH:PATH=C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-build-env-xnrggfin\\overlay\\Lib\\site-packages\\skbuild\\resources\\cmake' '-DPYTHON_EXECUTABLE:PATH=C:\\Users\\SAURAV\\TFODCourse\\tfod\\Scripts\\python.exe' '-DPYTHON_INCLUDE_DIR:PATH=C:\\Users\\SAURAV\\anaconda3\\Include' '-DPYTHON_LIBRARY:PATH=C:\\Users\\SAURAV\\anaconda3\\libs\\python39.lib' '-DPython_EXECUTABLE:PATH=C:\\Users\\SAURAV\\TFODCourse\\tfod\\Scripts\\python.exe' '-DPython_ROOT_DIR:PATH=C:\\Users\\SAURAV\\TFODCourse\\tfod' -DPython_FIND_REGISTRY:STRING=NEVER '-DPython_INCLUDE_DIR:PATH=C:\\Users\\SAURAV\\anaconda3\\Include' '-DPython_LIBRARY:PATH=C:\\Users\\SAURAV\\anaconda3\\libs\\python39.lib' '-DPython_NumPy_INCLUDE_DIRS:PATH=C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-build-env-xnrggfin\\overlay\\Lib\\site-packages\\numpy\\core\\include' '-DPython3_EXECUTABLE:PATH=C:\\Users\\SAURAV\\TFODCourse\\tfod\\Scripts\\python.exe' '-DPython3_ROOT_DIR:PATH=C:\\Users\\SAURAV\\TFODCourse\\tfod' -DPython3_FIND_REGISTRY:STRING=NEVER '-DPython3_INCLUDE_DIR:PATH=C:\\Users\\SAURAV\\anaconda3\\Include' '-DPython3_LIBRARY:PATH=C:\\Users\\SAURAV\\anaconda3\\libs\\python39.lib' '-DPython3_NumPy_INCLUDE_DIRS:PATH=C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-build-env-xnrggfin\\overlay\\Lib\\site-packages\\numpy\\core\\include' -T v143 -A x64 '-DPYTHON3_EXECUTABLE=C:\\Users\\SAURAV\\TFODCourse\\tfod\\Scripts\\python.exe' -DPYTHON3_INCLUDE_DIR=C:/Users/SAURAV/anaconda3/Include -DPYTHON3_LIBRARY=C:/Users/SAURAV/anaconda3/libs/python39.lib -DBUILD_opencv_python3=ON -DBUILD_opencv_python2=OFF -DBUILD_opencv_java=OFF -DOPENCV_SKIP_PYTHON_LOADER=ON -DOPENCV_PYTHON3_INSTALL_PATH=python -DINSTALL_CREATE_DISTRIB=ON -DBUILD_opencv_apps=OFF -DBUILD_SHARED_LIBS=OFF -DBUILD_TESTS=OFF -DBUILD_PERF_TESTS=OFF -DBUILD_DOCS=OFF -DCMAKE_BUILD_TYPE:STRING=Release\n", + " \n", + " Not searching for unused variables given on the command line.\n", + " -- Selecting Windows SDK version 10.0.22000.0 to target Windows 10.0.22621.\n", + " -- The CXX compiler identification is MSVC 19.35.32216.1\n", + " -- The C compiler identification is MSVC 19.35.32216.1\n", + " -- Detecting CXX compiler ABI info\n", + " -- Detecting CXX compiler ABI info - failed\n", + " -- Check for working CXX compiler: C:/Program Files (x86)/Microsoft Visual Studio/2022/BuildTools/VC/Tools/MSVC/14.35.32215/bin/Hostx64/x64/cl.exe\n", + " -- Check for working CXX compiler: C:/Program Files (x86)/Microsoft Visual Studio/2022/BuildTools/VC/Tools/MSVC/14.35.32215/bin/Hostx64/x64/cl.exe - broken\n", + " CMake Error at C:/Users/SAURAV/AppData/Local/Temp/pip-build-env-xnrggfin/overlay/Lib/site-packages/cmake/data/share/cmake-3.26/Modules/CMakeTestCXXCompiler.cmake:60 (message):\n", + " The C++ compiler\n", + " \n", + " \"C:/Program Files (x86)/Microsoft Visual Studio/2022/BuildTools/VC/Tools/MSVC/14.35.32215/bin/Hostx64/x64/cl.exe\"\n", + " \n", + " is not able to compile a simple test program.\n", + " \n", + " It fails with the following output:\n", + " \n", + " Change Dir: C:/Users/SAURAV/AppData/Local/Temp/pip-install-a7g7tqzu/opencv-python_d80a738241c04d159aae0db0c6fb8ae2/_skbuild/win-amd64-3.9/cmake-build/CMakeFiles/CMakeScratch/TryCompile-868cq6\n", + " \n", + " Run Build Command(s):C:/Program Files (x86)/Microsoft Visual Studio/2022/BuildTools/MSBuild/Current/Bin/amd64/MSBuild.exe cmTC_2b3fc.vcxproj /p:Configuration=Debug /p:Platform=x64 /p:VisualStudioVersion=17.0 /v:n && MSBuild version 17.5.1+f6fdcf537 for .NET Framework\n", + " Build started 6/28/2023 6:44:28 PM.\n", + " Included response file: C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Current\\Bin\\amd64\\MSBuild.rsp\n", + " \n", + " Project \"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj\" on node 1 (default targets).\n", + " PrepareForBuild:\n", + " Creating directory \"cmTC_2b3fc.dir\\Debug\\\".\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppBuild.targets(527,5): warning MSB8029: The Intermediate directory or Output directory cannot reside under the Temporary directory as it could lead to issues with incremental build. [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " Creating directory \"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\Debug\\\".\n", + " Creating directory \"cmTC_2b3fc.dir\\Debug\\cmTC_2b3fc.tlog\\\".\n", + " InitializeBuildStatus:\n", + " Creating \"cmTC_2b3fc.dir\\Debug\\cmTC_2b3fc.tlog\\unsuccessfulbuild\" because \"AlwaysCreate\" was specified.\n", + " ClCompile:\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\VC\\Tools\\MSVC\\14.35.32215\\bin\\HostX64\\x64\\CL.exe /c /Zi /W3 /WX- /diagnostics:column /Od /Ob0 /D _MBCS /D WIN32 /D _WINDOWS /D \"CMAKE_INTDIR=\\\"Debug\\\"\" /Gm- /EHsc /RTC1 /MDd /GS /fp:precise /Zc:wchar_t /Zc:forScope /Zc:inline /GR /Fo\"cmTC_2b3fc.dir\\Debug\\\\\" /Fd\"cmTC_2b3fc.dir\\Debug\\vc143.pdb\" /external:W3 /Gd /TP /errorReport:queue \"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\testCXXCompiler.cxx\"\n", + " Microsoft (R) C/C++ Optimizing Compiler Version 19.35.32216.1 for x64\n", + " Copyright (C) Microsoft Corporation. All rights reserved.\n", + " testCXXCompiler.cxx\n", + " cl /c /Zi /W3 /WX- /diagnostics:column /Od /Ob0 /D _MBCS /D WIN32 /D _WINDOWS /D \"CMAKE_INTDIR=\\\"Debug\\\"\" /Gm- /EHsc /RTC1 /MDd /GS /fp:precise /Zc:wchar_t /Zc:forScope /Zc:inline /GR /Fo\"cmTC_2b3fc.dir\\Debug\\\\\" /Fd\"cmTC_2b3fc.dir\\Debug\\vc143.pdb\" /external:W3 /Gd /TP /errorReport:queue \"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\testCXXCompiler.cxx\"\n", + " Link:\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\VC\\Tools\\MSVC\\14.35.32215\\bin\\HostX64\\x64\\link.exe /ERRORREPORT:QUEUE /OUT:\"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\Debug\\cmTC_2b3fc.exe\" /INCREMENTAL /ILK:\"cmTC_2b3fc.dir\\Debug\\cmTC_2b3fc.ilk\" /NOLOGO kernel32.lib user32.lib gdi32.lib winspool.lib shell32.lib ole32.lib oleaut32.lib uuid.lib comdlg32.lib advapi32.lib /MANIFEST /MANIFESTUAC:\"level='asInvoker' uiAccess='false'\" /manifest:embed /DEBUG /PDB:\"C:/Users/SAURAV/AppData/Local/Temp/pip-install-a7g7tqzu/opencv-python_d80a738241c04d159aae0db0c6fb8ae2/_skbuild/win-amd64-3.9/cmake-build/CMakeFiles/CMakeScratch/TryCompile-868cq6/Debug/cmTC_2b3fc.pdb\" /SUBSYSTEM:CONSOLE /TLBID:1 /DYNAMICBASE /NXCOMPAT /IMPLIB:\"C:/Users/SAURAV/AppData/Local/Temp/pip-install-a7g7tqzu/opencv-python_d80a738241c04d159aae0db0c6fb8ae2/_skbuild/win-amd64-3.9/cmake-build/CMakeFiles/CMakeScratch/TryCompile-868cq6/Debug/cmTC_2b3fc.lib\" /MACHINE:X64 /machine:x64 cmTC_2b3fc.dir\\Debug\\testCXXCompiler.obj\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: The specified task executable \"link.exe\" could not be run. System.IO.DirectoryNotFoundException: Could not find a part of the path 'C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.dir\\Debug\\cmTC_2b3fc.tlog'. [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at System.IO.__Error.WinIOError(Int32 errorCode, String maybeFullPath) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at System.IO.FileSystemEnumerableIterator`1.CommonInit() [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at System.IO.FileSystemEnumerableIterator`1..ctor(String path, String originalUserPath, String searchPattern, SearchOption searchOption, SearchResultHandler`1 resultHandler, Boolean checkHost) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at System.IO.Directory.GetFiles(String path, String searchPattern) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at Microsoft.Build.Utilities.TrackedDependencies.ExpandWildcards(ITaskItem[] expand) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at Microsoft.Build.CPPTasks.TrackedVCToolTask.DeleteFiles(ITaskItem[] filesToDelete) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at Microsoft.Build.CPPTasks.TrackedVCToolTask.PostExecuteTool(Int32 exitCode) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at Microsoft.Build.CPPTasks.TrackedVCToolTask.ExecuteTool(String pathToTool, String responseFileCommands, String commandLineCommands) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at Microsoft.Build.Utilities.ToolTask.Execute() [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " Done Building Project \"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj\" (default targets) -- FAILED.\n", + " \n", + " Build FAILED.\n", + " \n", + " \"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj\" (default target) (1) ->\n", + " (PrepareForBuild target) ->\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppBuild.targets(527,5): warning MSB8029: The Intermediate directory or Output directory cannot reside under the Temporary directory as it could lead to issues with incremental build. [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " \n", + " \n", + " \"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj\" (default target) (1) ->\n", + " (Link target) ->\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: The specified task executable \"link.exe\" could not be run. System.IO.DirectoryNotFoundException: Could not find a part of the path 'C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.dir\\Debug\\cmTC_2b3fc.tlog'. [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at System.IO.__Error.WinIOError(Int32 errorCode, String maybeFullPath) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at System.IO.FileSystemEnumerableIterator`1.CommonInit() [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at System.IO.FileSystemEnumerableIterator`1..ctor(String path, String originalUserPath, String searchPattern, SearchOption searchOption, SearchResultHandler`1 resultHandler, Boolean checkHost) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at System.IO.Directory.GetFiles(String path, String searchPattern) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at Microsoft.Build.Utilities.TrackedDependencies.ExpandWildcards(ITaskItem[] expand) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at Microsoft.Build.CPPTasks.TrackedVCToolTask.DeleteFiles(ITaskItem[] filesToDelete) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at Microsoft.Build.CPPTasks.TrackedVCToolTask.PostExecuteTool(Int32 exitCode) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at Microsoft.Build.CPPTasks.TrackedVCToolTask.ExecuteTool(String pathToTool, String responseFileCommands, String commandLineCommands) [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " C:\\Program Files (x86)\\Microsoft Visual Studio\\2022\\BuildTools\\MSBuild\\Microsoft\\VC\\v170\\Microsoft.CppCommon.targets(1096,5): error MSB6003: at Microsoft.Build.Utilities.ToolTask.Execute() [C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\\CMakeFiles\\CMakeScratch\\TryCompile-868cq6\\cmTC_2b3fc.vcxproj]\n", + " \n", + " 1 Warning(s)\n", + " 1 Error(s)\n", + " \n", + " Time Elapsed 00:00:01.43\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " CMake will not be able to correctly generate this project.\n", + " Call Stack (most recent call first):\n", + " CMakeLists.txt:106 (enable_language)\n", + " \n", + " \n", + " -- Configuring incomplete, errors occurred!\n", + " Traceback (most recent call last):\n", + " File \"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-build-env-xnrggfin\\overlay\\Lib\\site-packages\\skbuild\\setuptools_wrap.py\", line 666, in setup\n", + " env = cmkr.configure(\n", + " File \"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-build-env-xnrggfin\\overlay\\Lib\\site-packages\\skbuild\\cmaker.py\", line 357, in configure\n", + " raise SKBuildError(msg)\n", + " \n", + " An error occurred while configuring with CMake.\n", + " Command:\n", + " 'C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-build-env-xnrggfin\\overlay\\Lib\\site-packages\\cmake\\data\\bin/cmake.exe' 'C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\opencv' -G 'Visual Studio 17 2022' --no-warn-unused-cli '-DCMAKE_INSTALL_PREFIX:PATH=C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-install' -DPYTHON_VERSION_STRING:STRING=3.9.13 -DSKBUILD:INTERNAL=TRUE '-DCMAKE_MODULE_PATH:PATH=C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-build-env-xnrggfin\\overlay\\Lib\\site-packages\\skbuild\\resources\\cmake' '-DPYTHON_EXECUTABLE:PATH=C:\\Users\\SAURAV\\TFODCourse\\tfod\\Scripts\\python.exe' '-DPYTHON_INCLUDE_DIR:PATH=C:\\Users\\SAURAV\\anaconda3\\Include' '-DPYTHON_LIBRARY:PATH=C:\\Users\\SAURAV\\anaconda3\\libs\\python39.lib' '-DPython_EXECUTABLE:PATH=C:\\Users\\SAURAV\\TFODCourse\\tfod\\Scripts\\python.exe' '-DPython_ROOT_DIR:PATH=C:\\Users\\SAURAV\\TFODCourse\\tfod' -DPython_FIND_REGISTRY:STRING=NEVER '-DPython_INCLUDE_DIR:PATH=C:\\Users\\SAURAV\\anaconda3\\Include' '-DPython_LIBRARY:PATH=C:\\Users\\SAURAV\\anaconda3\\libs\\python39.lib' '-DPython_NumPy_INCLUDE_DIRS:PATH=C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-build-env-xnrggfin\\overlay\\Lib\\site-packages\\numpy\\core\\include' '-DPython3_EXECUTABLE:PATH=C:\\Users\\SAURAV\\TFODCourse\\tfod\\Scripts\\python.exe' '-DPython3_ROOT_DIR:PATH=C:\\Users\\SAURAV\\TFODCourse\\tfod' -DPython3_FIND_REGISTRY:STRING=NEVER '-DPython3_INCLUDE_DIR:PATH=C:\\Users\\SAURAV\\anaconda3\\Include' '-DPython3_LIBRARY:PATH=C:\\Users\\SAURAV\\anaconda3\\libs\\python39.lib' '-DPython3_NumPy_INCLUDE_DIRS:PATH=C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-build-env-xnrggfin\\overlay\\Lib\\site-packages\\numpy\\core\\include' -T v143 -A x64 '-DPYTHON3_EXECUTABLE=C:\\Users\\SAURAV\\TFODCourse\\tfod\\Scripts\\python.exe' -DPYTHON3_INCLUDE_DIR=C:/Users/SAURAV/anaconda3/Include -DPYTHON3_LIBRARY=C:/Users/SAURAV/anaconda3/libs/python39.lib -DBUILD_opencv_python3=ON -DBUILD_opencv_python2=OFF -DBUILD_opencv_java=OFF -DOPENCV_SKIP_PYTHON_LOADER=ON -DOPENCV_PYTHON3_INSTALL_PATH=python -DINSTALL_CREATE_DISTRIB=ON -DBUILD_opencv_apps=OFF -DBUILD_SHARED_LIBS=OFF -DBUILD_TESTS=OFF -DBUILD_PERF_TESTS=OFF -DBUILD_DOCS=OFF -DCMAKE_BUILD_TYPE:STRING=Release\n", + " Source directory:\n", + " C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\opencv\n", + " Working directory:\n", + " C:\\Users\\SAURAV\\AppData\\Local\\Temp\\pip-install-a7g7tqzu\\opencv-python_d80a738241c04d159aae0db0c6fb8ae2\\_skbuild\\win-amd64-3.9\\cmake-build\n", + " Please see CMake's output for more information.\n", + " \n", + " [end of output]\n", + " \n", + " note: This error originates from a subprocess, and is likely not a problem with pip.\n", + " ERROR: Failed building wheel for opencv-python\n", + "ERROR: Could not build wheels for opencv-python, which is required to install pyproject.toml-based projects\n" + ] + } + ], + "source": [ + "!pip install opencv-python==3.4.11.43" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": { + "id": "o_grs6OGpfDJ" + }, + "outputs": [ + { + "ename": "ValueError", + "evalue": "in user code:\n\n File \"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\ipykernel_25004\\1007919961.py\", line 11, in detect_fn *\n image, shapes = detection_model.preprocess(image)\n File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\meta_architectures\\ssd_meta_arch.py\", line 485, in preprocess *\n normalized_inputs, self._image_resizer_fn)\n File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\utils\\shape_utils.py\", line 492, in resize_images_and_return_shapes *\n outputs = static_or_dynamic_map_fn(\n File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\utils\\shape_utils.py\", line 246, in static_or_dynamic_map_fn *\n outputs = [fn(arg) for arg in tf.unstack(elems)]\n File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\core\\preprocessor.py\", line 3330, in resize_image *\n new_image = tf.image.resize_images(\n\n ValueError: 'images' must have either 3 or 4 dimensions.\n", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[1;32mIn[49], line 10\u001b[0m\n\u001b[0;32m 7\u001b[0m image_np \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39marray(frame)\n\u001b[0;32m 9\u001b[0m input_tensor \u001b[38;5;241m=\u001b[39m tf\u001b[38;5;241m.\u001b[39mconvert_to_tensor(np\u001b[38;5;241m.\u001b[39mexpand_dims(image_np, \u001b[38;5;241m0\u001b[39m), dtype\u001b[38;5;241m=\u001b[39mtf\u001b[38;5;241m.\u001b[39mfloat32)\n\u001b[1;32m---> 10\u001b[0m detections \u001b[38;5;241m=\u001b[39m \u001b[43mdetect_fn\u001b[49m\u001b[43m(\u001b[49m\u001b[43minput_tensor\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 12\u001b[0m num_detections \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mint\u001b[39m(detections\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mnum_detections\u001b[39m\u001b[38;5;124m'\u001b[39m))\n\u001b[0;32m 13\u001b[0m detections \u001b[38;5;241m=\u001b[39m {key: value[\u001b[38;5;241m0\u001b[39m, :num_detections]\u001b[38;5;241m.\u001b[39mnumpy()\n\u001b[0;32m 14\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key, value \u001b[38;5;129;01min\u001b[39;00m detections\u001b[38;5;241m.\u001b[39mitems()}\n", + "File \u001b[1;32m~\\TFODCourse\\tfod\\lib\\site-packages\\tensorflow\\python\\util\\traceback_utils.py:153\u001b[0m, in \u001b[0;36mfilter_traceback..error_handler\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m 151\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m 152\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n\u001b[1;32m--> 153\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\u001b[38;5;241m.\u001b[39mwith_traceback(filtered_tb) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28mNone\u001b[39m\n\u001b[0;32m 154\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[0;32m 155\u001b[0m \u001b[38;5;28;01mdel\u001b[39;00m filtered_tb\n", + "File \u001b[1;32m~\\AppData\\Local\\Temp\\__autograph_generated_filego0z5dpn.py:10\u001b[0m, in \u001b[0;36mouter_factory..inner_factory..tf__detect_fn\u001b[1;34m(image)\u001b[0m\n\u001b[0;32m 8\u001b[0m do_return \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[0;32m 9\u001b[0m retval_ \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mUndefinedReturnValue()\n\u001b[1;32m---> 10\u001b[0m (image, shapes) \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(detection_model)\u001b[38;5;241m.\u001b[39mpreprocess, (ag__\u001b[38;5;241m.\u001b[39mld(image),), \u001b[38;5;28;01mNone\u001b[39;00m, fscope)\n\u001b[0;32m 11\u001b[0m prediction_dict \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(detection_model)\u001b[38;5;241m.\u001b[39mpredict, (ag__\u001b[38;5;241m.\u001b[39mld(image), ag__\u001b[38;5;241m.\u001b[39mld(shapes)), \u001b[38;5;28;01mNone\u001b[39;00m, fscope)\n\u001b[0;32m 12\u001b[0m detections \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(detection_model)\u001b[38;5;241m.\u001b[39mpostprocess, (ag__\u001b[38;5;241m.\u001b[39mld(prediction_dict), ag__\u001b[38;5;241m.\u001b[39mld(shapes)), \u001b[38;5;28;01mNone\u001b[39;00m, fscope)\n", + "File \u001b[1;32m~\\AppData\\Local\\Temp\\__autograph_generated_file0s6xumju.py:35\u001b[0m, in \u001b[0;36mouter_factory..inner_factory..tf__preprocess\u001b[1;34m(self, inputs)\u001b[0m\n\u001b[0;32m 33\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m 34\u001b[0m do_return \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m---> 35\u001b[0m retval_ \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(shape_utils)\u001b[38;5;241m.\u001b[39mresize_images_and_return_shapes, (ag__\u001b[38;5;241m.\u001b[39mld(normalized_inputs), ag__\u001b[38;5;241m.\u001b[39mld(\u001b[38;5;28mself\u001b[39m)\u001b[38;5;241m.\u001b[39m_image_resizer_fn), \u001b[38;5;28;01mNone\u001b[39;00m, fscope)\n\u001b[0;32m 36\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m:\n\u001b[0;32m 37\u001b[0m do_return \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n", + "File \u001b[1;32m~\\AppData\\Local\\Temp\\__autograph_generated_file92il5var.py:37\u001b[0m, in \u001b[0;36mouter_factory..inner_factory..tf__resize_images_and_return_shapes\u001b[1;34m(inputs, image_resizer_fn)\u001b[0m\n\u001b[0;32m 35\u001b[0m \u001b[38;5;28;01mpass\u001b[39;00m\n\u001b[0;32m 36\u001b[0m ag__\u001b[38;5;241m.\u001b[39mif_stmt(ag__\u001b[38;5;241m.\u001b[39mld(inputs)\u001b[38;5;241m.\u001b[39mdtype \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m ag__\u001b[38;5;241m.\u001b[39mld(tf)\u001b[38;5;241m.\u001b[39mfloat32, if_body, else_body, get_state, set_state, (), \u001b[38;5;241m0\u001b[39m)\n\u001b[1;32m---> 37\u001b[0m outputs \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(static_or_dynamic_map_fn), (ag__\u001b[38;5;241m.\u001b[39mld(image_resizer_fn),), \u001b[38;5;28mdict\u001b[39m(elems\u001b[38;5;241m=\u001b[39mag__\u001b[38;5;241m.\u001b[39mld(inputs), dtype\u001b[38;5;241m=\u001b[39m[ag__\u001b[38;5;241m.\u001b[39mld(tf)\u001b[38;5;241m.\u001b[39mfloat32, ag__\u001b[38;5;241m.\u001b[39mld(tf)\u001b[38;5;241m.\u001b[39mint32]), fscope)\n\u001b[0;32m 38\u001b[0m resized_inputs \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mld(outputs)[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m 39\u001b[0m true_image_shapes \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mld(outputs)[\u001b[38;5;241m1\u001b[39m]\n", + "File \u001b[1;32m~\\AppData\\Local\\Temp\\__autograph_generated_filelflpjw_0.py:186\u001b[0m, in \u001b[0;36mouter_factory..inner_factory..tf__static_or_dynamic_map_fn\u001b[1;34m(fn, elems, dtype, parallel_iterations, back_prop)\u001b[0m\n\u001b[0;32m 184\u001b[0m elems_shape \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mUndefined(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124melems_shape\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 185\u001b[0m elem_shape \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mUndefined(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124melem_shape\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m--> 186\u001b[0m ag__\u001b[38;5;241m.\u001b[39mif_stmt(ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(\u001b[38;5;28misinstance\u001b[39m), (ag__\u001b[38;5;241m.\u001b[39mld(elems), ag__\u001b[38;5;241m.\u001b[39mld(\u001b[38;5;28mlist\u001b[39m)), \u001b[38;5;28;01mNone\u001b[39;00m, fscope), if_body_5, else_body_5, get_state_7, set_state_7, (\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdo_return\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124moutputs\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mretval_\u001b[39m\u001b[38;5;124m'\u001b[39m), \u001b[38;5;241m3\u001b[39m)\n\u001b[0;32m 188\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mget_state_12\u001b[39m():\n\u001b[0;32m 189\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m (do_return, retval_)\n", + "File \u001b[1;32m~\\AppData\\Local\\Temp\\__autograph_generated_filelflpjw_0.py:179\u001b[0m, in \u001b[0;36mouter_factory..inner_factory..tf__static_or_dynamic_map_fn..else_body_5\u001b[1;34m()\u001b[0m\n\u001b[0;32m 177\u001b[0m outputs \u001b[38;5;241m=\u001b[39m [ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(fn), (ag__\u001b[38;5;241m.\u001b[39mld(arg),), \u001b[38;5;28;01mNone\u001b[39;00m, fscope) \u001b[38;5;28;01mfor\u001b[39;00m arg \u001b[38;5;129;01min\u001b[39;00m ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(tf)\u001b[38;5;241m.\u001b[39munstack, (ag__\u001b[38;5;241m.\u001b[39mld(elems),), \u001b[38;5;28;01mNone\u001b[39;00m, fscope)]\n\u001b[0;32m 178\u001b[0m outputs \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mUndefined(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124moutputs\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m--> 179\u001b[0m \u001b[43mag__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mif_stmt\u001b[49m\u001b[43m(\u001b[49m\u001b[43mag__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mor_\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43;01mlambda\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mag__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnot_\u001b[49m\u001b[43m(\u001b[49m\u001b[43mag__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mld\u001b[49m\u001b[43m(\u001b[49m\u001b[43melems_shape\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mlambda\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mag__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnot_\u001b[49m\u001b[43m(\u001b[49m\u001b[43mag__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mld\u001b[49m\u001b[43m(\u001b[49m\u001b[43melems_shape\u001b[49m\u001b[43m)\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mif_body_4\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43melse_body_4\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mget_state_6\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mset_state_6\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mdo_return\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43moutputs\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mretval_\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m)\u001b[49m\n", + "File \u001b[1;32m~\\AppData\\Local\\Temp\\__autograph_generated_filelflpjw_0.py:177\u001b[0m, in \u001b[0;36mouter_factory..inner_factory..tf__static_or_dynamic_map_fn..else_body_5..else_body_4\u001b[1;34m()\u001b[0m\n\u001b[0;32m 175\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21melse_body_4\u001b[39m():\n\u001b[0;32m 176\u001b[0m \u001b[38;5;28;01mnonlocal\u001b[39;00m outputs, do_return, retval_\n\u001b[1;32m--> 177\u001b[0m outputs \u001b[38;5;241m=\u001b[39m [ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(fn), (ag__\u001b[38;5;241m.\u001b[39mld(arg),), \u001b[38;5;28;01mNone\u001b[39;00m, fscope) \u001b[38;5;28;01mfor\u001b[39;00m arg \u001b[38;5;129;01min\u001b[39;00m ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(tf)\u001b[38;5;241m.\u001b[39munstack, (ag__\u001b[38;5;241m.\u001b[39mld(elems),), \u001b[38;5;28;01mNone\u001b[39;00m, fscope)]\n", + "File \u001b[1;32m~\\AppData\\Local\\Temp\\__autograph_generated_filelflpjw_0.py:177\u001b[0m, in \u001b[0;36m\u001b[1;34m(.0)\u001b[0m\n\u001b[0;32m 175\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21melse_body_4\u001b[39m():\n\u001b[0;32m 176\u001b[0m \u001b[38;5;28;01mnonlocal\u001b[39;00m outputs, do_return, retval_\n\u001b[1;32m--> 177\u001b[0m outputs \u001b[38;5;241m=\u001b[39m [\u001b[43mag__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconverted_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43mag__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mld\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfn\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43mag__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mld\u001b[49m\u001b[43m(\u001b[49m\u001b[43marg\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfscope\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m arg \u001b[38;5;129;01min\u001b[39;00m ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(tf)\u001b[38;5;241m.\u001b[39munstack, (ag__\u001b[38;5;241m.\u001b[39mld(elems),), \u001b[38;5;28;01mNone\u001b[39;00m, fscope)]\n", + "File \u001b[1;32m~\\AppData\\Local\\Temp\\__autograph_generated_fileun_4sku9.py:34\u001b[0m, in \u001b[0;36mouter_factory..inner_factory..tf__resize_image\u001b[1;34m(image, masks, new_height, new_width, method, align_corners)\u001b[0m\n\u001b[0;32m 32\u001b[0m retval_ \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mUndefinedReturnValue()\n\u001b[0;32m 33\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m ag__\u001b[38;5;241m.\u001b[39mld(tf)\u001b[38;5;241m.\u001b[39mname_scope(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mResizeImage\u001b[39m\u001b[38;5;124m'\u001b[39m, values\u001b[38;5;241m=\u001b[39m[ag__\u001b[38;5;241m.\u001b[39mld(image), ag__\u001b[38;5;241m.\u001b[39mld(new_height), ag__\u001b[38;5;241m.\u001b[39mld(new_width), ag__\u001b[38;5;241m.\u001b[39mld(method), ag__\u001b[38;5;241m.\u001b[39mld(align_corners)]):\n\u001b[1;32m---> 34\u001b[0m new_image \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(tf)\u001b[38;5;241m.\u001b[39mimage\u001b[38;5;241m.\u001b[39mresize_images, (ag__\u001b[38;5;241m.\u001b[39mld(image), ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(tf)\u001b[38;5;241m.\u001b[39mstack, ([ag__\u001b[38;5;241m.\u001b[39mld(new_height), ag__\u001b[38;5;241m.\u001b[39mld(new_width)],), \u001b[38;5;28;01mNone\u001b[39;00m, fscope)), \u001b[38;5;28mdict\u001b[39m(method\u001b[38;5;241m=\u001b[39mag__\u001b[38;5;241m.\u001b[39mld(method), align_corners\u001b[38;5;241m=\u001b[39mag__\u001b[38;5;241m.\u001b[39mld(align_corners)), fscope)\n\u001b[0;32m 35\u001b[0m image_shape \u001b[38;5;241m=\u001b[39m ag__\u001b[38;5;241m.\u001b[39mconverted_call(ag__\u001b[38;5;241m.\u001b[39mld(shape_utils)\u001b[38;5;241m.\u001b[39mcombined_static_and_dynamic_shape, (ag__\u001b[38;5;241m.\u001b[39mld(image),), \u001b[38;5;28;01mNone\u001b[39;00m, fscope)\n\u001b[0;32m 36\u001b[0m result \u001b[38;5;241m=\u001b[39m [ag__\u001b[38;5;241m.\u001b[39mld(new_image)]\n", + "\u001b[1;31mValueError\u001b[0m: in user code:\n\n File \"C:\\Users\\SAURAV\\AppData\\Local\\Temp\\ipykernel_25004\\1007919961.py\", line 11, in detect_fn *\n image, shapes = detection_model.preprocess(image)\n File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\meta_architectures\\ssd_meta_arch.py\", line 485, in preprocess *\n normalized_inputs, self._image_resizer_fn)\n File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\utils\\shape_utils.py\", line 492, in resize_images_and_return_shapes *\n outputs = static_or_dynamic_map_fn(\n File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\utils\\shape_utils.py\", line 246, in static_or_dynamic_map_fn *\n outputs = [fn(arg) for arg in tf.unstack(elems)]\n File \"C:\\Users\\SAURAV\\TFODCourse\\tfod\\lib\\site-packages\\object_detection-0.1-py3.9.egg\\object_detection\\core\\preprocessor.py\", line 3330, in resize_image *\n new_image = tf.image.resize_images(\n\n ValueError: 'images' must have either 3 or 4 dimensions.\n" + ] + } + ], + "source": [ + "cap = cv2.VideoCapture(0)\n", + "width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))\n", + "height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))\n", + "\n", + "while cap.isOpened(): \n", + " ret, frame = cap.read()\n", + " image_np = np.array(frame)\n", + " \n", + " input_tensor = tf.convert_to_tensor(np.expand_dims(image_np, 0), dtype=tf.float32)\n", + " detections = detect_fn(input_tensor)\n", + " \n", + " num_detections = int(detections.pop('num_detections'))\n", + " detections = {key: value[0, :num_detections].numpy()\n", + " for key, value in detections.items()}\n", + " detections['num_detections'] = num_detections\n", + "\n", + " # detection_classes should be ints.\n", + " detections['detection_classes'] = detections['detection_classes'].astype(np.int64)\n", + "\n", + " label_id_offset = 1\n", + " image_np_with_detections = image_np.copy()\n", + "\n", + " viz_utils.visualize_boxes_and_labels_on_image_array(\n", + " image_np_with_detections,\n", + " detections['detection_boxes'],\n", + " detections['detection_classes']+label_id_offset,\n", + " detections['detection_scores'],\n", + " category_index,\n", + " use_normalized_coordinates=True,\n", + " max_boxes_to_draw=5,\n", + " min_score_thresh=.8,\n", + " agnostic_mode=False)\n", + " \n", + " try: \n", + " text, region = ocr_it(image_np_with_detections, detections, detection_threshold, region_threshold)\n", + " save_results(text, region, 'realtimeresults.csv', 'Detection_Images')\n", + " except:\n", + " pass\n", + "\n", + " cv2.imshow('object detection', cv2.resize(image_np_with_detections, (800, 600)))\n", + " \n", + " if cv2.waitKey(10) & 0xFF == ord('q'):\n", + " cap.release()\n", + " cv2.destroyAllWindows()\n", + " break" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "rzlM4jt0pfDJ" + }, + "source": [ + "# 10. Freezing the Graph" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "n4olHB2npfDJ" + }, + "outputs": [], + "source": [ + "FREEZE_SCRIPT = os.path.join(paths['APIMODEL_PATH'], 'research', 'object_detection', 'exporter_main_v2.py ')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "0AjO93QDpfDJ" + }, + "outputs": [], + "source": [ + "command = \"python {} --input_type=image_tensor --pipeline_config_path={} --trained_checkpoint_dir={} --output_directory={}\".format(FREEZE_SCRIPT ,files['PIPELINE_CONFIG'], paths['CHECKPOINT_PATH'], paths['OUTPUT_PATH'])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "F6Lsp3tCpfDJ", + "outputId": "c3828529-bf06-4df5-d7f3-145890ec3edd" + }, + "outputs": [], + "source": [ + "print(command)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "1Sw1ULgHpfDJ", + "outputId": "6fd441e1-9fc9-4889-d072-3395c21e40b6" + }, + "outputs": [], + "source": [ + "!{command}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "wTPmdqaXpfDK" + }, + "source": [ + "# 11. Conversion to TFJS" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "gZ6UzY_fpfDK", + "outputId": "0c84722e-1c2b-4002-d857-80827ade828a", + "scrolled": true + }, + "outputs": [], + "source": [ + "!pip install tensorflowjs" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "0oxbVynHpfDK" + }, + "outputs": [], + "source": [ + "command = \"tensorflowjs_converter --input_format=tf_saved_model --output_node_names='detection_boxes,detection_classes,detection_features,detection_multiclass_scores,detection_scores,num_detections,raw_detection_boxes,raw_detection_scores' --output_format=tfjs_graph_model --signature_name=serving_default {} {}\".format(os.path.join(paths['OUTPUT_PATH'], 'saved_model'), paths['TFJS_PATH'])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "DB2AGNmJpfDK", + "outputId": "fbc9f747-f511-47e8-df8f-5ea65cef0374" + }, + "outputs": [], + "source": [ + "print(command)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "K7rfT4-hpfDK", + "outputId": "532707fd-6feb-4bc6-84a3-325b5d16303c" + }, + "outputs": [], + "source": [ + "!{command}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "VtUw73FHpfDK" + }, + "source": [ + "# 12. Conversion to TFLite" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "XviMtewLpfDK" + }, + "outputs": [], + "source": [ + "TFLITE_SCRIPT = os.path.join(paths['APIMODEL_PATH'], 'research', 'object_detection', 'export_tflite_graph_tf2.py ')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "us86cjC4pfDL" + }, + "outputs": [], + "source": [ + "command = \"python {} --pipeline_config_path={} --trained_checkpoint_dir={} --output_directory={}\".format(TFLITE_SCRIPT ,files['PIPELINE_CONFIG'], paths['CHECKPOINT_PATH'], paths['TFLITE_PATH'])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "n1r5YO3rpfDL", + "outputId": "5fcdf7a4-eee2-4365-f1ca-1751968379ea" + }, + "outputs": [], + "source": [ + "print(command)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "I-xWpHN8pfDL", + "outputId": "7f6bacd8-d077-43b5-c131-5b081fba24a4" + }, + "outputs": [], + "source": [ + "!{command}" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "iJfYMbN6pfDL" + }, + "outputs": [], + "source": [ + "FROZEN_TFLITE_PATH = os.path.join(paths['TFLITE_PATH'], 'saved_model')\n", + "TFLITE_MODEL = os.path.join(paths['TFLITE_PATH'], 'saved_model', 'detect.tflite')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "command = \"tflite_convert \\\n", + "--saved_model_dir={} \\\n", + "--output_file={} \\\n", + "--input_shapes=1,300,300,3 \\\n", + "--input_arrays=normalized_input_image_tensor \\\n", + "--output_arrays='TFLite_Detection_PostProcess','TFLite_Detection_PostProcess:1','TFLite_Detection_PostProcess:2','TFLite_Detection_PostProcess:3' \\\n", + "--inference_type=FLOAT \\\n", + "--allow_custom_ops\".format(FROZEN_TFLITE_PATH, TFLITE_MODEL, )" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "E8GwUeoFpfDL", + "outputId": "fac43ea4-cc85-471b-a362-e994b06fd583" + }, + "outputs": [], + "source": [ + "print(command)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Nbd7gqHMpfDL", + "outputId": "7c8fe6d5-2415-4641-8548-39d425c202f7" + }, + "outputs": [], + "source": [ + "!{command}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5NQqZRdA21Uc" + }, + "source": [ + "# 13. Zip and Export Models " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "tTVTGCQp2ZJJ" + }, + "outputs": [], + "source": [ + "!tar -czf models.tar.gz {paths['CHECKPOINT_PATH']}" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "whShhB0x3PYJ", + "outputId": "b773201d-35c9-46a8-b893-4a76bd4d5d97" + }, + "outputs": [], + "source": [ + "from google.colab import drive\n", + "drive.mount('/content/drive')" + ] + } + ], + "metadata": { + "accelerator": "GPU", + "colab": { + "name": "3. Training and Detection.ipynb", + "provenance": [] + }, + "kernelspec": { + "display_name": "tfod", + "language": "python", + "name": "tfod" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.9.13" + } + }, + "nbformat": 4, + "nbformat_minor": 1 +}