From 6a6d4cc54dc806b336e16f3b3a4f0ec277e35b44 Mon Sep 17 00:00:00 2001
From: Ganesh Shet <72651335+ganesh-shet@users.noreply.github.com>
Date: Tue, 20 Jul 2021 12:02:55 +0530
Subject: [PATCH 1/4] Created using Colaboratory

---
 Brain_tumor__classification.ipynb | 588 ++++++++++++++++++++++++++++++
 1 file changed, 588 insertions(+)
 create mode 100644 Brain_tumor__classification.ipynb

diff --git a/Brain_tumor__classification.ipynb b/Brain_tumor__classification.ipynb
new file mode 100644
index 000000000..a38073f50
--- /dev/null
+++ b/Brain_tumor__classification.ipynb
@@ -0,0 +1,588 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "Brain_tumor _classification.ipynb",
+      "provenance": [],
+      "collapsed_sections": [],
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/ganesh-shet/Open-contributions/blob/master/Brain_tumor__classification.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "PAPwrQbqi_my"
+      },
+      "source": [
+        "import os\n",
+        "import keras\n",
+        "from keras.models import Sequential\n",
+        "from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization\n",
+        "from PIL import Image\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "import matplotlib.pyplot as plt\n",
+        "plt.style.use('dark_background')\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.preprocessing import OneHotEncoder"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Eo_wWiFCjDOF"
+      },
+      "source": [
+        "**One Hot Encoding the Target Classes**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "4UobBFDVjLS3",
+        "outputId": "3f6f9e73-769c-4bb6-9d56-2aa3f7f95a26"
+      },
+      "source": [
+        "encoder = OneHotEncoder()\n",
+        "encoder.fit([[0], [1]]) \n",
+        " \n",
+        "# 0 - Tumor\n",
+        "# 1 - Normal"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "OneHotEncoder(categories='auto', drop=None, dtype=<class 'numpy.float64'>,\n",
+              "              handle_unknown='error', sparse=True)"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 18
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4bM74LOJjOuT"
+      },
+      "source": [
+        "**Creating 3 Important Lists --**\n",
+        "\n",
+        "data list for storing image data in numpy array form\n",
+        "\n",
+        "paths list for storing paths of all images\n",
+        "\n",
+        "result list for storing one hot encoded form of target class whether normal or tumor"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "BDwqGB0ujU6N"
+      },
+      "source": [
+        "# This cell updates result list for images with tumor\n",
+        "\n",
+        "data = []\n",
+        "paths = []\n",
+        "result = []\n",
+        "\n",
+        "for r, d, f in os.walk(r'/content/yes'):\n",
+        "    for file in f:\n",
+        "        if '.jpg' in file:\n",
+        "            paths.append(os.path.join(r, file))\n",
+        "\n",
+        "for path in paths:\n",
+        "    img = Image.open(path)\n",
+        "    img = img.resize((128,128))\n",
+        "    img = np.array(img)\n",
+        "    if(img.shape == (128,128,3)):\n",
+        "        data.append(np.array(img))\n",
+        "        result.append(encoder.transform([[0]]).toarray())"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "YW7z5NWdl0LI"
+      },
+      "source": [
+        "# This cell updates result list for images without tumor\n",
+        "\n",
+        "paths = []\n",
+        "for r, d, f in os.walk(r\"/content/no\"):\n",
+        "    for file in f:\n",
+        "        if '.jpg' in file:\n",
+        "            paths.append(os.path.join(r, file))\n",
+        "\n",
+        "for path in paths:\n",
+        "    img = Image.open(path)\n",
+        "    img = img.resize((128,128))\n",
+        "    img = np.array(img)\n",
+        "    if(img.shape == (128,128,3)):\n",
+        "        data.append(np.array(img))\n",
+        "        result.append(encoder.transform([[1]]).toarray())"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "K2_2d70kl8cl",
+        "outputId": "1c980e34-849e-473e-c4d4-293f916af185"
+      },
+      "source": [
+        "data = np.array(data)\n",
+        "data.shape"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "(139, 128, 128, 3)"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 21
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "qV8JRzJomCpH"
+      },
+      "source": [
+        "result = np.array(result)\n",
+        "result = result.reshape(139,2)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FCMJkBWQmGW9"
+      },
+      "source": [
+        "**Splitting the Data into Training & Testing**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "nGsHO-YnmIi7"
+      },
+      "source": [
+        "x_train,x_test,y_train,y_test = train_test_split(data, result, test_size=0.2, shuffle=True, random_state=0)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "-VsblLdin64H"
+      },
+      "source": [
+        "**Model Building**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "YcFozx8gn9GV",
+        "outputId": "6638d79a-8a02-4a99-9d8c-64536a4fd52e"
+      },
+      "source": [
+        "model = Sequential()\n",
+        "\n",
+        "model.add(Conv2D(32, kernel_size=(2, 2), input_shape=(128, 128, 3), padding = 'Same'))    #filter = 32\n",
+        "model.add(Conv2D(32, kernel_size=(2, 2),  activation ='relu', padding = 'Same'))\n",
+        "\n",
+        "\n",
+        "model.add(BatchNormalization())\n",
+        "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
+        "model.add(Dropout(0.25))\n",
+        "\n",
+        "model.add(Conv2D(64, kernel_size = (2,2), activation ='relu', padding = 'Same'))\n",
+        "model.add(Conv2D(64, kernel_size = (2,2), activation ='relu', padding = 'Same'))\n",
+        "\n",
+        "model.add(BatchNormalization())\n",
+        "model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))\n",
+        "model.add(Dropout(0.25))\n",
+        "\n",
+        "model.add(Flatten())    #to convert it into 1D array\n",
+        "\n",
+        "model.add(Dense(512, activation='relu'))\n",
+        "model.add(Dropout(0.5))\n",
+        "model.add(Dense(2, activation='softmax'))\n",
+        "\n",
+        "model.compile(loss = \"categorical_crossentropy\", optimizer='Adamax')\n",
+        "print(model.summary())"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Model: \"sequential\"\n",
+            "_________________________________________________________________\n",
+            "Layer (type)                 Output Shape              Param #   \n",
+            "=================================================================\n",
+            "conv2d (Conv2D)              (None, 128, 128, 32)      416       \n",
+            "_________________________________________________________________\n",
+            "conv2d_1 (Conv2D)            (None, 128, 128, 32)      4128      \n",
+            "_________________________________________________________________\n",
+            "batch_normalization (BatchNo (None, 128, 128, 32)      128       \n",
+            "_________________________________________________________________\n",
+            "max_pooling2d (MaxPooling2D) (None, 64, 64, 32)        0         \n",
+            "_________________________________________________________________\n",
+            "dropout (Dropout)            (None, 64, 64, 32)        0         \n",
+            "_________________________________________________________________\n",
+            "conv2d_2 (Conv2D)            (None, 64, 64, 64)        8256      \n",
+            "_________________________________________________________________\n",
+            "conv2d_3 (Conv2D)            (None, 64, 64, 64)        16448     \n",
+            "_________________________________________________________________\n",
+            "batch_normalization_1 (Batch (None, 64, 64, 64)        256       \n",
+            "_________________________________________________________________\n",
+            "max_pooling2d_1 (MaxPooling2 (None, 32, 32, 64)        0         \n",
+            "_________________________________________________________________\n",
+            "dropout_1 (Dropout)          (None, 32, 32, 64)        0         \n",
+            "_________________________________________________________________\n",
+            "flatten (Flatten)            (None, 65536)             0         \n",
+            "_________________________________________________________________\n",
+            "dense (Dense)                (None, 512)               33554944  \n",
+            "_________________________________________________________________\n",
+            "dropout_2 (Dropout)          (None, 512)               0         \n",
+            "_________________________________________________________________\n",
+            "dense_1 (Dense)              (None, 2)                 1026      \n",
+            "=================================================================\n",
+            "Total params: 33,585,602\n",
+            "Trainable params: 33,585,410\n",
+            "Non-trainable params: 192\n",
+            "_________________________________________________________________\n",
+            "None\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "26lOZchrqCqy",
+        "outputId": "5eee4c65-d327-4008-822a-81e56ffcdca4"
+      },
+      "source": [
+        "x_train.shape,y_train.shape"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "((111, 128, 128, 3), (111, 2))"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 25
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Iz9r6PERqNBy",
+        "outputId": "17d1a5a1-9c73-46d9-b0e7-e9a2ae433927"
+      },
+      "source": [
+        "history = model.fit(x_train, y_train, epochs = 30, batch_size = 40, verbose = 1,validation_data = (x_test, y_test))"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Epoch 1/30\n",
+            "3/3 [==============================] - 23s 2s/step - loss: 24.8065 - val_loss: 122.1450\n",
+            "Epoch 2/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 30.8271 - val_loss: 6.1901\n",
+            "Epoch 3/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 6.2034 - val_loss: 20.0883\n",
+            "Epoch 4/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 5.8615 - val_loss: 9.9306\n",
+            "Epoch 5/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 3.5619 - val_loss: 7.8809\n",
+            "Epoch 6/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 2.4879 - val_loss: 5.5015\n",
+            "Epoch 7/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 3.3705 - val_loss: 8.0041\n",
+            "Epoch 8/30\n",
+            "3/3 [==============================] - 4s 1s/step - loss: 1.4793 - val_loss: 11.7809\n",
+            "Epoch 9/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.6725 - val_loss: 10.3848\n",
+            "Epoch 10/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.5452 - val_loss: 6.1997\n",
+            "Epoch 11/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.4472 - val_loss: 3.2398\n",
+            "Epoch 12/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.3110 - val_loss: 3.2581\n",
+            "Epoch 13/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.1722 - val_loss: 3.7988\n",
+            "Epoch 14/30\n",
+            "3/3 [==============================] - 4s 1s/step - loss: 0.1607 - val_loss: 3.1843\n",
+            "Epoch 15/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.6450 - val_loss: 1.7232\n",
+            "Epoch 16/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.0555 - val_loss: 1.1013\n",
+            "Epoch 17/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.0566 - val_loss: 1.1441\n",
+            "Epoch 18/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.1296 - val_loss: 1.2352\n",
+            "Epoch 19/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.2164 - val_loss: 1.1803\n",
+            "Epoch 20/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.3882 - val_loss: 1.0945\n",
+            "Epoch 21/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.0034 - val_loss: 1.3205\n",
+            "Epoch 22/30\n",
+            "3/3 [==============================] - 4s 1s/step - loss: 0.0318 - val_loss: 1.5557\n",
+            "Epoch 23/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.0014 - val_loss: 1.7030\n",
+            "Epoch 24/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 5.2023e-05 - val_loss: 1.8164\n",
+            "Epoch 25/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 2.1774e-05 - val_loss: 1.8930\n",
+            "Epoch 26/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.0015 - val_loss: 1.9366\n",
+            "Epoch 27/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 5.0864e-05 - val_loss: 1.9636\n",
+            "Epoch 28/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.0107 - val_loss: 1.8991\n",
+            "Epoch 29/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.0056 - val_loss: 1.7370\n",
+            "Epoch 30/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.0014 - val_loss: 1.6413\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "WhhzL2UWsVfk"
+      },
+      "source": [
+        "**Plotting Losses**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 295
+        },
+        "id": "kE1Q4WsvsYLE",
+        "outputId": "6b29ebce-1b83-4d0a-b309-67cbb0444f21"
+      },
+      "source": [
+        "plt.plot(history.history['loss'])\n",
+        "plt.plot(history.history['val_loss'])\n",
+        "plt.title('Model Loss')\n",
+        "plt.ylabel('Loss')\n",
+        "plt.xlabel('Epoch')\n",
+        "plt.legend(['Test', 'Validation'], loc='upper right')\n",
+        "plt.show()"
+      ],
+      "execution_count": 36,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 432x288 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "kNgbi7zjuoHA"
+      },
+      "source": [
+        "**Just Checking the Model**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "YPYNjKFyupfW"
+      },
+      "source": [
+        "def names(number):\n",
+        "    if number==0:\n",
+        "        return ' **A Tumor**'\n",
+        "    else:\n",
+        "        return '**Not a tumor**'"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 286
+        },
+        "id": "FZtS-Kcsuyb8",
+        "outputId": "9e056869-7a02-44cf-b897-6b26f78c6399"
+      },
+      "source": [
+        "from matplotlib.pyplot import imshow\n",
+        "img = Image.open(r\"/content/no/18 no.jpg\")\n",
+        "x = np.array(img.resize((128,128)))\n",
+        "x = x.reshape(1,128,128,3)\n",
+        "res = model.predict_on_batch(x)\n",
+        "classification = np.where(res == np.amax(res))[1][0]\n",
+        "imshow(img)\n",
+        "print(str(res[0][classification]*100) + '% Confidence This Is ' + names(classification))"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "100.0% Confidence This Is **Not a tumor**\n"
+          ],
+          "name": "stdout"
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 432x288 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 286
+        },
+        "id": "_DWEKsQFwTni",
+        "outputId": "44e38749-9922-4620-d718-239611d07b6c"
+      },
+      "source": [
+        "from matplotlib.pyplot import imshow\n",
+        "img = Image.open(r\"/content/yes/Y102.jpg\")\n",
+        "x = np.array(img.resize((128,128)))\n",
+        "x = x.reshape(1,128,128,3)\n",
+        "res = model.predict_on_batch(x)\n",
+        "classification = np.where(res == np.amax(res))[1][0]\n",
+        "imshow(img)\n",
+        "print(str(res[0][classification]*100) + '% Confidence This Is ' + names(classification))"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "99.98278617858887% Confidence This Is  **A Tumor**\n"
+          ],
+          "name": "stdout"
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 432x288 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "zc1WZJZjw852"
+      },
+      "source": [
+        "**THANK YOU**"
+      ]
+    }
+  ]
+}
\ No newline at end of file

From 20fb774cf3c0c6b70d9730a9ede9114c51c8118d Mon Sep 17 00:00:00 2001
From: Ganesh Shet <72651335+ganesh-shet@users.noreply.github.com>
Date: Tue, 20 Jul 2021 12:08:04 +0530
Subject: [PATCH 2/4] Create Ganesh_G_Shet_Brain_tumor_detection.ipynb

---
 Ganesh_G_Shet_Brain_tumor_detection.ipynb | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 Ganesh_G_Shet_Brain_tumor_detection.ipynb

diff --git a/Ganesh_G_Shet_Brain_tumor_detection.ipynb b/Ganesh_G_Shet_Brain_tumor_detection.ipynb
new file mode 100644
index 000000000..8b1378917
--- /dev/null
+++ b/Ganesh_G_Shet_Brain_tumor_detection.ipynb
@@ -0,0 +1 @@
+

From 95dc3b243e964c6619aa3813555820d3bf9a0b67 Mon Sep 17 00:00:00 2001
From: Ganesh Shet <72651335+ganesh-shet@users.noreply.github.com>
Date: Tue, 20 Jul 2021 12:11:20 +0530
Subject: [PATCH 3/4] Created using Colaboratory

---
 ...h_G_Shet_Brain_tumor__classification.ipynb | 588 ++++++++++++++++++
 1 file changed, 588 insertions(+)
 create mode 100644 Ganesh_G_Shet_Brain_tumor__classification.ipynb

diff --git a/Ganesh_G_Shet_Brain_tumor__classification.ipynb b/Ganesh_G_Shet_Brain_tumor__classification.ipynb
new file mode 100644
index 000000000..6acd8c68d
--- /dev/null
+++ b/Ganesh_G_Shet_Brain_tumor__classification.ipynb
@@ -0,0 +1,588 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "Brain_tumor _classification.ipynb",
+      "provenance": [],
+      "collapsed_sections": [],
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/ganesh-shet/Open-contributions/blob/master/Ganesh_G_Shet_Brain_tumor__classification.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "PAPwrQbqi_my"
+      },
+      "source": [
+        "import os\n",
+        "import keras\n",
+        "from keras.models import Sequential\n",
+        "from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization\n",
+        "from PIL import Image\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "import matplotlib.pyplot as plt\n",
+        "plt.style.use('dark_background')\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.preprocessing import OneHotEncoder"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Eo_wWiFCjDOF"
+      },
+      "source": [
+        "**One Hot Encoding the Target Classes**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "4UobBFDVjLS3",
+        "outputId": "3f6f9e73-769c-4bb6-9d56-2aa3f7f95a26"
+      },
+      "source": [
+        "encoder = OneHotEncoder()\n",
+        "encoder.fit([[0], [1]]) \n",
+        " \n",
+        "# 0 - Tumor\n",
+        "# 1 - Normal"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "OneHotEncoder(categories='auto', drop=None, dtype=<class 'numpy.float64'>,\n",
+              "              handle_unknown='error', sparse=True)"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 18
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4bM74LOJjOuT"
+      },
+      "source": [
+        "**Creating 3 Important Lists --**\n",
+        "\n",
+        "data list for storing image data in numpy array form\n",
+        "\n",
+        "paths list for storing paths of all images\n",
+        "\n",
+        "result list for storing one hot encoded form of target class whether normal or tumor"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "BDwqGB0ujU6N"
+      },
+      "source": [
+        "# This cell updates result list for images with tumor\n",
+        "\n",
+        "data = []\n",
+        "paths = []\n",
+        "result = []\n",
+        "\n",
+        "for r, d, f in os.walk(r'/content/yes'):\n",
+        "    for file in f:\n",
+        "        if '.jpg' in file:\n",
+        "            paths.append(os.path.join(r, file))\n",
+        "\n",
+        "for path in paths:\n",
+        "    img = Image.open(path)\n",
+        "    img = img.resize((128,128))\n",
+        "    img = np.array(img)\n",
+        "    if(img.shape == (128,128,3)):\n",
+        "        data.append(np.array(img))\n",
+        "        result.append(encoder.transform([[0]]).toarray())"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "YW7z5NWdl0LI"
+      },
+      "source": [
+        "# This cell updates result list for images without tumor\n",
+        "\n",
+        "paths = []\n",
+        "for r, d, f in os.walk(r\"/content/no\"):\n",
+        "    for file in f:\n",
+        "        if '.jpg' in file:\n",
+        "            paths.append(os.path.join(r, file))\n",
+        "\n",
+        "for path in paths:\n",
+        "    img = Image.open(path)\n",
+        "    img = img.resize((128,128))\n",
+        "    img = np.array(img)\n",
+        "    if(img.shape == (128,128,3)):\n",
+        "        data.append(np.array(img))\n",
+        "        result.append(encoder.transform([[1]]).toarray())"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "K2_2d70kl8cl",
+        "outputId": "1c980e34-849e-473e-c4d4-293f916af185"
+      },
+      "source": [
+        "data = np.array(data)\n",
+        "data.shape"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "(139, 128, 128, 3)"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 21
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "qV8JRzJomCpH"
+      },
+      "source": [
+        "result = np.array(result)\n",
+        "result = result.reshape(139,2)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FCMJkBWQmGW9"
+      },
+      "source": [
+        "**Splitting the Data into Training & Testing**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "nGsHO-YnmIi7"
+      },
+      "source": [
+        "x_train,x_test,y_train,y_test = train_test_split(data, result, test_size=0.2, shuffle=True, random_state=0)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "-VsblLdin64H"
+      },
+      "source": [
+        "**Model Building**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "YcFozx8gn9GV",
+        "outputId": "6638d79a-8a02-4a99-9d8c-64536a4fd52e"
+      },
+      "source": [
+        "model = Sequential()\n",
+        "\n",
+        "model.add(Conv2D(32, kernel_size=(2, 2), input_shape=(128, 128, 3), padding = 'Same'))    #filter = 32\n",
+        "model.add(Conv2D(32, kernel_size=(2, 2),  activation ='relu', padding = 'Same'))\n",
+        "\n",
+        "\n",
+        "model.add(BatchNormalization())\n",
+        "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
+        "model.add(Dropout(0.25))\n",
+        "\n",
+        "model.add(Conv2D(64, kernel_size = (2,2), activation ='relu', padding = 'Same'))\n",
+        "model.add(Conv2D(64, kernel_size = (2,2), activation ='relu', padding = 'Same'))\n",
+        "\n",
+        "model.add(BatchNormalization())\n",
+        "model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))\n",
+        "model.add(Dropout(0.25))\n",
+        "\n",
+        "model.add(Flatten())    #to convert it into 1D array\n",
+        "\n",
+        "model.add(Dense(512, activation='relu'))\n",
+        "model.add(Dropout(0.5))\n",
+        "model.add(Dense(2, activation='softmax'))\n",
+        "\n",
+        "model.compile(loss = \"categorical_crossentropy\", optimizer='Adamax')\n",
+        "print(model.summary())"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Model: \"sequential\"\n",
+            "_________________________________________________________________\n",
+            "Layer (type)                 Output Shape              Param #   \n",
+            "=================================================================\n",
+            "conv2d (Conv2D)              (None, 128, 128, 32)      416       \n",
+            "_________________________________________________________________\n",
+            "conv2d_1 (Conv2D)            (None, 128, 128, 32)      4128      \n",
+            "_________________________________________________________________\n",
+            "batch_normalization (BatchNo (None, 128, 128, 32)      128       \n",
+            "_________________________________________________________________\n",
+            "max_pooling2d (MaxPooling2D) (None, 64, 64, 32)        0         \n",
+            "_________________________________________________________________\n",
+            "dropout (Dropout)            (None, 64, 64, 32)        0         \n",
+            "_________________________________________________________________\n",
+            "conv2d_2 (Conv2D)            (None, 64, 64, 64)        8256      \n",
+            "_________________________________________________________________\n",
+            "conv2d_3 (Conv2D)            (None, 64, 64, 64)        16448     \n",
+            "_________________________________________________________________\n",
+            "batch_normalization_1 (Batch (None, 64, 64, 64)        256       \n",
+            "_________________________________________________________________\n",
+            "max_pooling2d_1 (MaxPooling2 (None, 32, 32, 64)        0         \n",
+            "_________________________________________________________________\n",
+            "dropout_1 (Dropout)          (None, 32, 32, 64)        0         \n",
+            "_________________________________________________________________\n",
+            "flatten (Flatten)            (None, 65536)             0         \n",
+            "_________________________________________________________________\n",
+            "dense (Dense)                (None, 512)               33554944  \n",
+            "_________________________________________________________________\n",
+            "dropout_2 (Dropout)          (None, 512)               0         \n",
+            "_________________________________________________________________\n",
+            "dense_1 (Dense)              (None, 2)                 1026      \n",
+            "=================================================================\n",
+            "Total params: 33,585,602\n",
+            "Trainable params: 33,585,410\n",
+            "Non-trainable params: 192\n",
+            "_________________________________________________________________\n",
+            "None\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "26lOZchrqCqy",
+        "outputId": "5eee4c65-d327-4008-822a-81e56ffcdca4"
+      },
+      "source": [
+        "x_train.shape,y_train.shape"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "((111, 128, 128, 3), (111, 2))"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 25
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Iz9r6PERqNBy",
+        "outputId": "17d1a5a1-9c73-46d9-b0e7-e9a2ae433927"
+      },
+      "source": [
+        "history = model.fit(x_train, y_train, epochs = 30, batch_size = 40, verbose = 1,validation_data = (x_test, y_test))"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Epoch 1/30\n",
+            "3/3 [==============================] - 23s 2s/step - loss: 24.8065 - val_loss: 122.1450\n",
+            "Epoch 2/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 30.8271 - val_loss: 6.1901\n",
+            "Epoch 3/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 6.2034 - val_loss: 20.0883\n",
+            "Epoch 4/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 5.8615 - val_loss: 9.9306\n",
+            "Epoch 5/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 3.5619 - val_loss: 7.8809\n",
+            "Epoch 6/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 2.4879 - val_loss: 5.5015\n",
+            "Epoch 7/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 3.3705 - val_loss: 8.0041\n",
+            "Epoch 8/30\n",
+            "3/3 [==============================] - 4s 1s/step - loss: 1.4793 - val_loss: 11.7809\n",
+            "Epoch 9/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.6725 - val_loss: 10.3848\n",
+            "Epoch 10/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.5452 - val_loss: 6.1997\n",
+            "Epoch 11/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.4472 - val_loss: 3.2398\n",
+            "Epoch 12/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.3110 - val_loss: 3.2581\n",
+            "Epoch 13/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.1722 - val_loss: 3.7988\n",
+            "Epoch 14/30\n",
+            "3/3 [==============================] - 4s 1s/step - loss: 0.1607 - val_loss: 3.1843\n",
+            "Epoch 15/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.6450 - val_loss: 1.7232\n",
+            "Epoch 16/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.0555 - val_loss: 1.1013\n",
+            "Epoch 17/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.0566 - val_loss: 1.1441\n",
+            "Epoch 18/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.1296 - val_loss: 1.2352\n",
+            "Epoch 19/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.2164 - val_loss: 1.1803\n",
+            "Epoch 20/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.3882 - val_loss: 1.0945\n",
+            "Epoch 21/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.0034 - val_loss: 1.3205\n",
+            "Epoch 22/30\n",
+            "3/3 [==============================] - 4s 1s/step - loss: 0.0318 - val_loss: 1.5557\n",
+            "Epoch 23/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.0014 - val_loss: 1.7030\n",
+            "Epoch 24/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 5.2023e-05 - val_loss: 1.8164\n",
+            "Epoch 25/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 2.1774e-05 - val_loss: 1.8930\n",
+            "Epoch 26/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.0015 - val_loss: 1.9366\n",
+            "Epoch 27/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 5.0864e-05 - val_loss: 1.9636\n",
+            "Epoch 28/30\n",
+            "3/3 [==============================] - 5s 1s/step - loss: 0.0107 - val_loss: 1.8991\n",
+            "Epoch 29/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.0056 - val_loss: 1.7370\n",
+            "Epoch 30/30\n",
+            "3/3 [==============================] - 5s 2s/step - loss: 0.0014 - val_loss: 1.6413\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "WhhzL2UWsVfk"
+      },
+      "source": [
+        "**Plotting Losses**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 295
+        },
+        "id": "kE1Q4WsvsYLE",
+        "outputId": "6b29ebce-1b83-4d0a-b309-67cbb0444f21"
+      },
+      "source": [
+        "plt.plot(history.history['loss'])\n",
+        "plt.plot(history.history['val_loss'])\n",
+        "plt.title('Model Loss')\n",
+        "plt.ylabel('Loss')\n",
+        "plt.xlabel('Epoch')\n",
+        "plt.legend(['Test', 'Validation'], loc='upper right')\n",
+        "plt.show()"
+      ],
+      "execution_count": 36,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 432x288 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "kNgbi7zjuoHA"
+      },
+      "source": [
+        "**Just Checking the Model**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "YPYNjKFyupfW"
+      },
+      "source": [
+        "def names(number):\n",
+        "    if number==0:\n",
+        "        return ' **A Tumor**'\n",
+        "    else:\n",
+        "        return '**Not a tumor**'"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 286
+        },
+        "id": "FZtS-Kcsuyb8",
+        "outputId": "9e056869-7a02-44cf-b897-6b26f78c6399"
+      },
+      "source": [
+        "from matplotlib.pyplot import imshow\n",
+        "img = Image.open(r\"/content/no/18 no.jpg\")\n",
+        "x = np.array(img.resize((128,128)))\n",
+        "x = x.reshape(1,128,128,3)\n",
+        "res = model.predict_on_batch(x)\n",
+        "classification = np.where(res == np.amax(res))[1][0]\n",
+        "imshow(img)\n",
+        "print(str(res[0][classification]*100) + '% Confidence This Is ' + names(classification))"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "100.0% Confidence This Is **Not a tumor**\n"
+          ],
+          "name": "stdout"
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 432x288 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 286
+        },
+        "id": "_DWEKsQFwTni",
+        "outputId": "44e38749-9922-4620-d718-239611d07b6c"
+      },
+      "source": [
+        "from matplotlib.pyplot import imshow\n",
+        "img = Image.open(r\"/content/yes/Y102.jpg\")\n",
+        "x = np.array(img.resize((128,128)))\n",
+        "x = x.reshape(1,128,128,3)\n",
+        "res = model.predict_on_batch(x)\n",
+        "classification = np.where(res == np.amax(res))[1][0]\n",
+        "imshow(img)\n",
+        "print(str(res[0][classification]*100) + '% Confidence This Is ' + names(classification))"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "99.98278617858887% Confidence This Is  **A Tumor**\n"
+          ],
+          "name": "stdout"
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPIAAAD8CAYAAABNYvnUAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOy9SYxk2XXe/8WUMc85dWbW1FSxScoS1RagFiDAIGDBsrTpnWBoQVoQyBVhGPBCDW+8lVeGVlo0ZFgCbBgCBINaSBYNGhQ8wATdIFuy2FRXNbuGzKrKOSMzpozIiPgv8v878cXrrGpabMlJoS6QqMrIF2+49wzf+c6556UkzfRyvBwvx4/1SP+/voGX4+V4OX708VKRX46X4+/AeKnIL8fL8XdgvFTkl+Pl+DswXiryy/Fy/B0YLxX55Xg5/g6MvxFF/qVf+iV9//vf17179/Sbv/mbfxOXeDlejpcjMWaf5E86nZ7dv39/dufOnVkul5t997vfnX32s5/9RK/x8uflz8ufxZ9P3CP/3M/9nO7fv68PP/xQ4/FY//E//ke9+eabn/RlXo6X4+Wwkf2kT7i5uanHjx/H79vb23rjjTde+J39/X09evQofp/NZpKkVCr1f3392Wy28L3k7z/KSKVScW+f9Pm4R37/v73vdHrRJqdSqfi+n9s/T16Pf/2eZrOZptOp0ul0fH82m8XvyZH87IeZr+SzJ//2w35+1Zwlf3/R/bzoPn7Y4ffw15WXF33vxo0bWl1d/cjnn7gi/7Djy1/+sr7yla9Ikvr9vv7BP/gHymQymk6nmkwmC4LCg/nDTadTpVIpZbOXjzCZTOKYTCYTk8lxCPpkMonrMPg7QouwI8AMvyeuxTH8SNLFxYVms5my2Wwc4+eYTqcfUSr//2QyiWtwTq67tLSkdDqtTCajQqEQn9VqtfhbsVjU0tJSPGuhUNBsNos5Wlpa0mAwUCqVUrFY1Gg00mAw0GQy0cXFhVKplEajkabTqc7Pz+N+stmsRqORJCmXyymdTms8HmtpaUnn5+caDoc6Pz9XPp9XLpdTr9fTcDiM76RSKU0mE+VyOY1Go3he5nUymcRasyash8uCz6crzmQyiTnnvMiAfze53i4Dfl7k5OLiQplMRtlsNo5n3a+SV/6ObLrsuQz6efy5k4rM59PpVH/2Z3+mq8Ynrsg7Ozu6ceNG/L61taWdnZ2PHPf222/r7bffliS98847McFMAP9H6P2BmHRfVF/0pDBwHMrlE+VCIS1aQ5SV31kIFoFz8z0WHaVOCl/SgLCgLLgvqt8PnxUKBVWrVeXzeZVKJVWrVRUKBRWLRRUKhVDwpaUljUYjzWYz5XI5TSYTTadT9ft9LS0tSZKWl5dDQNPpdNzD2dmZlpaWNB6PdX5+Hgp2eHioVCqli4sLVSoVZTIZjUYj5fP5BQN6cnKi09NT1et1zWYznZ6eqtvtajKZaDwexxxxXubZnx1jwvO7Uc5kMguGwA0qxzLfKHYmk9HFxUXIAIbej+Uafiz3gnFgbTmPGwH/l/P4fbsB8GdxY+MGyX//YZDCJ67I3/72t3X37l3dvn1bOzs7+if/5J/o137t1z72eyiHpIWFYeKSk8YEpNPphYnPZDILCp88Xpp7b4YLBNaVc0nzSU8unk8w3tOVknO5YicNjiSNx+MFhU2n01paWtLS0pIymYzK5bLK5bKq1aqKxaJqtZqq1aqy2azy+byWlpaUSqXU6/VCgbnH8/Pz8Lj8rdlsqtPpaDAYqFAoKJ/PK5/PhwDlcrlYE4fXe3t7qtfrarfbGo/HcZ3xeKxqtap0Oq16va4PP/xQmUxGKysrWl5e1vn5uc7OzpROp8NzDwYDDQaDuD/3yLlcbmHNmRc8Oscx99xnMgTwH+Y+nU7HOVAkdyCcO5PJLMiCK5mvN39LGmmXGxTf78FlCWPr64ac8IxJA58cn7giTyYTffWrX9Wf/umfKpPJ6N/+23+r733vey/8DpOBJXbv7ArFsUlPKS1CLI/lHK6x0MmFl7TwN5SQa3NMNpsNAXalTMJfn3gU++LiIq7j9+zPWCgUlMvllMvl1Gw2VSwWAyaXy2XV6/VQ3lwuFxAYSHt2dqbRaKR+v698Pq9UKqV+v6/z8/PwrpJ0cnKi8XgcSsxzYRAODw9VrVZ1enoaBuX8/FyFQkHD4VD7+/sql8s6Pz9fuP9UKqWlpSWtrKxob29Pw+FQ9XpdjUYjEIMknZ+fazweazKZqNvt6vDwMJQaz+1zhEK5rCQ/T66Bw14Uw8+Bd+U8mUxG5+fnHwnXHFklERjG3a+XRHTukPy+OQeykVR0fyaU/G9VkSXpT/7kT/Qnf/InP/TxPHDyZpNKxYQDfxhXKZNDdAaTDaT0WCmpuJwfoXKPKs0FCu+RFCq3qEkDxfd5lmw2q3K5rHw+r0ajoWq1qlwup3w+r1qtpmw2q4uLi3h+/j8ajdTpdDQej9Xr9UJBxuOx+v3+guJwP3j/XC6nfr8f8879Z7NZ5XK5iKuHw2HEwyjAdDpVo9GIv0tSuVyWdBmvY2i2t7fV7Xa1vLysTCajfr+vSqWitbU1nZ6eajabqVwua3V1NRQaVNHtdsP4IOjIAOFBLpdbWDv+jkF2z8f/XSaSRigZrrnDcE/P9ZARdypJssvPl1RoRwrPM/DIE99/3vh/RnYlRxL6uGVLWju3UO5h/TvJz57nwVEO4KQvBMKQhDgelzmxJc2Fw4UlaQS4HiRVPp9XpVJRvV5XsVjU8vJyeKbJZKLhcBjKWiwWAwKfn5+r3++r1+tpMBgsGJThcBge0oUQJcBI8sPcj0YjXVxcaDAYSLo0ZMTd0pywOjg4iHvIZrPqdDqSLlHL0tKSstmsut2ujo6OggC7uLgIr8c9VatVTadT5fN5lcvlUOTDw0OdnZ3FM3ocLs35iuRAUUajkbLZ7EcQl3s/P97lKUmW+WeuYPzN42Y/LhnTekiQlKOr4uGr4ufnjWuhyB4b8LtDIv97MhZKKo5bwOTkugWUtGAwkmgAxfR7SAqAX8OfI3lffs18Ph+QttVqqd1uq1arqVKpaDqdam1tLSDncDhUt9tVr9dTr9fT8fGx0um0crmcMpmMBoNBeHtHDsPhMI6bTqdBiAHDl5aWdHFxoVKppFwuF7GyI55erxes9Gw2U7FYlHSJLpaWlhYMIfOC5+/3+0EQ9Xo9PXjwQKVSSbVaLZ4Jlr3X66lSqQQqWVpaCjRVq9V0dHQUiOT8/DwQgcuOcwv8zrNzPA7C437my0lVR4ceqzvHgoHAoPp3kzyKIzWH4j78eTzuduOSPC45roUiJ70pC5LL5RZglUMTvucPl4RE7omuUlY3DEkY4+kDh27cIwqUjMUdJTi6WFpaUi6XU7lc1srKitrttorFosrlstrtti4uLtTtdpVKpdTpdHR0dKSjoyMdHh5qPB5rMBhoPB5HDC1Jo9EoYth8Pq/hcKiLi4swFk5alctlFQqF+BmPx8F+DwaD8LqghePj41BSFGMymajf74chmUwmKhaLkWLi3jAkMNzT6VS9Xi9STygIEB54C0pBuUqlkvL5vHq9nrrdbhB23W43PDNMuCuo33cSCV0VQyMLSfm7uLhYiKX9/MlU2VWhk/8duSQGd/REqOey64bJ7+1541ooMsNv2GMR93Q8mCuwTx4w10kFZxT9vElP697TJ9shnSutLyLCyeA4POLy8rKq1ara7bYajYYajYYymYyGw6F6vZ5OTk60tLSkZ8+eaWdnJ9I2/X4/FB7D4gJXLBbjHvBYwPNsNqvhcBhxLAojKVhv5og0Cx4dUg2Ij6cB2kuKeBOPmU6n1ev1VCgU4tpwAKPRKGA77PV4PNbZ2Znq9XrE1TwrbDwpt9PTUw2HQ/X7/VAwh8mODBwNOXfiLLTLAMfynC5PQGfmjjVl/t1YJI39VUp51X06WkgqtDulF41rpchMFCOZTuAzaZEAwCJLH61Q8kl2peRavthuWbmP5AQmCRGsvOcYyV8uLS2pUqloY2NDGxsbKpVKKpVKkYPFww0GgxD6VCql4+PjeOZCoRDpJ4SI87daLVUqFZ2cnOjw8FCVSmWBgYUtZh76/X4oFnGw57IHg0EYwXw+H+RYcl75PkUjzrQyFyi4pFAQ98TE8DwveXEKWTiePHAqlVKtVlO321U+nw/mHTQAn+C8hmcikB2XKQ+VMGJJ5IYCu/I5CYsMOBr06z3PGyeNTRI1JuX8RbBaumaKfFVMK2lhIpNwxf/OSCovAwF0S+jX8/u4Kp2BsnJvblySkCqbzarZbOrWrVtqt9uq1+vhcVKplAaDgQ4PD9XpdHR6ehqQmLgX8ieVSkUKCq8JKy1J9Xo90k+tVkv5fF7Hx8eq1+u6deuWMpmM9vb2dHh4GKkmoC9zCXtNnDwYDFQul8NzuuIy3xgLF2hpXsyAZ/c1AzqDHIDonLdYLOr4+DjgN1Cf80GKkZYbj8eRuhqNRpGr9qyDQ+ekUjlx5oaUNfe0Z1I+k8rn5+X/mUwmDKHLcHJwLOdPxuRJo3PVuBaK7LGHQ5lkPOP/dwYQD0UM5gSUM96u/B7rYo3xJElmlIVz5QYOJXOcwM9ms6nXXntNN2/ejJzvwcGBTk9PlU6ndXx8HNVTCBEeDiKI2BdvDJkEYQQj3O/3VS6XdefOHR0fH6tSqeizn/2sarWaOp1OoAMUk9CB5+z3+yFwwF/Wg2owPkOJIbX8uZ1oY7j3QdB5Tq+Qm0wmOjk50XQ61XA4VLVaVb1eV6lUUrFYVKlU0vn5ecBtCLlCoRCpKog71vEqQvQq6CspcuiurMgGzyDNw4mPU2j/e9Kb42DcobgzSDo015PnjWuhyNIixX8VYZC0ej650twrJi2wk1DJvGGySMNTSG4V8YIs4ng8Du/sAgNhVCqVVC6XVSqV4v6Ig3mWXq8X6RuIsFwuF4QWAsszjEaj8GQYlV6vJ+kyn7q+vq6bN2/q5s2bQZzt7OxEzjmfzyudvqwYGw6HAZ1JFR0dHYVCY2AwHi68mUxGxWIxhBSU4dAWg4oSoFik0bh+vV4Pw5JKpdTtdpVOp9XtdsNj+78YENai2WwG497pdMJIQIx5qaeHUUl4zTo7gYkcEBa4cXdDxby4sXJ59tDDP+MYrsN9YCj5zA3Qi8a1UORkXOLDvas/0FXQI8lS+neTMa2fB4/ghIV7maS1TEK0ZDEILHGr1Qqoenx8rL29vfDOGBQquCC1WGiUdzabRWUW8BZCq16vB+t948YNtVotjcdjPX36NHKwKPJkMlGz2VShUIgU0sXFxUL99f7+fngNDAXxaq/Xizh1aWkprk8cj7IRd6O01H0Ph8MF75xOp9XpdAIdgBrIX3sFGQYDUjGdTqtcLms4HKpcLkeRS6vVUqfTiZifGm+H0lcZeIps/HdpsRyTkZQPl12PbZ1c5Xz+HZcv5O8q9JCU9eeNa6HIPpKEQnI4geHKmSynY7JIwfjiXZUbRJj9u77Y0mIRgueZZ7NZwD1g+tramlKpVCjU8fGxer1eVESxuHjEarUauVuYWXKqeGOMCuRXu91WqVTSysqKMpnLDQvE3Ny352VXVlbUaDSUzWbV6/WCNV9bW1O/39ejR4+0vb0djDH3s7e3p/Pzc0lSrVbTjRs3goUHOcxmM52dnS2wy562gps4OzuLNFm3211Ya9AGhBvHQbBxLWJ9nx88dSqVUrlcjnXHqDxv+A4llAlkwd+TXtSJVRST49xYOGr0UJDzeLjh4VnSMLwoNo7n+Ngj/paGw5Kkx+MzrBcwLhlLX+XZHbY8L+5wL+jWkBJAqpskfSSOli5JmkajoclkokKhoK2tLVWrVfX7/fBG5F9ns3lxBWWNQGxiPATg7Ows7h8vXyqVVKlUYgsjhgIoixCWy2VVKpUg1zKZjO7cuaOVlRXlcjl1u92AjTz3pz71Kf33//7fdXJyoq2tLc1mM7Xbbf3P//k/dXh4qOl0qm63q0KhoM3NzTBgk8lE+/v7oVDpdFrLy8sxh9w3ZF6/39fZ2ZlOTk705MmTiI2THhFmm2dqNBrqdrsL5zw/P1en0wnCrFAoaDQaqVAoqNFoLJTaOnqCE/GwyuFtMs5l7ZMOxGUsKXtc63mFR0ll9795iOiFLM8b10aRkxYrqbjS3AIisEnCQZrvOLmKRHCl9fiWyUx6Yve6LCJeV5pb52KxqK2trVAciizY5ZNKpaIMM51Oq9ls6vz8PGLLZKkl98s2QWqw2+22qtVqkF3ATOJZ2G08VzqdVqPRUKVSUbPZ1J07d+IeKIXkHCj0kydPtLu7q1dffVVHR0d68OCBDg8Pg/zp9XqhOGwnxMuOx+NQMK/JXltbizw48fZkMtHOzo4KhYL29vZ0dHSkdDodu6JSqUu2ntBgOp3q2bNnms1mkWZzrz8ej/Xs2bM4tlarqVgsqtVqBTEGMoAc9bprN/YgA98CmoTOyADHcA6HzcihKysymJR3/74bCpfPF41ro8goLTeNwvoE+8MnIQg/7nHdw/tEYPVZNI7l3P43Ko5cySFgSqWSVldX1W631W63Q6kHg4E6nU6khTAcS0tLsZ+YmPH8/FyDwSCql2C9p9OpBoOBZrOZVldXdffu3SCq8Egwz5zbn3E0GqlWq0X5Z7vdVqVS0crKilKplOr1elRFkUO+uLjQa6+9ptdff13ValUPHjzQ/fv3dXR0FMIMaXZ+fh65XHZaZTKZgOUIcj6fD4ILQo/S1Js3b6rVaunevXt6/PixTk5OIt4mnAANQQDm8/lYHwwYXq9QKESarVgsxhpBJhK/s5c5KUPIBs/CWuORnYRCPpg/iL0kJ3NVfJu8FvKXdDzIfJJIu2pcG0Vm8pIKB6zgodz7+kK4R3Wozb8el/I5lvkqAssJEM8Fksus1WpaXl7W7du31Ww2lc/ndX5+rl6vp9PT0/AWxM7ATJRnMpmo0+lEPExOtVKpqNVqRX31bDZTrVbTrVu3NJvNQuFOT0/Do6PwzFO/3w+IyV5hcq+lUinSP91uV8fHx0EKTSYTra+vK5VKaW1tTaurq/rwww/1zjvvxLbHmzdvam1tTZ1OJ1h1YkRgNsUuuVwuDAn3500Rms1mzHMul9PBwYGOj4+jLvzk5CQgMwrpNeMw/BjjZrMZBi6dvtwbvbS0pEajoXw+r4ODg4U6AmQoKYcM1t1lw+WAeJ65czlNEqCgOklB3BH/u9y5XLuHfx4ZzLg2iox3kuYT59aIARx2WO0WC5hDPjnJSBMbpdPpKEHk+g61EU6GpxDq9bpWVla0sbERcBcvfHR0FDuVqOzK5/OSLmPi0WgUEBq4B4Ss1+taXl5Wo9HQBx98EN6ZyjA2G6RSqfg+sJZUkbS4symTyaharapWq6lcLsecbG9v65133tGzZ88kSa1WS81mU8vLyxoOhzo4ONDy8rLu3LmjT3/60yoUCqrX68FakzbjeoQB3Id7rmKxGJ4UDw7EX15e1t//+39fr7zyiu7fv6+nT59GeSq7oZhL1t+JKLw3MfBsdrk1Eh6CDR6rq6tRBgqR5rKWzHa40knz/eQuezgQ31yBDKGsToi5E3JSl4Ibru3K7c7nRez1tVHkJLzxckoP9nnQJDlyFXWf/MwtJQotLVZ8udJzLWdAC4WCarWaNjc31W63lc/n1e124+fs7CzO6ft6qSsGQoMG8Nikq9bW1sLQwEzfuXMnqsPwyu12W4PBQPfu3VsIPdwrSHM0UiqVNJtdppG2t7f1n//zf47YV1KUOqZSKTUajWhQ8Oqrr+of/sN/KElaX1/XYDDQ3t5e7CcmjUVcy/lg4yWFF5YUxgtksLS0pNXVVZVKJaVSKbXbbe3u7urw8FAnJychEyCZwWCwcG6ez/uJkaPnnMSx8Av9fj+KcJytlua7u5JymSTikoy0b/DxjIjDYZcrP7fv0HJl9eOT4WFyXEtFlhZjC2KuJOyWFMqJJUQpsdAuXJ4ndgvIRHmrF7egLFKhUNDa2ppWVlbUbDZj4wFbDc/OzmIH0+rqauRsp9NpQGA2SVQqlYjd2ERRqVSiDpk0UT6f1/LyslqtliRFgQaQ8eDgQJ1OZyHelxbz5bDjs9lMu7u7+rM/+zPt7u4uhAzEweVyORjns7MzVSoVfeYzn9F3v/vdKLqgACMZB1LQQWkp3oZctZN+jpwIQfL5vPb29sII8ryk5MhlExt7lRcMP8U6yEYmk4lNHLPZTMvLy6FsbBV12XI224lPRjI19Dz0yN+9HttRpMfS/juy6XILwrr20Job9Jwi3phJ9sR+Mn64ykq6F/a0gjQv/Hcv5hb0KvgEXCI2LpVKmk6nOjw8VLfbVafTCUFHWLD6knR6ehoxMuz28vJytPAhb5vL5XTjxg3dvHlT9+7di3PjxRAI4lHgOxv9fQ7H47FKpZImk8v9zdlsVn/1V3+lnZ2d4AYGg0HsSz48PFSj0dBnPvMZZTKZUB6UsVgs6s6dOzo5OYmcNQYU5ITxkhQsOtskEcZnz57p4OAgFJhwBkO8vr4e0DuVSml3d1fSvMIOpfXYFANOZgEFBSlQgebejWtSauqy6F7YIbd7W4fdrqR+vPTRFkGurHzfDYM3n3Qm+9orMiNp+ZI3nySrpMVN3snvo3xJq+f7TJOW1ReCBSKebjQa2tra0vr6unK5nM7OzmLjA3XPeB7uF2+BwLFlr1wua2NjI4Quk7lsVvfqq69qY2NDe3t7Oj4+lqSIAREM9gAfHR0FjERhgJCEBEtLSzo5OVGj0dCTJ0/0/vvvh8BTjok3gU3vdrtqNBoR06PQ7OB6+PBhzImTkFSe8XxUZVFBdnh4GKmps7OzUBJXrFQqFTH9nTt3orjj7Ows8s9cZzKZhKEpFoshB96EkDQdsTRefGVlRePxWAcHB0H+JWWL35/3Gc7G0aOHhC5zV53LU1QeO7tsukN50bgWinxVIJ9kFZOQxWGzWzeOSaasnIhIsuMYDTcKLAixGLuJXnnlFUmXkO/09DQ6d9DOhta0wFasfblc1sXFharVqpaXlwNad7tdlUolvfbaa3rllVe0ubkZcSjFG2wMIDYcjUY6PT3V7u5uKK+n7yRFKgxmuVqt6i/+4i/CczvbjcfCS5+engZSKBQK2t/fV71e1+rqqk5OThZ6fSGwGNnBYBAKPhwOdXJyEn/r9XphFIhnk/2ts9msTk9PdXh4qDt37mhtbU3j8Tium8vl1Ol0QjH7/X4gL9r4YpxIX4HaSqWSxuOxRqORMplMtAQmd+3VVdK8ACQpkwxgc7LJBDLliuuErMtyEmo7MvTwLmlMkuNaKLK0uIPJFZW/SfP4JGmtrlJahyfukZ1B9O8lIQywKZ1Oq91u61Of+lRA6vPzcx0eHmp7ezs8hffeKpVKUfgPISQpKrBWVlaCvS6Xy7p9+7Y2Nze1tLSk+/fvR3oFb4QykqJinJ6eRq4ziShSqXlXkk9/+tM6PDzUhx9+qFQqtcDwkm9lnjASP/mTPxmCT8vabDarx48fazKZ96hGIZMpPHLHZ2dnUV1WKBRCmXO5nE5PTyNvzDnJjVNMs7GxEUUxlKHW6/Xon+0MNsazUChEFgTFZUtltVqNgh1a+DoMd1LVZdNhtiukf+ZhGAMj56mm53FBHhMzpz63L1Lma6PIz4PHSc/J4HOUnwlLenf/v8csCK6XNaIQbG7P5XJaXl7WK6+8EoSUpNhCyPY5GsVz75RZ+mYAdihtbGxEDjmfz2tzc1PFYlHvvfeeZrOZRqNRKJd0CaNBBTCuz549i5gcAsh3ZLGfeDabRSHIt7/9bT158mRhBxIIAQSCwvjcegoJAoxuHx7DgV6Gw2HkgkEE5L4JA1A0ykzx3lSGpVKXPbr39vZ048YN3b59WycnJ/rggw/ivhyBOOuLweP/zJkkVSqVkAOv3W40GpEyo/ILOXH+xjkX6aN1DMS37qGTSDGpjM8j1CiEceP4YxEjX1XsgbK5pUo+sHtk90oYAU8xOPTkMyaM83jlz3g8Vjqdjk4c1CjDTqM4LDxewxc7nb5sx7O2thZ52r29PaXT6ahXfvToUSgxi+0bAyg22d7e1s7Ojo6Pj1WtVmM+6DKZnDc81NOnT7W7uxse1D0sc0487+FHuVxWv9/XZDJRq9UK9EJWQFIo6WQyCY82m80ip81OLY7nOAwV6StvAUSu9/T0VOPxWCsrK0EGHhwcRPcTJ7xACMB6r8ZDmVEQDCsFMrxL6eLiIniJpJz5cMjrSp/kdfx33yLrGQWXY9b+ebXVPxbpJ+mjN5rMxTkT7f93uOlxTpJs8FgSwXVCy+NoJ7io3EJgd3d3Y5cPXSy8LpvNA/l8Prx1rVbT+vq6arWaDg4O1Gw2FzwEzfXy+fyCkmEUxuOxHj58GG1naehOMYgbDo97JenDDz+MGNP36SZZfhTd/wV6cgxK49fDkwGR+QzIytz7hhNPFVKaCoogHCEPjBJWq9XgKDKZy73f5IS5Ly87RREwJG60mWfWGLhPnH2VB0zKJ8+S5G3c8ybjbhhrJ145j2dYPKXKcDlPjmujyA5hGEwOk89xyYlyeMMiei7wKjbb01lY9nQ6HV54NrssjVxdXQ34PRgMtL+/r5OTE52dnalQKERvaqq7IJCw9nhWcpnT6TSqrNwLs8+YZ6OSisokctDMD4UVzBPsMHE0RBQVZ6RsmB+u7XlpIClKQg12Op1WqVSKXK+3pcVg4IXpqsE8o2TEsAgjRBKbLxBknqPRaKherwdDDWG3tbWlpaWlYOz7/b6Oj48DJVAeCwlGrTdzwb3RJZSy0UqlotXVVV1cXCw0gEjKncsS9/siVhv5JSXnBJfLPp7a1xNF9lj5eeMTfz/yjzrcI/Jg7nEQ0GT8kCQnpHn6JzmxwE4nv/CoeItKpaKtrS21Wi3lcrlgqUkzUYKHwrKdMJvNRr43l8uFV55MJnr69KmePHmiTCajV199VbVaLfpveQeQfr8fxQq+gd+rmfCaXgqIQgBRMQDE8tw3QsMPhJoTjqAPKr7K5bI2NzdVq9UWyENnx5O11u5V8ELAaN/pxXoj3PV6Xc1mMxh6DA3KDEHmGYuTkxPt7u5GiSyhB4YFZWVOMCR0GW00Gmq1WqrVaiFb/OuhHaWLTBcAACAASURBVHOP3CTDP+cNXD7512VN+ijqRHb5f/L3542PVeTf/d3f1e7urv7iL/4iPms2m/r617+u999/X1//+teDBJKk3/7t39a9e/f07rvv6vXXX/+408e4ynP6hLjn9WOdgZY+yp66kgNrpHmPJs4NNEunL3cS1ev1eOsgHT4ODw8jbkNhvcgAb1wul0NIYH07nY4ODg5CaUulktbW1qIjBoKJ8Pf7fW1vb0dXEV4jgwLTzoZ9xRcXF8HSMids7dvb2wsI6kqGUIEsHMGgxJQsplKX1Wq3bt2Kem+QTDabVaVSUbVaVaPRUK1WkzSHjV5Dz3zj8YHgwGlSc+yyIhX3V3/1V/re976nd955R++++27ksn3rJpsquKanoChWcZLNc74U+6yursbzOSz2uJZ18lDMZZdQyz2pH+MQGjnlc5dVZJ6/uwFIjo9V5H/37/6d/vE//scLn7311lv6xje+oU9/+tP6xje+obfeekuS9Mu//Mu6e/eu7t69q6985Sv6nd/5nY87fQwm1G886WVdMf2BnVTwiU2SOL7dzFNaDiklxUvTyPVKl6meTqcTlrxYLAYBRjqHiQZGU5AymVzunUXIU6mUHj9+rNlspo2NjRAQiB+IobOzMz1+/FgPHz7U2tpalGmi7BgZILcLHt6MVrmnp6cBb1Gaer1+KQTpeWWVM7fdbjfmg/ve2trS5z//+Wie4Omr2WwWjQ+ofHNFgu2mNxjIgIINdjhR1HF6eqrt7W299957+sEPfqCdnR1tb29H0Uuz2dTt27f18z//8/qlX/ol/cIv/IJ+6qd+Srdv3w5DCmkJ9EdZRqORjo6OoglBLpeLTSG+K8vZcZSPrZrJHG8yrk46Jo+TfU89a4nMeNiIHLvXv2p8bIz83/7bf9OtW7cWPnvzzTf1hS98QZL0e7/3e/rmN7+pt956S2+++aZ+//d/X5L0rW99S41GQ+vr67HD5kWDh3TL51sMgWcInLPFXh2EN3HBduMgXRoI6qdZVM+9FovFaKODt8MLTqfTeCsii+2b/CVFJRVb6mazWexZxuufnp6qVCrpzp07Ojw8jDmi4goPMh6P9d5778Ve4sePH0fzOknx8jaUM52ev7KFXUSwyXh/2HWOl7QQWlSrVT19+lSZTEY//dM/veDdm82mtra21G639d3vfldHR0dBxkGmpdNp1Wo1TSaTeKPjcDiM+ZQUWxCl+bY+lGo6ner4+DgIKeJsSQGPue9qtar19XVNp9NIJ4EmYNwx9CAPFBpYTbqQhoCtViuMn6NAZMk9Z5L0c2dDDO6lxig++Xcn5ZzERZ6TZNnzxl+L7FpbWwvBe/bsmdbW1iRJm5ubevz4cRy3vb2tzc3NKxX5y1/+sr7yla9IunzptjSn5rHWbpF88VzpJS14abd6SZLMoToC5aQC1UHtdjvKMCkn9HSTv7KUyipiRLywx/mUNjrxw+6ffr+vW7du6eTkJDYdEMfxPBcXF/re976nn/7pn9bm5mbEl6ADSisRHHLgeCT6PksKVMK8odTA/fX1deXzeX3rW9/SG2+8EWw9O7dqtZqePHkSfbzwupSfYkim02nsNgKVOKrytcWgEN87uw48JlbmXzy8pOgGgkHgb2z1ZF93KpUKJhzYz1sggdTwHR7qJMswkb3kc3l9AgjzKtbaDYMTZsmQ0GXWz3HV+ERY6xe5/OeNt99+W2+//bYk6Z133vlIHs5jELyax2UQO76LySfJJ0pSePdkLI0xgNnEG3M8EIztiXgM95wI5cXFRezXnUwm0QVDmsfAEDwYh7OzM62urmp9fV2PHz9euC5KIEmdTkf7+/u6/f8XRzx58iTmg+d0pUVhXQlSqVRsqyR8oAtlqVRSq9VSo9HQ2dmZtra29LM/+7OazWbRdrdYLGp3d1cPHjzQvXv3FjgADBiKyZ5sSdHEzwUVIU8SRV7Ywv8pegF6SvP4G6RCN5bZ7LIV0M2bN9Xr9SJ1dnFx2fSfRg7uqSEaua+tra1oaoARcAfDvSczIxB67nykj2ZafLhsu5FLEmYeDl41/lqKvLu7G5B5fX1de3t7kqSdnR3duHEjjtva2tLOzs7Hni9JnLgiOvnica+0+FYD8pL+sEnY43GOKwy/53K5eL2pvzys1+sFFKQUk1pfIDZFEzSnv3v3rlqtVhBFbN2DET49PZU0L0LY2NiIflhAUUgiBPjBgweq1+v63Oc+p3Q6HT2siP+A+JJiMz5hBPfBXEH4SIp3Uq2vr2t1dTXqnGu1Wgg43v309FQHBwexp5r3RHnemLXytj2sq+ftC4VCvOQtnU6rWq0Gq02mwNM2oA9J0e5oeXk5Nj4wB4eHh1paWtIrr7wSc4qh9hw24QD3SmxP3Tlr6y2FWDNk0JUOpXQOJ5ltcWclLb7VhPNxvPMWHwet/1rppz/6oz/Sl770JUnSl770JX3ta1+Lz7/4xS9Kkt544w11Op0fKj5meB4tlZqX2nlsIS2ye0yis7BMbjLmcOILhXJvkM1mg4Gn2IK00mw20/r6erzDmLiQ2IwSzvX1df3sz/6sNjc3Y0M9W/tOTk50cHCgg4MDDYfDeFXM6empzs/P1W63YwF9myHPOhqNIn31Ez/xE6pWq7Elkny1NO+KgZL5WyuIA2lksLKyojt37ujVV19VKpXS3t6eTk5OIhePR6PXF+14iPXxTBBYzDmedDKZRLkmA0WhrDWdTscbKtl4QvxKYQowllRasVjUzZs3lU6n9fjxY/3gBz+I/O94PFan01Gz2dTGxkZ0XXE5oN2QpGh3xPpMp9PYb069e7KRgactkxA4GRIyMOTO7Ti5ldwfwPUwPD9SQch/+A//QV/4whe0vLysx48f61/9q3+l3/qt39If/MEf6Dd+4zf08OFD/eqv/qok6Y//+I/1K7/yK7p//776/b5+/dd//eNOvzB8krwGOgm1PRby8kqs1lVEmKehkgouKZSR9AdKxCKjpMBFIKV0Cbfp4PH5z39e9Xo9LDivR02lUgsQHehM+ur4+Dha1Mxms1B+mF48+v7+vp49e6a/9/f+no6OjvT+++8vPINDfc8d44FokMB7ouAnvvvd78YaULSCB8xms/qJn/gJjcdjbW9vh4FAyTA2KHSlUglFTr5ulfRXo9GIuLjVaunWrVsajUYLDQuA2h7XFwqF6OXNNkTqz0EkxL5s2FhfX9fh4aGOj4/j3NwPWQteP1OpVKLme3V1NYgpzwx4kQayxP89bEiyzfwNmXU5RHk9G4P8eoHT88bHKvKv/dqvXfn5L/7iL175+Ve/+tWPO+VHxmw2T+z7g0nziUr+DhPoSpu0dHzmSn7VRMHUvvLKK9HbqdPpxF7jQqGgjY0NSVrYKQMcvHHjhtrttu7evavNzc1QoocPHy4QLiwqLDJpGxhb0jlANyeTzs7Ooq3Q97///dhS+fDhw9hCyWYIJwZBKGzGwCsfHBxIkh4/fhxFE/xbLBb1+PFjlctl3bhxI3Yq0fweqCzNt0vSlof7ZT1dsfDi3kJ2Op0GCvJuHc5tENMy31R87e7uRnownU7r7OwsarNrtVr02i6Xy0GInZycLJTD0l2TdTk6Ooqqutu3b2s6nerk5CTuAV7mKpjsTiPpKJJcD0qN/HuBjcfHcAUfx0NdmxJNnwSPO5Isp3tojkdYEQAXZGmx0ovJcUOQSi32nZ5MJvHWhH6/r5WVlajWarVa2tvbi3geeLi5uak7d+7E+4OJ24izqfX1BYQ9560P5GEpGvEOFCjFbDaL9zrdvn07YLSjFogZYndJwcBnMpl4basLI56H7x0fH+vhw4cql8sBO2mQgOHxSrBqtRrEmleGcf/ebggPPZlMotHAkydPopEgxohBNoD19pQRmYZsNqtarRYdW8rlcuz3ns0uS2ar1WrAf7qC4vFhx7l+rVZTq9XS0dGRGo2Ger3egkFBLpNz6NmSJDx2pJGMe5FHdzxJgutvnLX+JAYKJi32RfIYFsjiDLbDF1fgq2C3W0MGgkV/6tns8tUnEDoICVvhENZer6dms6n19XXdunVLd+/ejRwnrXDoWc13HJoRyxFDSor6bYTBU2NnZ2eh6LPZTAcHB/GmRwgh4BesNF4db44BwUDgIYHg5Fqn0+lCw/xMJhNbN1krjB/EFHMK48yawWIjyJBmeJrRaKTDw8MFAyEt9rhyxpgOIcThMPNepEHXkGazGWk/+A5qtL2eHDRD4Q6vdoW4XF1djXx5kqhyOXOZdXl2ApDnxvC6/Lsj4jP/+4vGtVFkaR5DeEUN3Rz4m3sehsMYt5bJ8+JtPWUwm83UbDZVr9c1nU7V6/V0dHQUm/ap3oLdpnc1RQ+f+tSn9JnPfEbLy8txz2x6B8Y5ciA2gkUGYrv3pHkBsBTISJ65WCzq7OxMZ2dnQYIkSSEYeeaHNArezXP1KALzRkscYl7f4VUoFELxuQ4KwQ8K6rl5sgIIq793mWo2T9/gLX3ThDP06XQ60Egmk4nKuc3NzWCtQTeEOnQrQcacczk/Pw/jwLG5XE7NZlPD4XDh/VeeLUEBPV9MqAhn4c7GQztXWOTCnVly/Ehk19/WQEHdivF5kll2CC599AXTfrzH3MnYBmGAnSQ2Pjs7iz2z7XY7oDgCKCla17ZarYVumd1uV48ePdLR0dECFHNvLC2mGSh+8PptmuWRQ3UhQEnp2OnnRlCd9SZN5Ay/CzHGwNEMCjKdXrb+YdcT8aQTaBiCTCYTjfE5hvM57GctMCgQiNQHkGLyzfXAdRoU+jHO2Ofz+djFBIQHCTSbzYDSlGem0+mY81Rq3i9cUhByvKmDF/G5AiIXvs7MrRNhrJMro3M3LutuIPgcWXneuDaKLC12CeHmEUiHbq640mKXBQQ6mU/22MaLT9rtdqQniJFOTk6CUb64uFClUol41hW83W6Hh8bAPHjwIIoJUAhgKzAaGIfS0XY2nU4vxHeQPzDE/h1YcLbmMVcoDIwv3holB5ay7dJ7ZnktOnlah894eMICadFLkLf2F9Fxrx7nA6/9Hr2N0Wx2uYU0l8vFXmT33hBHpNRQbOYGDwsaaLVaSqVSsb1xMpnELi6ez8k7jB/EF11E6HbiUBoDflX2BLl1B5Vksn2OktxQUjd+JNb6b2M8L54g1ksyzlh1j6M4z1XxcnKCOZYCj1qtFnCIhabkj2sQZ9F+ltivXC5H/Eq3x2T5HooBTJbm6Q88IVVcxOVYevYpn5+fR3zM3JycnCx4bC8BJSSR5rXVzEexWFzo+Mmcs/3PNxFIitjRITtxuedXKX/03tJcEyhPTtlzo15Tz/OBADxs8HVkbijg8I0RvAeaWJi3V0KmsTadTidelO67pjC0EF2VSiVehMdae6oomeL03DBGiPV0R8LfkW3nfFwnOO7aK7K0mEP2yi232MlGbw45eHCHcNJiZZj/TpoFuEz/aCBxNnv5zmKsOdsXiTMpb2TwWlWvf+b+EQw6WiC4vV4vtuGlUpcpmkqlEm9n5HteFMJAIFFyjAVC7dATI0I1FdyDQ890Oh1IoFQqRQdN8tiz2Wyheybe1xEU2x7J9fIic4eV3APelHV2Acd7Eg44EgCuIwO07iEehanmGelSynuhWMPj4+OAynhynp1wYTKZRFzNFsterxcVdcmqq6SSJv92lexeddxVaSwnwa4a10KRXRG9zM33X7oH5nevoGGBgTvJ1IBPFAJINdbp6WkQRygQVVlLS0vhRb0We3V1NdjklZWVgH6UdsJWc00EwxsaAHeJySRFqSFxs6dPsNDE3rz5ka2MXCdp1XkeNnuMx+PIKTtr7tDaY2TIJdJ8xJnkrSGzqARzb4Jg4vFYR/fCeGCMOegHxELPbmTD0RYsP4au2+1GdRiekB7auVwuOJDJZLJQdANzLV1uwkAmlpaWwggsLy+r2+1GG2RHgq5wyVAP+V5aWgqj5FD5KpbanxOv/mPhkb2YQ1p8gyIxmbPXfoy0mArw6hmHbF5kkMlkVKvVtLa2pvPzc33ve9+LdI1bZu8Bxc4oiB7IjouLCx0eHi7klWFUgcS+FY+ST2JESSHMdKnkufg/1+L5aUaHkfGQwsk9jvd92B6T0uKHOBpFI6+OMkFKOXIixmQ+OI8LqyOkJGHnZFEyrUPsycYM5t8Za46lyAQewftZw2tIiv7g/opX1hcjjCMgrp1MJlH1xcYSUotJyM9wxfaY13kF/9wJWQ+dkHH+dUVPjmujyEmGWfpoZ0K3dgy8BIvmist5IYG8soYYkC4gtVpN29vbmk7n+1ZrtZrS6XTA13w+H32rSqWSXn311QUvRcwGhC4WiwvFGXh7Z69RCKqhgLPSvN6bXGeSGyBuRdldWYmRga88Rzqdjpa3DtUwYvydz9jEwVxjfHwnkL/HmPlFEZJkmysyg/nD+OHZUWSq0gh5QAeESLDynBMC0l/21u/3Y/2oQkNuINUweDRdoCiI0k0qvhqNRtSbO9l3FXHFcN4H/gAj6yFZksfx87ixSI5ro8heVOCUPdbOrTt/c8+DorJwbt2SbHgqlYoOH/47DCbN9FKpVBT+4+VHo5Fu3bqlz33uc6pWq7E3l8WgQ4ZDbKClpChgIP4l3vSeXXgXYlueBxKKmBgFZqeUs9fO4GPAnHhCgDEihCbMIfd0cHAQAs5cuVHAy3AengnYjcfGEHouGaPrDeXhI1gvZ7hRXFcYYmj+RpjBPXIsbwTxnDd7wrl/1hl0cXFxEaW6dELFwNOOF9gOuvA54rzS4k487s35Gk9RuiPjHO6crhrXRpGZRM81Mlyxk0lxFoC/8z1P2uM9pHkReqVSid5SZ2dn0YmR9qh4gNlsFnHX0tKS7ty5o9dff10rKyv6y7/8Sz169CiUMJfL6ejoKCA2O2z8Naps0geWgSQgYlxogdsXFxfxsjU8scNI4K+TfMxBkhAkzr8q7ECZgaoUxnhTAgpIrppvPAzxLYgET4+353sYWxQO5aeYwo0RWzEhywgNptNp5Hsxbq4s3B89wIh5KVOtVqvBj4AiyBoAyylRpeMLe7Z5MV+SiLrq/x4rM9xBOULw//va/VjEyK6sTIxvY3QrjPI6xPZ8pccdPnF+fL1eV7vdlqTYRohCSfP6YCqDcrmcXn31VX3+85/XjRs39ODBg9iwgHIAj+j8cX5+rnK5rGazqen0svhemrerIV/pL1+jygm453E9tdAor5NSCB9emtgX5cWz+UYN5hG04J+Nx2Otr69rf38/UjXSfEeSpDAmDgExNKwjSIJ1gGQiTs1kMsEyS1rYOw3Jx+fE5HTtpOrOt0wyB75vGXRB+ENnU1BKPp+PnDz5cw/B0um0dnd3I6SqVCpRc09RjrTI2Tjr7DKOsfAwyPkC98qcI5lmvWpcG0V2D5q0QJAdWG+31Ek222GNw2mHKbnc5fuXisVieBx2J/n+09FoFA0A2u129Koaj8d68OBB7NVFmTEiCAhVQoPBQK1WK941JCk8k+8a8iISFhxvBumCZ2EwX8SRpHgctvlmDWdpuU9P7TknQLNBXxe8McKIQeVc/gwYEl8jJw/dS3Ndaf4eJwwjysi8AfPZluhpMe4VRWEuqDpDmWlRjIL7DqhCoRDvvqbKrtfraWdnJ97kyLbX4+PjINOSipfkITgmSew5LHco7kjTSd6rxrVQZH8QaV7wAdT1ZPpVlD8CyiTwO1DWj0un01GSKV16Y2A18RMKsL+/H+ep1+s6PT2NtFCn01lItaAIw+Ew3iCB0NOcgBQQe5A5t0PNyWSykF/FI3j6BwKMmBIG1ktQvV6djfpAdQwE8+GMN/dDPMv5UFj/DtcGSmNsmD/P/yPYXuXmBR2gCF+75ECZB4PBQmM9f27y0yAcngfyDxlDeUEYzKEjKRQHoi6bzerk5CSqzqgogwdxY+JstnMKSQV2HcCQcZ/OP/xYQGv3wP5w7imkxW6ZTJQXvLsQS4p/pfm+5EwmE501pEsloxUMr4ah8slrcSuVitbX19VsNrW3txfsM9fz9M3R0VHcCyWZPCPKjbGigMFjVFcsNlAg3JBgpMm4BwpN3OAhHJSQovxsiADCeiwNMgLue4XYbDaLmJ2Oop4igsV1PgIDgCG6uLjsiNJsNmPeIBKBzygDz4onx2N6DhleAWXBGGEAQVxe2Yayb2xsqNvtRjEQO6S63a4ymUxUqhG6sOagNOJzOIvnpYqc23Hy1VNNKC1/c5bfw8vnjWuhyNJHk+IODZOEFsfjqZ2i57OrSAPiQdrvQGKQ9oGZZLMChBQs9Pr6etTbUigC5EfxMQLcCwtDDI4Hg4RjkfAcwHriQRhZvLQLP57ShZR5YQeTK/d0Og2Cz5XLQxP38qAclAmDIc03biBwvi7T6WUHTTxjUjglRc/sbDYb7DaGh2PxpFTgSYvvmnJvhwIj/JSRcj5kgusl0Q5OwxlkcuIcAz/BbrTl5WUVi0Xt7+/HmiKLKKATYTy7k5msPWvisu9h5I9NHln6aD8kz70lf66i+FF4FgyFcA9RLBa1ubmpZrOpp0+f6vDwUKPRSO12OxrIJ5sA4AGx3MBS4A+eF0YaISAdAlyG4KGc0Ku/crlcVBoRH1KR5WQHUNAViNJEBB8hRcH9rRp8hsB66g7POB6Po7JpNpvp8PBwYWMIMa+nyZy8wqh53hdj5t/juSGeQFBAcHpzsYbT6TQq3FwuPDVGGtDRAPIENEfWUCKMLwgIqI7MSIrGCYQ19Xo92j+zti67Lp88E1A7aYCTf3OZZvBszxvXRpFZCN9sICmqb7ykz62eM9QssMOWJGEAY0mxA50fJEVukTctIhScp9frRf9pyA7axuC5JYUlxyNIirRKJpOJ+Nw5AUnBmnLvsL3MBwLqDK40b3ZAQYW0uFEC74rnYysghS/eywtDOBgM9OzZMw2Hw2CEqQNH+WezWaTNkqW1zBckE+Qa8Jq1RYERbIwhx2AsPY/vnt0LMDxzAdR1gk3SwjuZkTe8OP20gfC0COJ8HsKxJzyfz6tWq0VszcA7e2zrTiXJQidJ2iRb/SJvLF0jRZa04OE8xnMWNplz80lKxtksOt/LZDLR7vbi4kJHR0fq9/sqFArRNdE3PRB3SgrvSjH/YDCINwbSz4pUBMJKCkiaewAYYawyCulxobPJeCdno/18Djn5nPRRch7YiudxmqfrCCVg7vG21CETy3M9Z4e9YQEGzJUbQwMKcIMLgoAI86yEk5p811lveAavOuM8Phd8h1CB7qMUo6TT6cjv06Ce56NFEM/S7/cDRaDse3t74SxcBt1Ye6qJtXIF9jUDJXEc8vC8ca0UWZrHyk4OJC2XK7rT9zwwkwHkYpDTJb7d39+PBfYXgPm7ier1egh1v98PL453azabajQaQZrwJkXgNjHuZHK5FbBcLkcO2J/Ra655Xk+/cLx/D+HwtIrDNWmegnODguEgPYSRm0wmC+9fIjaHHCuVSmEAvOwVg4v3BZJ7SgXFdITksbMrijP6PAtKhVen0b6vM+iKOfRm/WzJ9HQW/cuB/SAUUApGmR1qk8n8xXYgjmKxGG+o8LDGDYnPBT/MgcfLvinESUP+73qQHNdGkR1KeOpI+ujb7JJEgRMDruBMBMeTyE+lUtrf39fx8bHS6XRsoJ/N5uV+MLEeU8IAo3SkooCOeHXaBmG9J5NJxM4IrYcF0mLZpLOU7vU8rEDogc3SXKCdxEkKvsM1BBZ4iSBTh46i8nJ2NwiUkmJUMAqORCgMkbQgmO6ROB8ohbkAiSWbIpA24jpuDJABvCrncLaeNYEHYO0wzvAPvjGG+aTNrxshEAFNJq6KbVlr8uPMh//NU6heZZZ0Ws8b10KRPcD39IMTDknBT1o6J2oceuNxgFPNZlOVSkVHR0fRB5lXlpZKJU0mk4iBDw8P4z5KpZIkRfcQ91qDwUAnJydBemBdiZnwNsm+0wgaMRcL5buWUFSe0ftwAWEp8PC5GQwGwdD7e5E8ZnbuAcKMbhhra2vqdDoL3gLyCa/uTR8QetYFw4F3lRSIAUIJRhol9BQM6wlaIgzgfk9OTsLwEBKw8cJr1v3dVWQmQDB42OSbPSj0SRKApC5Ho8s+1/V6fYEXcDQFXPYiDq9pwDAn54h15f8Ov6+9R3b4lUrNtwCiKF4p4zuYHHI46+dEGIoIBKpUKup0OpFG4b2+tH2F8ICooYEA8BeriSUul8shhLCa3LukEE68sO8c8s0KnjNFiYGF0mKuHZTAj+8akhTKQkkhnhOhYj8ygzgPxf7c5z6nra0tffvb345NAo8ePQrv7ftqgZnSvEYb5cFAIIAUWmBo8J54SISctbxKTvw5UCgMGkad3WIQpUBjjnXlQEm9YIRjj46OwgASPrE5BZQFf0Hu2tN9zI8rr+fkpXl7JsIbZN2NWvK7V41ro8gONRyCoYyS4kERHCaDhUfxk3Q+RR1ra2uq1Wo6OjoKJeJ9P2ztI16CuCKOIk/ofbR8zy4F/5JCsZNpkmTOkJprvEMqlQrSyFNv7D3285DmwROTpyYE8JiMuXNPV6lUgqVvtVq6e/eu/vf//t+q1+t67bXXoixRku7evRtIhfz6wcFBsOxJb+HhDt5WUhyL0lJuyY/3DxuNRvHmDeYSA8J+cZCBNM8K0FAAQ8mcOSLhXt2DElqdnp4qnU7HdtJutxuVccgB7L3nxhuNRqA8ZNBDQ66FZ3cnhfJ6yOE//t3njY9999PW1pb+63/9r/rLv/xL/Z//83/0z/7ZP5MkNZtNff3rX9f777+vr3/96/G2AEn67d/+bd27d0/vvvuuXn/99Y+7RCwyk+uw2NML7nWYIGerpXnswYS4sOBZh8NhFCSkUqnwusTP5DCly1e+ei2wN0bnnHh7oB7N0CnsRwjdO3qLWWleX0w6C0sOAgH6EmakUqmA4wgx98nC45WkOVzn5e00Gdzd3dWzZ8/0/vvv65vf/KYkRWM6kAPxPS1/2WCQzNG7BRis4wAAIABJREFUB4adl+Z15aQWWQ/CEtYSowvaYZcT7LIzt77tkvi+0WhE2g3kwPP6dT2cIEPBubkWJBjIges76UV3FpSZsk6v9HPj6Xl/L9JxD45MugHm/1ehFMbHeuSLiwv9i3/xL/Sd73xHlUpF77zzjv7Lf/kv+qf/9J/qG9/4hv71v/7X+s3f/E299dZbeuutt/TLv/zLunv3ru7evas33nhDv/M7v6Of//mff+E1HAqjtK6wyQdgARAMr5jxeFqab7igz9ZwONTOzk5skvAOGXxG50ZiRbwtzduc7JpMJtra2tLFxYX29vai6sfb9wAhPVfqVWnAc5TZY2leA+pGzCEowk/xCHlQSQv7dPGGbDDAq89mMz19+lQnJyeq1+saDAb6zne+Ez2thsOh3n333diU/+zZs3gOBIxwAmElRi2XywslmDwHa+UVatL8bRi+zqAc0mbA9slkEooD6VQoFGIOuT+8crFYjHVFdhyF4TRarZay2ay63a62t7cDnrN+cAOSgjfp9Xqq1+tqNps6ODiI8MnrGdzrJp1NkvhCB9A/zy8/b3ysIj979izeqNjtdvXee+9pc3NTb775pr7whS9Ikn7v935P3/zmN/XWW2/pzTff1O///u9Lkr71rW/Fy89e9FZG4k+EEq8CxPS6Zh/JOBQvgtX1OIT3KlE8wX5ZWvfwZoXRaBTehvdAIQBe25vJZOKVnRsbG/GOY14mxuaBwWAQjC9xIwLOzibiLJSRZ3MFZDGpouJYBHs2m7/HmGO837SXg5K79o4go9FIN2/eVCaT0Q9+8APV63WlUpeb/Pf29qIABiSBEQNC8mykfTwV6CQV6R0/lhQa8BGYPRwOY0shSuSKWCgUFopAMJiei4cI8/JN7gVeAig9mUxCTnZ3d6PQA/YdBMQa8ZI4R03IHLyF542Rdf+dkVRgzsWP9Al2CLl165Zef/11fetb39La2loo57Nnz7S2tiZJUbbG2N7e1ubm5gsVmUlwK+SL46mnJIPtCwmMccIIIaFe+uzsLMoy8Xzj8Ti8LT2dGo2GNjY2IieKhcXiI4Tb29vq9XqxxbFYLKrVaml3dzcMgjPcxLx4BCCYd4wEcvOMGA++569B8dxjLpeLrY4YHVIixMiSIrxg7vFg/X4/UjLMNw36yclyr8nyRwwH60CIgPfCiPIsFFngERle+MIGC9/dhVHwXl5u+CHkvKpOmtd0c1/Mg88J4Uin09GTJ09Ur9ejPxfzzjUymcvKQOA416JRgeeHmWeGy4IrO8ci99yXI7DnjR9akcvlsv7wD/9Q//yf//No+ObjRRe5anz5y1/WV77yFUmKV3uimF44n4TKwDq3UleRFx4z09YH78r9VqtV9ft9HR4ehvCRo7x9+7Y2NzdjTy5k12w2iyov4riDgwOdnZ2FZV9eXg6vk81edpTIZrOxE4dzOITGM3rbHmIt4DFkDznUyWSyUH1FTttjTe7LG7l7KxyHl2ywJ11FbJv0Dg4N8XLE6cwRcBpUheKxRpBKPCvCjLHC07HTaDgcRhWeNO8f5vvIJUWFGDLkqA24jzz5/EqXocijR480nU61ubmpg4MDPXr0SP1+X7nc5RspWQMMLqWZ3veaAhrmzXkLBgYERXYOyOE0c/xx44dS5Gw2qz/8wz/Uv//3/17/6T/9J0nS7u5uQMn19XXt7e1JknZ2dnTjxo347tbWlnZ2dj5yzrfffltvv/22JOmdd96JB8XK+0N6Pu0qZpuJ8e9Jc3iKws1msyixdDjkyXfehcwL0iSF4hBv4S2cGcfr4bUotnBizO+da3vKxFMMXszgqSfieTyTpIVrAqNRTG+Ty24tPApwM0kkYiTYJMIzwOQSwjhS8hy3F0A4G0t6zfPlTuDBHXCPqVRKzWYz1gePDuLwNr3MZa/XCw/q65q8vl87SSqynXUwGEQTvkqlEk0IyEoQTnDf9AVHHh0uOw/EXLtRZH2TCNQh+1WQnPGxrLUk/e7v/q7ee+89/Zt/82/isz/6oz/Sl770JUnSl770JX3ta1+Lz7/4xS9Kkt544w11Op0Xwmpp7ol5AKy57+BBwL3ED1joxAKGwIsJiKVms1nsXgIO+vuLZ7PLNzHW63WVSqUoDOG6pKYcArGfGehJk7e9vb343Dfee44TgYQ1Z7HYE00c6CkrjzMlBQOO53RmluH9wYDgeGmuhSKMx+MF1pZQg2cn7QIJxHw4HHdoCNpgrfwNHh6/u7HDAMJX8CZI+lFPp9OF/tKsDcU4lJlKc2TmpZXJzMhkctmIHs8IKioWi2o0GhqPx0ESkksmnQVSoCzXOQ3f+cVaee2De2VXXK+HcL34kaD1L/zCL+iLX/yi/vzP/1zf+c53JEn/8l/+S/3Wb/2W/uAP/kC/8Ru/oYcPH+pXf/VXJUl//Md/rF/5lV/R/fv31e/39eu//usfd4mFfJl7B39oBMThWjIviOA4A0gszIYB2GdJIUDS3Huvra3ps5/9rNrtdggScJwCe2JvyCTqbil4oGIMeIwnY6cMC+6lkShQr9dbKEqhxhmvCDuLB8Sie3iBkvnWOopDJpNJbJgHxgFpPdZms7zvqPI14HOujeHjOQhH2HDhJZwezxKXSlroYoIyu3fn+2z8xyOCMDAmnjP2Mk6U2ks6mRNp3lmGTEKj0Qi+5/j4eAEq88P9NJtNzWazCOGoN/D0KKGWF4Fwr8wx84+nd2/8I5Fd/+N//I/nuvRf/MVfvPLzr371qx932isHCyXNiwrcQjn8cSjt3kda3GtKswCUhG4g5GUdTq6srGh1dVU3b97UrVu3NBqN9OGHHwaj6SkOrkG8hAC54aHCqtFoKJVKqdVqaWVlJd7Y2G63dXh4qMePHwey8BQTz4XxIP7zAgnfzwyx5fOEBz8/P492sMSfCJLXIZN3l+YopFwuBxPtVXYIM8d5psErmsjTujBjhBBWh6iQUbDU/neuSw6fdCF/h13muh57e4EIa0k4wNZWUEImk1G9Xtfa2pp2dnZ0cHAQ2z8xWjwn6IACH9KcxPfMtYdkrrgeQiZDRPfcLxrXorJLWuya4Ow1D+nxo1uopNf2WIPFhLQhuY+wOOnE4lDp9Nprr8XEE1dzPyiANO+rRQGCQ1Ze/kXlWLvdVr1ej4ZtCAj3Ii3u+nKhdnbXa7dRCP7uMMw7axJT0+HEBYvvM2j/62wpKSdQBDE4UBs2GI/CMwBVpXnPbLwwipNKpRZe68Iae1EKEJj78TX2whiPl5k7zxq4oXM5Gg6H0RzRC3hu3bql+/fvRwdU9rPjuV02iJNLpZIODg7CAXnMi4PieVhbn3+H1Y4A/ZjkuBaKjNAy3DoBT11ReUBnprHu0rzvkaRoQs/x/X5/IV1Brrbb7erx48fa2NhQvV5Xq9VSvV4PC7m9vR2pKnLR5IrZ2yrN+yfzZoJUKhX56eFwqO9///tRQ80LwtzjeDEMrDTP7bHXdDovQYS59tI/PK0rh1cWAXcRZjYwSPN4kq19PDP3h6KARrh/jAlrRYzIvZE7Z13wmKSRfI1ZM2leNMFmCwwQXUmcUWc+uL6Taa7k9EID3RAOwJoTEm1uburu3bvBoPOuMAw293J+fvnivXq9HhwL8uEI0o0QTsBR51W68Ymmn/6mRzKN5JaIzz0f6qy1s8XOAqKwy8vLarVaun//vo6PjyUpWM1yuRx7aGkCn06n9bWvfU1f+MIXdPv27ejrdXR0JElB+uDRUbhqtapmsxmez+EisTlGgIXkGH8WvBy/O8QmppK0kNslxpfmb7H0+Irv+NZM/gUyotDOdnM+RydJ4cMrYTCA6eSOiYddsZNeHOPkykuTPLwyjfhRxul0GiWSrDfzjWEHifE9SUHe+dx45gFFxiCsrKxIkv78z/9cz549i7/BO3hYlM1mo44d9p05TNY4YMSSI6m4yTzzVeNaKLIrsLS4kRoYBsvsjB8L59CFGApYTc0z+WIgEtvZ1tfXw3JLl/lyfzfQvXv39L/+1//S06dPQ9CAqnhfYCaCiif2/KjHoyweFV2QezwPsRcxK/dGLMjAs/hWxyTz63EX5BXMqgu0b1wYjUZR5ywp7oXSRZRSmhOGzpp7yIJx4DwgLNYbJMbOMbY1eq6aQQjj+XNJ8aZGYmFHLBhRCDrgPDLEc7NmXqNwcHCglZUVNRoNbW9vRyzMnDPvk8lkwZhVq1XVarVg2R1e83/WBpl15OlsNvP0Im8sXRNFlhY3mydLMhFKZ6T5jkNyJ8LIkUJ88PoTrO5sNov9pORLEcCbN2/qxo0bevTokd5///3oXQVDjQWW5jXArVZLy8vL0aGT6h526eC53IsD+zwX6sIECUXs51sP8S58D4/ihBTnxhslt8aheORs+RvX9hZD0rxRnldVOVzGUOGxvb4bYwchOBgMApqOx2OVSqUwDh6zo3iOXHhO7xWOwcMIcj+cnx+MLUaYTRu80I/0mHRpXF555RUtLy/HNk6MYbPZVLFY1MnJibLZbDwj+XYKVDyHzHxz/0kFTSJQX6sfG0V2qMODS/O4js893vDPgC5OMLBfmEZp+/v7AYkKhYJarVZsdjg8PIxig/F4rA8++EAffvhhKDHnJm8ozd8iCDwEFvvOJlIqeGK8iUMuhAOCBuPkC4sBIu7leT13jJED/noe01l/fry9DdAVpME1ndVnfngmlADU5CiJ4z3+ZR6o3JLmeV4MDvlb7p0crsuA59CLxaLK5XI8J9AduZAUKabpdBrdQMlp82zUBEBaAusdrqOA7B/A8Ny/fz/y7aw72Y0khHfSNsn0S/oICkl67ueNa6PIHg/gofjdGT8mhuO9gobjXQCJW3d2drS/vx/WeHV1VZJCGPEeKysr0Zvr5OQkSvCAiF4M4XnY0Wik/f39yCcCc72OGbgPhPKdOalUauFlbKenp3EOTy15rHR+fh69qNLpdMTWlDE6Y4wgc05pnheXFAbM1wOFJj7GgNCLjFgfJcSTkfLybYte90xJI2tHvh7UQeUU3p6cNd4ZjwdUx0iCcLh/SDY3Yjx3MmXGM4IUisWi7ty5o3Q6rR/84AexA2xrayueh7VpNBqBuDqdTtTde5rKQ0Vpsed5kuTj/nkWJ8yeN66FIicfhJjRFTRZbwrxg+BzHIuTzV72mmo2m2EJETjePk+uj3fjYk29vC/JirLRwRP9CBkb0TEKybdKeCoNywz04/z8DS/hBJCXBBKjYQCShTQYEUIMad5Rg7nxmJZnwfCAXDAifObMthsH1o/6dRSFa3qxBRCYOXYUglHEcMCaE3PjzT3U8t5jHnZhAHhmlJTUF7vFqH8n15xOp7W5uak7d+4on8+r2+1qfX090Fsul1Or1VrIUFC9R1xMdZlDae7Lw6DkcITiz/Jx8PqHKtH8mx5JdpbfnXqXtGC9kqyf5wWBZfV6PZjTg4ODYGLxROPxWMfHx8FGr6ysaG9vT++++25YUqw/Gy9KpVK8LpX6bZSGH9hkngHl8jgUr4myA+e88sdLIN06M0/wCRgeL8KQ5uSSNI8riW9RQK+0Yo69qmtjYyPyqwhlsoczjRRAKiAB+oZJ81QQz+8e3qvTPCvheXE8sW8lBI3QQAAvBrHlBjyXu2woyKtR8e7ki4HSrO/GxoYmk8uyzxs3buinfuqn1Gq1FvK5nU5H6XQ6ymsJu2azmdbW1nTjxo1AYC7jPteso0Nq1tDTrD826SdiGgTVUwh4IbdMybRB0stRY03D+d3dXU2n81d8Yu09Fq9Wq5Kkn/u5n9NP/uRP6sGDB9rb29Pjx4/jBW4wjJKiblpSwGyEjGfivpwVRQkotfT4Hkjp5BcCyvc4D3E19+KbO0AsSV4B4QQ5uAL1er1oK0RuFAhMySewF6+bFEBp/lIB37vt2zOd0ANJeOcNR2OpVCrSOSgf98M6e1rH88F8jsGQFPXzToSydhBya2trymQyOj4+Dnb8lVdeCYVnDoi9J5PLtk2U1jo346k+R3DMF84JeZcW3/3laOlF41oosse3PKSTBP6AwEGHHggE1jKdTse+4EqlEnBHumQneZF5LpdTu93WBx98oH6/r3a7rX/0j/6RXn/9dZVKJa2srGg4HMbrZLxvNQtIjAZk43k8PiNnCvQDTie3NCKc2Ww29hVLCqgpLTY65xw+j8B0Nw7MXXIuMY4QWN4XGyHd2dmJ7XsYPuL7ZMyOYeh2u4FC3Bv5+vEsxMbSYsUa6S8MEkiF9eZcGEqUgfOBOnyXEddE4UE8eNVqtaqVlRVNp1M9efIkNpNgfEBR7km5r1qtpuPj4+BWKB8FaRH2eCjiWRiPjd1JeWr1x8YjE0MxkoG/M4guoG65+BsLQxkjkK9YLKper4eFX19f19nZmcrlslZXVzWZTPSnf/qn2t/fD5hcKBS0tramu3fvRs3206dPtb+/H0IuzXtTe+cJiC7uFcHmeYlRgf0eq7rQe8oEEgivTFGIv5Sd+cJrQazxOfAehUfIvPLp6dOnqlQqWllZic0c3AvfkRSvL8Xzev6aZ/MUG/dJn2jYcOdDMEoePyflg+dhrobD4Ud6a3G/yE2j0QiiDo+Jsg+HQz179kydTkfr6+uSFF47WafNfC0tLQUvkOQZeIUQhJ5DZM+ucE6Xaf+7G8TnjWujyA7zkoLgiuqeWNLCcQgK1TXtdlv9fj+KOfxNjKlUSoeHhzo4OFA2mw3l3t7ejpwz12Qr3dOnT6Pj5M/8zM/o/v37unfvXtwzSgmLCpNbq9Uih+07YxB+RyK+MYCCAzyKzwXK6vCZeJRjaJWDwSCO9m2LzJsrCOdMplAQUveCjkLG43Fs56PiCZjrzDACSYyJocEweRGFtwACYvOM/sYOR0SO0DBaoBeyDmxHdDaYtBrVfh7Lnp+fR4aD8tBKpRJVcUDj8Xgcvc+ptT86OornR169vp45TiIcRjKEuWpcG0V24Ug+jCf4GQgvnxPjSPM+zcSjBwcH6na7Uc3lUAsIW6lUYusgwwkmlPP09FQHBwf6mZ/5Gd25c0edTica2cPk0sSd+uRsNhvv0eW+UWS8qT+PC7THcElPy/0DQfkcxUT4KKggXzydXr5e1buYeMEGuVSa2+GpGQg2ML/X60W8zw8Glcoq5tJLLr1YBSPoMBnYj0GAASdM4YfvuvfCm7Mm3Bf3AnpwZQKaTyYT1Wo1lcvlhReqI3ccy7pBbuZyl73SeGsFqJBCIp4NZME53QPzGQ7LjXcyc+PjWigyFleaw2lnLP04J0+kOXuNpUP4l5eXVSgUdHh4qKOjI11cXARjSc6RyfWKI96uABzDktNfGU/+zjvvxL5lSfGKElAFsZffMwwm7Wa96R7Pmuyx5ekIIBrGAgFAiDxdgTJ7WStMbiqVCgHlmVBUUjPSYj9mlB6DCbnmqScXeKAkxBLli8wtz4YhcfTBc3pel/uDwHSy0o24GzRXhFKpFGw8hs1jZU+NwdID2SH+CFuoy+/1eoEa8OaSolyzVqvFFlqIUpdxNz4YMYbzPVd56eS4FooszR/qKhbUIbdvkUNJnAUkvmu326pWq9re3lan05Gk2JEEtKRo34kyvA9eQ5q3ZSXexNvdv39fN27c0NraWiymW25PK6AwLsQIv8dJeIlkvA2phsBSoVQsFmOvMHlWaf7Cco/HYVx9c4XfK/fL/KBcXpHmyopy8xkKhXB6epAww7+PMjk5Jc1JIBQOth7SaTabxQYUb4+LUZQUc8bf/c0hybnHwEmKnUuOaAgbMK5A6+FwGGkrwqe9vb3Y9UTVnMsxPx4TOyIBmfE3J7iufUGI9NHCcO+v5KkYz3u6x2ACKL1kr6x3zERhs9msjo+Pg2TJ5S7fOMFrU4B7QHqUyN9+gJXe3d3V+fm5Wq2Wbt++HQjAU1RYfOJ0apY9tXZ6erpQNYYiI3DehM/JF88zA8E9zePGLsl+J1Mb/B/PSA7eGXKHzJyPuXdDwDURSmfmMZq+ywiyy70TCg1CIO2FUSB0IuzwlJuTfI7WeE68OakjkBnrShrJ00fSvGqt3+9HbltafF8X7Z42NjbUarVUq9XU7XYX0qROPCLXyLF7YZfvF6Wgro0iM5x5duLHH4pJ9YdDCLPZeeeIs7MznZ6eLtQU04R9MBgsdNTAU7NIXllEnJVOpyOfTOxDqmU2u+zKuba2ptlsFi9LR7FYDK6bTl9WD2UymXjrBblut9auaK6czJGHICiZ137jgZ2ZRqnxhmzs8LlGyRA28q4OY+kY6f29SMcAo/E0fl+5XC5i0STRhoF2OE11mXRJkHFNntlDEo/xgbOgA5RfUigpGyDoCUYO33kDZ+iZo8FgoFarFSiDQRjBc5ZKpYXYNslac06+67UD/M7xLxrXRpGdepfm+zfd814Vj3m8QT6v3W5rbW1NJycnOjg4kHRZOA8z7U3xgEW855j4xuMs4Dr9uxAWFguoxTVWVlbUbDa1v7+/0DAOsgrI5/nWXC4X7Xo9vcTzIngOTZ2l962FTpA5LHQG2kkphIreU75nmhiQJne5XE6dTidiftYIthdj4RsqYJi5H551Op1Gi1tgP8cB23ke5MM3gjBHXgREyIT8ICs+lzTVky4Nw8HBQRhvv95oNIq+5lT2VavVaMGLQyBup1Ls/Pxce3t7Ojg4UKVS0fLycmzYSYZcvh4YTgwPw/PMzxvXRpHxjEko4RbJPZVbKfc8xWJRN2/eVKPR0JMnT6LOFzjrsBnvj/LXarUQTiw6wtLv98Mj8RrVdrsdxxWLRXW73YBkxOmNRiMIJ2dJZ7OZdnZ2QgnIWRMTurJJ85a3btQoSnHo54ICVHRIh+FweEqNOHPj8aw0j6U5F/lnDA5pKvdaCCNrhAHjHohNKURxcsqNAwYaCO6xfjKO9Jpz5pHrAr0xqlR4eRsi0IYbXifFfFdTKpUKttqLP2CuQRClUim2R0KI+vx4eOif8YMxYl6fN66NIieJgGQczHCPJC2+/AuPXCwWo9Ee6SQvr8NqS5cvoyNVRZzMYhHXYAzwxpBh3W5X6XQ6FAYI/ejRIzUaDeVyuRB2FO/8/DzuiRgPYZX0EWJHUgg93TCAq3hhF1JnyF0xHUoD/zCeKAdEEQ36gKt8BlfgJBVzkfTKbpSdjOJ5SPt5A0FP6bjQptPpiDNRZvgG78xByIA8eXji/cZIRVKKChJw7sFhMaRaq9VSu92O0k3m2DMQILVer6eTkxNVq9WoXfAGEF6s4rKMIUmSYvw8b1wbRXbL415Lmlt4BFOa9+VyJc7lciqXyxE/nZycRJ4VwQQ6I0hra2tqt9u6ffu2KpWKdnd39fDhQ52eni7ENpA00lxISP4TL/McxMIQV5Q++jZBjw8xCuQ9k8PjJoQADwWXwKJ7Sspzs2x0x0uh8MwpcWiSIMODetrJPRlFKawR7Lk/KwaH+mSHsBgdSVEhh0I58UgOHoH2sIIXtGFgfL0wKN5lhcHcQyyyVxrDzLMxD2tra+r1evrwww9jswpzCopDuQlPptOpKpWK6vX6AoT3tJPLk+ePfQ0gDp83roUi+816KokF8x1OTnpxHA9ZKpW0uroa8Ia4BBILy8tbMZaXl7W1taXPfe5z+uxnP6sPPvhADx8+DPIJIcbqA39guiE1iHWJ+8jfsjHh4uJi4VU1npJaWloKxhp2mHjWizFAJnjQTCYTVt6FwefEhYHvONyFfEIZQAyeg/aU0f9H3bvFSHpd5d9PVZ+ru6urq/p8mBnPeMbO2PEhiWMCyT84hCgHFCciChFCGGQlV0hICEHEVS7gIlcBCQmQlQuDBE6IFMUhCIJIiADhELBN4sSxZ3pmevrcXefq83R1fRf9/VY99XrGNn++D3VeadTT1VVv7XfvdXjWs9Zem/mAHMOTo2AwuFwoiGcavADG91lzsiHPTyztMsGzY8R4D8bJU14YYTgHjAbrIbV5GDeAHtrg3emW0mw29eKLL2p1dTUQEWgJttplBicyNzenjY0NLS0tBfLyy8OlpHy7Yt/us1ynZhujCyyvOcTyyhePn1ggthv29fVFX2GarrHNzWGZpKifvnTpknZ2drS4uBiWnTiHfygR4yAnidetVqtx4BfwiPETH+NJIUkajYY2Nzc7DlTD4yAoHnu5cPFc3lnECSrmtKenJ3YEuecGJVDWSazHES1szXNEgwdB0F3oQQbEzgheKpUKiOrvY1833glFAn1gQDz9xvO58eZgcUkxvygXpCLKJSnywnh85M73QPNZuJe+vj7t7OzoO9/5jl566SWlUqlIWRGXM9fI4O7ubqQ4qZIjvMPTI+eOivDojk6RvZ+IGFnq3AUl3X6fJhPvhRWQEJAK6XRa29vbcVYxrWMODw9VqVR0cHCg4eFh3XXXXbp06ZLOnDmjF154QZubm6GICLtb2CSsY5FgML3jB8rlcSiCiMB4fttzoU6IIMzAUxYe6OgpKAyM517dk3sBAvOLF261WtEZg6NEgd58luITjIunp1wR3TvyLKwR43HizMfEcyRTP17phAFzT4/hhIhzMoyfXqHFnLDejiz4fsI19jIfHx9rdHRUkuL4XMIhio1oVVQqleIootHRUU1NTcWBBIyFZ/YCHU83Mq+slXNDyevUKLLHo5I64jtXXqm9MM7U9vX1aWxsTFNTU0EMOdvNZvhGoxHdMynCZ7M9XsAtnwsrGwLwxAgqDLF0UnEFEoBccdgLkcSYpXZMyEJxRAxj4h6+SSCTyUR1E/EfF/Pl+63ZluiVbFSsMbbd3d3IoXIWlhstNxSsEfNFyagbXtJBIKZUKtXRgBDP69CR+/MMrC8K7LwJioa3Rya8IwmhEIaZmnDOw2YuyUgwFjgFUBCtfyYnJzs6arqhwlMPDw+rXC5re3tbpVJJs7Oz8Tq71eAwWH/PUDj8x7C4Ut/uekNo3dfXp+9+97t68cUX9dJLL+lzn/ucJOncuXN67rnndOXKFT3zzDMBFXp7e/XMM89EG9mzZ88ZaBe0AAAgAElEQVS+0VfEhPETb+WpCH8g99wICUezkOdbXl6ODoeUyeEVseiNRkMLCwv6wQ9+oFKp1MFe4qmc7EEYHfKjsHghOod4fpn7OOsI1EbJUUYKKdyrMi9OesGk8h6KVlgDh+HEs3hxT29xOYk2NjYWyu69p/GyPD8xMDAcuO/KTEjgCIlnc7iIEnvNPXDVCSfgLAaUZ2eNnEgi3GKOadRHqIUCszHDjXgSBezv78eBhDwDMoiBckKwq+ukMUG9Xo/sR39/f3h0l3nu43Df+Q7G83oe+Q0V+eDgQO973/v00EMP6aGHHtIHP/hBPfroo/r85z+vL3zhC7p48aIqlYqefPJJSdKTTz6pSqWiixcv6gtf+II+//nPv9FXdAzYJw/hdSLMiyL4++DgoM6cOaNsNhvetVqthlfmIlfqJwRcu3ZNL7zwglZXV6MIHkuOQPjWOXLNxDnJeMrhHrutPM+Ld5PaiALhScbBeCWeE+/D3PC9kD28zvc75OQnMNkRhZd1NhqN2A3GGDzupg4ZRAFDzbPwbNyXdfJ43cfJnKC4Pl/AZ7yVQ3hnypOFH74mGBxHHoRHtOBFATGoMMhAbi9JxYCyvqS2eHbg/dDQUBhN6aSN1PT0dBClHueHMqbbXVz878h9ErX69abILvKebh3f97736Stf+Yok6emnn9bHPvYxSdLjjz+up59+WpL0la98RT/3cz/3Zr5CUudJEl4U4D+BMm71u7q6NDo6qnvuuUfZbFY3b97U6upqxGXUXUN09Pf3xw6XarUaTQIQOggvrLVbx93dXVWr1Ti/aXt7O2Aoi+TtaBgrxghhQJBhxFEkBIeLMQEJnfTjfkB7/s5cEndDLNF5A6F0QcWYNJvN6G2FB+R1kIznQcnhArPdCLondPQAMQcHgccj/OFvCDAoCSjOXPEszDtH/PjmEYyDb2rxfDlKmuQNhoaGQtZ9X3V/f79yuVx0S2XLIqXAGCs6kNZqNVUqFR0dHcW2UFdK5z1cYd2AOqK60/WmFDmdTgcZ9A//8A9aWFhQtVqNh19eXtbs7KwkaXZ2No6ibDabqtVqsdXPr09/+tP63ve+p+9973saGxvriHHckzj0cnreiQJ2uoyNjWlgYEDXrl3T7u5ueIqkZ0ewYKSpyMKLMZEw375LCgGgK4YTSSyO5xQ9FEDhEEJJ4dU9DkUwvVJob28v4iYEDMXn5AOuo6Oj2JxBGoRxJIWBuUSYEDxPq+CluAdK5jDbjYs3VWDeHYpDSHI5E49nxJB4gYavt6Md5tqRHPKHvDBPPI/UTnX5PEKMeqzOPPFeusnQ3BElw0CikEdHJ5thGo1GZDk804HX9fQm+uZy7nN/Rx2941/sOj4+1sMPP6y5uTm9853v1L333vtmPva611NPPaVHHnlEjzzyiIrFYkfs6Yl9HiCp2K7UEEgILDQ/FpyuHBRpkAqQFLENsZWTHFh8hAeWGkMAy4sioSTsyJHazRBc0aV2zJOMBZNpEe7hGwBQYiAdYYLnWz195fE2Xggj4VVnzDVH5uBpveEA8824EXhfG+aG7x0YGOjowcU8oTDsIsJ44aExeKxVJpOJ9A5GAy/JMwHHmX+Mo6cuyZszdn534s3jYOAxf6vX66pUKiFTzqcwRxxSR709BppwhOdE1jwu9pDLX3u9PPJ/i7Wu1Wr69re/rXe9613K5XJhQefm5rSysiJJWllZ0fz8vFZWVtTVdXLGLJT7m7k8xvM4WGq3VPX0DIKF9afzo0+CU/dsSieFIrVL+DKZjMbGxuJc23Q6HbtwYJD5Lk+FOPHSarWCGZcUeUiU7XZxkCuiCxLKD4qQ2hwCCuZejOdywsi5Bald8URszbxi9UEqwNmtra2YJ4wMHhSFhlhirVgvoCbPKuk1z+5Hq3i6zpl+4lL+jodGHmiY7wyycxKORPj88PBwzBXPR3rKEZvU3ttMhVZXV1ec2nnlyhWVSqUIK6hhYBz7+/va2NjQxsaGenpOmtnncrmOc7pd1lkXnBTy8XpEl/QmPPLY2Fj0D+7v79fP//zP6+WXX9a3v/1tfeITn5AkPfHEE/ra174mSXr22Wf1xBNPSJI+8YlP6Fvf+tYbfYWkzpyxC3TyPZ6nTKfTMbnU+K6srEQxO4uzs7MTFjOXy6lQKERMhyclFstmszp37lxHBxGP3Z3BhSmnpzKf4ULZEHZPxxDr4VGAnKSkvGuJQ1M3Ggg2/5wMcuXEmvMMXhRD/OWpNA68417Ef8muJ/SBJibEYyKMKBfziFKx24kQwUMp/k/en7Uk1mVOeVbWl80XlEum0+kOmOtkWbPZDPRGloH34Jk9Zu7r69P09LTm5+c1PDwcqSdkwZ2G75zDaRSLRdXr9ZCtmZmZYM+df/FxJtHp65VnSm/CI09PT+vpp5+OL/jyl7+sb3zjG/rRj36kZ555Rr//+7+vF154QV/84hclSV/84hf1F3/xF7py5YrK5bI+9alPvdFXxIQx6fxEYB1e346aRxnwXE6kwEyyV3Z6ejqql7DGnF9MOejFixfV19cXBSI9PT1RYI8AZrPZDq/AIXAU2/NMbpz46TEYHg6SzckQBC9JjDjSwBA5x4Cx4/lgljE2nobC8uNF/NC54+OT3l5AdR+Pw2BeGxkZCYX3XDprxkYFBJQ1pcspxgFWGpQCXPXnYny+uYS5wTuitBhA0lGUoZLhIASjhhxj6wcTeG9tOrGWSqUIowgHnLUmvt/Z2dHGxobe8pa3KJ/Px9nbID84GTdoSXL3jfLIb6jIP/jBD/S2t73tNa9fv35djz766GtePzg40Cc/+ck3uu1rB/L/Mqd4ESqZ3BoxwVInBEdwIIauXbvWUVtMf6qpqSm95S1vUTqdVrlcDjbXrenKyor6+/v10EMPqdFoaG1tLQgxTjcoFAoqFAoql8u6evVqCJv3pUIgiNepICLn7IUmvA409s0UUtuQeT8vvN7xcbuzhSMYCkKAi8S7GDnGwA4iDz/S6XQcCE/4ICmKKJxB97ZAjJ+40/O8GD3v4OnhAN7Wm/OzV5kNL0BdjCGsPZsxGAdox3kG4KlvFcXbQUaBXiAknfmmeT/90jG6W1tbsU+driEYHBj9/f19FYtFVavVuLeTap7BcEeV/Pk/UuT/rQsBAN4hzElr5CRXT09PtKctFAra3NzUv/zLv2hhYUHHx8dxckS1WlWr1dLU1FQIBVAaYdrb24szfF555RVtb29rYmJCExMTUajQ19cXR6N0d3fr7rvvVqFQ0PPPP69yuazj4+NQEthMGE2IMUnhraR2h1A8DgaIy0krcp5cXvKI4jh3QLzqFVh4RgQRLw3M5fu9jBQl9Tg+Sd6BovCkrJdvJkExPc/txTIQlRgtjLvvM3Yvj0EAYvv7+Q7GyP2RNebcY1CMA5tgqDGnkQKGr7v7pFUURKeHG7wnnU4rl8t1pKeKxaLuueceFQoFjY2NBeJLbr1kPB4+eNx/u+tUKTKTjbB4jEoMwWv8f2hoSBMTE2q1WlpcXAwlwsoyIYODg5qamop4DyXzQgsUcX9/X1evXtXy8rJGR0c1OTkZR3c2Go0gs/L5fBAnw8PDHSx0cn9qq9VStVrtCBlgkBEaPu/lqX7ahCsQcRzb8NzLu/Ii3M6oAiO5D2GJ1HkiIO9ttdqtfb0c1Ikt9yg8r1epMRZnuFEeQgvgPswuCswaYWik9s4qxspac4FmPL3HhhWpjQBRPqkdqkBg8szuCf2wAX56CEXZK7B8YGAg2j7RMLFQKEQvL9/5xoVsu1Pj3ne6To0iexzsntjzys5+NpvtPszNZlPT09NqNpuxdRCF4b6jo6M6OjqKZgDsOEJYgZwIjcdXpVIpmFkvIMjn87p06ZImJyej2ISjWBFYvAZQ159jd3e3Y/cS3oq4HILL84ruwclpJlveOKQkjcPnfH6TqAfhRrGJ+fDYGFOejTGSXnIIz1pK7X3GGEpIPhSJecHoAsWB4XzWoT8bODB6vs8Y4wccxwiApPByzCNGgHlDsTCS1L7zGnKFLPX394cXdw6DeUWZKdUkNMvn87H7jedzNMQae3XXna5To8gsKpbJYxyEzfOADmVQwNnZWf3gBz9Qo9GIe9GGZ2RkJGKk5NY24izpZGGpZINx5v7kV4FT1WpV5XJZs7OzQSqhWB7bO2HlAkXrF56L+M09i/9dUpB3nrrAYmPwPPXim+Sd7MI4IDS8B084NDSkwcHBqI8mXeftc4ith4eHQ/hBOQ7tuS/ryPsIG8gXA2u5N7yDh1KkoTAaeHO4B7gJXzuUlHuhFIyFqjVQDfPNuPHQxMzIA/UJHOCGx8cQSeqA+8vLy9rd3dXdd9+tSqWitbU1ra2tRTES6+2ZGc8u8J7bXadGkRmop1ykzs4hXJ53Y8J7enq0u7sbR6SyAEBKT8lgKV0AgK7sJkLIiOHIVxNP81na7WYyGVUqlWAssda839NYxM1JsgNl8PFKiqIDjmHx7ZAusHgir2hygg2EgRdxaMn4ILLYQcR8cy/ifQzl4eFhkDyemiPlBVpwyA2hlCThMIQYF1AQz+9e00tBm83OQ/L8QDrml896k4rbVa65XOANPXRhjBia7u72gXten00+Op/Pa39/X6VSSZVKRSsrK5qbm9Po6Gj0dNvc3OzIPDjs9zlL6oFfp0aRHY448eDFDvydSeRIDpL7HDTmzCdKxudhFSEQHDIS3wCpvNIHCM/EMtmek0ymkDwedNjrz+HFFJA9kjrSYXy/x9E+T1K7uot0FAbBq8PcWHje0sMVmulhSBiDM8zMDQwsP5lvN7S+0QMjmiT1IMgwQO7FfAcXsToKiLGivJJ5Ronw/DyrpI455Rk5TI7Gicwnhkh67dZSjCbj95Qi93ay8/DwUNVqVRsbG0H6DQ8Pa2RkJMISvpdQy1OGLju3u06FIvviOVuXJF74h/cA+mQyGY2OjmplZUXFYjGMAjk/ChaoIpLUIXiSOqwyaQ2v7AGmu3X0/cIULuAZEf7u7nbfaBhg4J8LCwLJYrkRQQjJwaIYIAcn9VxRUXo+7+ELsamnPNxzeVwLzPPCEt+Y4JCev4+MjKhSqYQBQklcIb1e2iEvdeV4N9YKpcQ4MQ6MssftHgI4L8FrhEiMme8BnUntUlN3Js4ewzMgW/SEI9wDuWBEDw4OtLKyoitXrujMmTOhzGRLHBnxfB5eesiVvE6FIsNGepLfc428x5UYq8xE4JGBsVhMVyaYZy7gtKSAd7eDOJBXkEYoMoJ8dHTSx8rb3bpwepknnjLZAhblAs7TpA7h9rwyAs53u9d3xpPNBDCwhCCMw3PCzCsoCCPFPDBW9zz8Q2jdyFHpxRlJHgqhpIQZTmbyfJ5ucjLPoTBrhUcljEAeuBfrkNweurOzo+Hh4Tj6xfO2zuLzTA7l3VngTLa3t4PQcrSVy+XihMalpSUtLy9rbm5OY2Njmp2d1fr6uvb29qJRgct80sjd6ToVipxk55xt9ljPFczJGw7oomcW1UFMPN0ZRkdHQxlR8J6ek4brNKvH82LlGR/eGW97dHQUOWWUB4/Pzh0EDQVEqVBEYJcz1MTCGCuHZ63WSdUQBghPgqCjDEBqFAPI7QrD8+GBgH9DQ0OBiPCgsMPJONLXxtlxvDBeijVDeRkL9/Atlck8uv+f8kmXDQwPBSQehrlydnV1vYb42t3d1d7eXpRL4jmdT/BUFF7b5RJncnx8rEqlEgiL58Bjw7LXajVdvXpVly5d0rlz51Sr1TQyMtIhs45M3QCeekV25ZXaVpC/OQmEMlPnjOft7u5WuVx+zR5gyjLPnTunubk5bW9vh9KyeFNTUzFhh4eH2tnZCXLCW7KgbB7zAqM46dHZcCy9500xLklD4YIBnHVCR1IIoisz8A/hc4uOV8DzefUcRBX3cO9H/vPMmTNaXV1Vo9EIhU+n0+HdmXdXap4JA+Q9v92I8J3OmDtbCzrB0JHGYU1BUB6L4l2ZJ7731q1bUaTBvSiKYYMIDgEyi3n3Cjc8uj8Dz+xbVmkhhIKDjEBi165d04svvqj+/n41Go0oLPEOKi4XPk93uk6FIkvtCicnRTyfRhzIBHd3d8exlU50eTtXKrGmpqY0NjYWbW6xjiwSMc7k5KRGR0dVr9cjzVOv11Wv1+OeDtUQNvLXLCAkFMLuhJPHbp6GgZDD+3os7HEqHpc5ca9N3hWCDxTDmFEMyCn30IQKvm8XdhkF4jWpHQ75egFZHYnwPI4OIG9QDBSM13heeAMn2vDsbCHEcGCE0ul0HMbnvAtIgcKd7u7uqLzi5JBms31cLSGRyxwOhdd85xuhW6VSCQVH4SVFJoNDDpaXl/Xyyy9rcnJS4+PjKpVKKhaLHdyQh33JtGTyOjWKzMA9PuCns79OjAHfUqmUVlZWtLa2Fq9j/ba2tvRv//ZvajQaunjxooaHh1Wr1VSv1zuIhe7ubi0sLMTm71brpAY3m80qk8lEs3vSJiiPM+vAUiqSUE7qbb3skMuVHbIDj+t/Q3AcprM7CC9DqswRCfdjboHj/uzejpfnOjw8jEbsXAh0Mj727/PxOh/gaTU8jsN0rxvnsxgNYm4YZzd0GE7mjDpmT4V5GsfrBTAolF3iCAhVMG6sL94fZcdYwLpTJccxvs1m+xACdk1ROZhKpTqgPZszaIjhc+Rreqfr1Cgyi+AD9nhBapMQx8fHkXrKZrM6c+aMrl+/rqWlpY54Apb47rvv1v3336+enh5tbW0FQyi1a4TpBELRB0qFV+cUilqtFnG0pIiRJXXkl1EGSBm+j3gYUsTjPKy4K4/HRp5+ci+HkDlJhXckhEjWIXvu2rcFMt+pVCrKChF0LzxBMbhc4IHbnlbhe4Da5Hk9HSd11px7fOuQnTibvcF8BwezwVcQPkA2JmE2nnR3dzfSQOSsyVqgzKwfcTpj9owBXpmdT6QiGRNztr+/H40hQRVkVxgjOuCy8RPhkb18MZkrZeJYZPJ4k5OTyufz2tjYCDjMhm1i7kKhoIcffli5XE43btwIIgv4iULwj4lkTJxCSL7Rt+HxnXgdTwHhrZwJde/lFTwwyVJb0b0ohb+7N0uyqMTDkqKpvDeyAybD9hOOeF7d65lRHL7XCyQwHBgjSC7mHM/luVrmAVSS/C48JPA12eGF52o2m9FDmlAD5poxOomWLGxxVEEI4Y3vPdUotRWJOLi3t302Ms/kqSM6nXhnT1j17e3tqPprNBrK5XLK5/MqlUoxV1KngUAmmKs7XadGkaXOhgJY4aSXkNqkk9QuYvC2p84uptNpbWxsqFwuvyauwiuwkB4vSoqtadRYA5W9oN+3UHoc5SkbfwbG7AqB4eFzzANeCaVF2SB6MAgsuhda8J0IHLEv9dNc+/v78SyQPFLby/Pd7pW8yAIBo1kA64jxRdGSxJ2kqH5DcP3ZEWzm1VNN3oJpe3tbw8PDsQ+deR0eHtbKyorq9bpmZmY6SEvQhRcV7e/vd5SjMi7kwmNtngsFI1zBaHg4iDGlpzZ9vWu1mn74wx/q3e9+dxwMz5UsPvqJSj85pHaFldpVPR6febL90qVLeumll1Sr1ULhuE+z2VS5XI4Yk3QN1p8F9ZwyJAfeGkFHmEiVMNm831/3PCwL4x00GR9K4taX6jIE2ckaz5e6x3flR7hcAIB+6XQ62H0XHmJ5lBEhJ4fue5adOXYFdV6D9QNZEHcODw/Hs3k6zllrxgPRxYF6nmnAywOveZ06AvLX586d09jYmGq1Wii6owDGAjdydHRyTlexWOzIdbuBp40Tz4SRTKVSIYMYGkjVRqMR++Lx3FtbW1pfXw8vzvwnSU9Hp3e6To0is5DuETx37FVPPHA2m9XBwUEQUS6cQCGIHgQU5QSKJiHlrVu3Ij0ltZvnsZjEnjQKoD2PlxI6gSN1nv3MPTEySUiJd0NxPNVDnOnKyrMyfr4DqMd3SdLm5maHMcAbHx8fxyHweHC6PdLf2tNTjJ1KNvLpzpKDCPxkCYyAp9i8Soq1oZCC7+X7CGMwcJLCOKBI9Xo99gCTEqSKDCTjio9j8CKagYEBnTt3LjgCUlQoKEZdUqCDsbGxGA8yTZUXOWvmoq+vT6Ojo8pkMiqXy8pms5LaR/96eWbS2N7pOhWKjBA6jPDqHmerufj/4OCg6vW6SqVSh4XF23nbWa+xZceJ1wm71d3f3w8m1NlRGtD53luPD7Ge/B1Cir/7Z9yyS+1zkB0aO2THAzAOPo9B4tkYh0NQxuSKxt96enqCqCFuzOVy+pu/+RtNT0/rvvvu0+LiYkdek7Exbn8eCEHyp3wne2+pgsMY8juGGBaXDADMMvfnWagjgPFNpVIaHh7WwcGBKpVKzK2n1jDoHvd6CMQ4ms1m1PEfHh6qVCoFdCaM4H2zs7PKZrPa2tqKe5BKwjlgtEAVGMjNzU1VKhW1Wq0g5khjuuy8nhJLp0iRPdj3VJR7ZgQIGOyWnuos7oPXcYuOwBObQTo0Go0OWOdVSryGYjI+SbGNDUNAnrLZbHaQHu5ZvVbXc53unaR2mSLIAcVgfy2kjOcdGXOj0VA+nw/v7Qrg7YKA+Sg+c9xsNlWpVPSud71LN27c0LPPPqu3v/3tsVY8x9HRUXg9ICljweBwuJ2TZRgSqY0mPI2zv78fXh5FcBTi90CxMEI8x8TEhEqlkhqNRtS2Q3CiRKwRpGcqdVLMUa/Xtbu7Gyc99vT0aHx8XMfHxwHRBwYGNDExocHBQZXLZQ0NDXUoN/PNM+ZyuY76gc3NzQh3stms0um0KpVKByHml3MLt7tOhSJL7RjPK5EQ1GRumQlJpVIdnR2TQkm+F+/EPtFMJhN/g21GgJNxoHeXwICQd/UFA65Dpu3v78e5zMBn3+SAQXIBRuCldqxMswGen37MPDf/p3SUgg8vqHAFxvJDwsCs4vFJN/H8kqLQpLe3N+aLZ/F0EOQf3sSPtgVtsGaeiZDaHT4w4hTrYEyBwozNYTulsV7lBqq4detWxKgoIUyyn9PFP+kkLMFT1uv1YL+ZC6DwxMSEhoaGND8/r1QqpY2NjTBevnMJY4fh5oA3T51RzorB8loD98x3uk6NIpOA9xwuAp/0FrzHa1p9ZxLwlMkD1kqKIgqP5/i+g4ODsI687sQUgoq39GZrXqHljC0Ei9T2Zl63nYx3gY0IPeNnHEkjR6yGMiMAPD9Gi/F7morqL+YF8sxTT93d3br33nvDIGB8UqlUVFAxboyLKyAGAyaZElgMrHdIYSyeCvS18yZ+vmbE/nhlFBtZoEJvY2MjjkLFIMIFsBOLOR8eHtbR0VHsIYbRZi67urqC2Do6OlKtVtPy8nKkP5ljuoEsLS1Ff3fkHMOLh5fap3/yf3der+eVT40iS+1maJ5k99wlMAeCA8vYarUilkKAYUedOEBAUTSUEhYb6Mo98R6MxQswgNLuuYjp/ERHFJIURDKEwHt47hYj43tqkyEGnyfOg5hBePG8CKwrsbeBJdZGkSCA8G54Ik+hodCsCdDXmXIEFEViHT1m5V6gLmfvm81mQHW+t9VqRe4bGH14eBhtZYnbUQpqmJknTzMhD3hl32/M57u7u6MBY71e1+bmphqNRrRPZsfS1NRUPLsbWcYLZPZ0oYdFGCTWP8l1IB+vd50KRXbo6BDX0yueY0XBs9msRkZGoj2M1K4G435AKawpygiER4EdrqKIwM5kfrerqyvirHK53AE9WVDIFJQIVheBB5Y6+QWETC4yhs3LOzEMkDVOEPq8euxMGaKnXjBGrVa7WZ4LludTvSoKpXQ4DJIgJqWYA6TAhgZfU+aJ70+iIZ4dZSercOvWLY2NjcUzVavVUGIyGswLWQjSSzDMyBFEmJOZXmxCTX+hUFClUtHS0pJqtVpHWunw8FC1Wi3QHvNDqCG1j6/xcIL1dCPmKS/mn/m603UqFBkF9tiURXBICByjCAPFA2ZLbeGQ2lvnKJXz/CNC4oQKE4lFdqVhnMmcKY3LUSRvMYSiplLtdj/kct2jOVN661a7R7NDcW9Qh2AAPR3e8twOQSH4mF/mFYH13CyIh1gbhAHbu7293VEgAXwnK8BYeDbPPHj4hKI4unGjgjLjiYhTKRclnue7j49Pyl63trZiXdl/7s0JWDeU3mN1nofxIWvMVW9vrwqFQqztzs5OkGPFYlFXr15VtVrt6AHH+JkLTyV6FoAx43iQYd77E0V23e4hUQQEQ2rn6iAwHIY4kw3T7NVQWGHqsIG2pEokxU4qLpTfa6a5vys5AuukBV6Zv8Ei01+b8bHNDdSAkrHIjJdnYqwoJc8ApPX0Bd7Oz4vm/Un468fXnD9/XsViUdeuXQuPSM4cbqBWq2l7e1tjY2PxfM5TIKA8EykcFJjvgueQ2ge1M2bW0wkn8rTHx8eh3MBsxgmb7buRPAPgOXYuZIn19JJP0pbd3e1D4A4PD7W2tqaVlZVoEEBu3uXSFdNllbUYHx9XV1eX1tfX4/1uDKXXJ7ve1GmMfPnzzz+vr3/965Kkc+fO6bnnntOVK1f0zDPPhGXr7e3VM888oytXrui5557T2bNn3+xXdEycM9AoGxMKidXb26tcLhcwWGoXbiCQLD65yd7e3sgDdnWdnN+EVUfAID6kE6NClZCz6h6nutUFToEsQAx4O+JPPAX38TZBnlJyVODsOPAVr+XpMa9YwwAB77kP43OF5//ZbFZTU1Oam5uLRvv+OeYvk8lEB1FPPblxIV98dHQUOVSMnFdqcTHuoaEhZTIZjY+Px3nEExMTsX5sM0XBGZcTjbVaLaAtMkQGA+W+nZxLbfIOD+n/CNMg7iDSgNsosc+HQ2qfn1QqpZGRkch/JwlF5Mp/3u5604r8m7/5m3r55Zfj989//vP6whe+oIsXL6pSqejJJ5+UJD355JOqVCq6ePGivvCFL+jzn//8m7q/xyvOVvpPXsdaMZG0r0VJUGAmY3R0VPfdd58uXbqkmTB3PycAACAASURBVJkZjY2N6b777tPb3/52HR8fR/N6BJ1cI8KCx/KFlDrTT6SmXPFgQz0O49CzkZGRgHd8j4cITtJAmHmsjvFwOOu1xs5u49UpzuCfp46YX7xREso5d4Eg8xOmH+OEoiQzD15txlxhUPHAoILBwcE4nA/00dvbq9HR0dd4OlKKeGG2k7IGrAeyxPc7K8wzMkbg8d7eniqVSsThW1tb0baHFBhIAkObJOgcmfE+QrnBwUGdP39eY2NjUZzkn+ee/H6n601B69nZWX3kIx/RH/zBH+i3fuu3JEnve9/79Mu//MuSpKefflqf+9zn9Kd/+qd6/PHH9bnPfU6S9JWvfEV//Md//Ga+Ih4QgUqmIxxiSCexGgl/FA/viUemabwkTU1NqVAoaHl5WdVqNTaSp9NpnTt3ToVCQT09PapUKh3Gw+E6eUupnZrxMkuMkLOPLBZKMz4+runpaXV3d2t1dVWrq6uRyoE0kRSezL0mC+slnpI6jBtKz1lFIBK8IoKBYiLUXjeMx6fIhjEA/6nQIr7HAEjt9joO/3l27/fsWwmB9xhS9oCzLfHg4CCqxfCQoB3KGkFXGMnR0VGNjo5qeHg45p/18nw6zgGkADKipBLPu7e3F4x1s3nSSKLRaMRuuuQ+YkeWyDbzgjyl0+kwWBgRjJnvp3aDcKfrTSnyH/7hH+p3fud34iylQqEQiiBJy8vLmp2dlXSi9EtLS6GAtVpNhULhDc9I5kEQELdezoy6ZQfipVKp8Gqwo1j4Vqulzc1NLSws6ODgQGtra3EYGQvIXma+l4Q+3w+pxsI7w8j3eCxOLIZgI2x4DgQklUopl8sFEQahBRxHyIeHh9Xb2xtEE4LiEFxqt2X1lBNjhYlHSHi/ewwUxeM89mezuwhh5fkguyj84BkwgCAtZ7o5W9sViDmidp0NBpTJAu9TqVR4XEnxfjpSYgCA43w3/APhj9QuLT06ah8lc3h4GEpaq9XUaDRUqVRUqVSiEyixMk7Da9Y9VekykkQ6zHsul4udWpC4yA9rDSH7P8ojf+QjH9Hm5qaef/55vfe9732jt7/p69Of/rQ+85nPSFIQJVI7F0hs50rMBCF0BwcHKpfLyuVyseOJ10mtNJtNra+v6/r16+rq6upgFbu6usJzQZqQgsCwsK/Uc4Asvi8KBoUYDM8MfG42T3Zhra+vd6SRiOs8ZdZqtUsbk9vjPHWEMnmKwmNHxgDr7UUfbBAgDPHzn2Dfy+Wyjo6ONDk5qVwuF+WOxPjOKPOMKDFCiNLwbMm2QTT8I/SQ2vuOm82mGo1G5N/hOaR2jpj+YplMJhos8rrn5eEQWNO+vr7wpqAQIG+lUtHW1pZ2dnZUrVZDqVlzJ6tQPhTQMxrO2LtHRZ77+vqUy+XiHhCVTpxi8JDtO11vqMg/8zM/o49+9KP68Ic/rP7+fmWzWf3RH/1RWNVms6m5uTmtrKxIklZWVjQ/P6+VlRV1dXXFObLJ66mnntJTTz0lSfrP//zPjnwlD+KQ0gW21WpF61FiSKw0HodYlhRKqVSKMkaUHeFCAak4QmnYOE/MCWvsCueL6sjA71mtVmPseHb+TkqFWl16f6HsnkfGy4JcnP3176QE0uvNMUYomueI6SOFkpEGcfKMMQ8ODoaweRtZlAS4joIjnAgiws5a0drHUzPDw8NhMFEG6tgpme3r64szqgcHByM2piSSWB6jBlJAgZwb8DgUYhDOAg6C+XNkSHEJCBClcxTpxt5TUMfHx8rn8x2ZCH8vF2vgLPf/lSL/3u/9nn7v935PkvTe975Xv/3bv61f+ZVf0Ze//GV94hOf0Je+9CU98cQT+trXviZJevbZZ/XEE0/oueee0yc+8Ql961vfeqOviOt2JZke1yStPXs9R0dHO2qSU6lUR84YQSRmQ5Clk1i30WhI6ixM9+/nd+ApCkZMSg601WqpXq+HdyE+ddiKN3N4J7Xb04AAnOAidgO68nwIRhIxMFY8tuezEThe90Z8HCpHKqq3tzea0/FZXwNiZ1+T1dVVpdMnR4pCvmEceF5YadhZDCUxI3wGoRPz7Ns9vVqMz6XT6dgl5bUIzgB7vppnIOWH8nsVlXtRNl2AFomV4VU8nPDY1glQlLi7++RUxqmpqVhjtj16WsqdxP8IWt/p+t3f/V0988wz+v3f/3298MIL+uIXvyhJ+uIXv6i/+Iu/0JUrV1Qul/WpT33qTd/TY0uH2gguk43XKRaLMbn5fL7DG2O1U6mUSqWS9vb2NDY21gGx3OMBuaT24rHoKBRxEJDVFY1xEQdi9V0wEGxiTL7fe2pzD8glEAB5bmA1F56FmB+0gcLyXmAsSoVSoiiMCwNA7ArEBXkghDwTnp+fblBBBqAQDAekGYrn8fL8/LxmZ2c1Ojoa3hUYjrFgLA6LMdyeVmJ+HaI6CcW6k/kAadRqNVWr1YC7x8fHAZ1BC7yXi+90dMI8e+qOtezpOek5lslkdOPGjY6qMM9OOKHpabrk9d9S5O985zv6zne+I0m6fv26Hn300de85+DgQJ/85Cf/O7eVpA4hxrrhyTwPl2STHZ7S5hbLSn4Y6JrNZgO2kt5hoVAocrNSW5ERaOIzLCOxMt7SvR3tf6QTj0zch+LhFbDevuGd7+dzCAOel88wVgpKIKrYOUXsjjLzWUotyZW7V/bGAY4sPGXFWknt3t0u6BgzkIF7Ip5/d3c3ylxBAcPDwxofHw+OwVOAEE1kBkAf8BrMOwrOfCEvkjrmEUUsl8taWloKVtvTag63u7q6VK/XNT8/H90uMQCeDkSWmEMnQz3uhVknreWGwQlMh9teVJK8Tk1lV9ITu1LzOpVIWMjNzU2tra3prrvu0qVLlzQ2NqZyuaxmsxnb8VKpVKQNxsbGoum8E2lsbIexRkm8VhaLD0TGwyTjIBYKOO8pBSehpHaFEgpDNxMWjUJ+Dy2kds8pZ4IlhZcjhPACA4RqYGAgvBzwGSVDUfDCPA+N4lxIQRUoK4QXAu0pQ9bUvWar1QrPzHOza8lRBD8xvE7w+W4vXmNN3RM6xCWdlEqlVC6XdePGDa2treno6CjaBjF+FBWuBcPNOFdXVyMF6pwOF3PgcLm/v19jY2N65JFHNDExoZdeeimMJ6GDozLncH4iFDnJ6CEwCKvUua2LSeUo1UKhoMnJSd24cSMS+ZLCKy8uLkYsRXcQJgchRqkwFgcHB7FrxdM3TtZwH49tiQOBfKlUKpTLYTkL1dfXp6GhoY5+ySghR3iSI3eITPwOsnCvilCTxmFcHI/i43d2ld/5u+cy+Ttemef1XlheSIEQEkZ4ThzjRyonl8t1VG55HEv45Ky4k4xuUP37PA3kKSBkZ21tTcvLy2o0GgG96TTihCjGibF7ERLywb0JO5g/d0zSyR7mRx55ROfPn1e1WlVXV1fk+JHz20H25P+T16lQZPe6yYVw5XXYzWJ4qimfz3fATknh7YiTR0dHVa1WQxildpyJ0HrfJIiTVqsVnpvCEAQcmAf54mwuxgJlTKfTkerBGwH9eW6UDVaUhuvch9ABBeUZmEPiYDwfXsnJo5GREc3OzgaBxqHtPF8qdVIRNzg4qI2NjVgXUAb39K4su7u74Z1Jvfk8Mya+k7Gk02mNj49HzIiBkTpzsO7h8VgoIM+PPLlXTjqA4+OTVsbVajWaxgP3mX+KULi/K1GpVFKpVFK5XO5gognTMLDMEdfAwICmpqZ0/vx5SdL6+npHEQqe2VEFcv96RJd0ShTZ4QMP757BySSHak7SjIyM6OzZs6HE+/v72t7eDsHZ3t7WzZs39cADD2hra0vpdDq2wzkjjmKgaG71q9VqLLb34fazmIjbnGhhYTlhEXiJMOLdgMwjIyPBkqLE9Xo9KpiI5ZNemXEzLoQbg8H8wfCWSiXlcrmosvKTCXt6enThwgUNDg7qP//zP5VKpcKA8awudA7HGROeGgjNs0LcAVFJazJ3Hq44QnNGOJmv9bFwJbMQGNxmsxmKTIEL8wVBR47ZkSHVgltbW1peXo6jhDzs8UyCpyeR0dnZWbVarVBaQkG+izVzhIrBcjY9eZ0KRZZeu2XQLTKWXWpvCGDhbt26pc3NTWWzWc3NzSmfz2t1dTU8AzXNe3t7unHjht761rdGkb8TFFhl4LWXYOIJffM3ltpJFV80UIMzvQg2bDKQ2EkZGPlKpRKfx/t6NZWHAw57ndnEQFAc4aksFLNUKnWw2x7KVCoVTUxMBOsstbuaYCRZCxANeWb3xCgiJBbGkjmm7Q4VXRg6nhvlPjxsH5YnvRZqJpXYYbTPyfHxcRzmhwzxfg81gPfDw8Pa3d2NrEe5XI7Yme/lO5z44vswAnNzc5qZmYn+4hSZAKuTMNyfCw7nTtepUeSkNcVDumdLJsR3dna0tbWle+65R5IiTr5586YkRR02k7u/v6/x8fEodMcSOqkGVJcU7V58M7xviezq6oqyVYyBM7t4Dk81SSdxFULt2wvx9uRtPeXj5Aev4z0gg/CWbiB8UwKX9zJj3IyTtUCJVldXI8ZE0cgSoJR07UDBPE50osaVg00OpA4938//CTuYX5SM32GTk9CavzNveEfPrXslWZKBZ/96oVAIJQVVcORQq9XqaCLg8gmX4iHixMSE7rnnHp0/f16Hh4fRtwuD4pyJjwmyNLmGyevUKLLUzsH5QyTjE6mTDaSvdblc1sWLF/WWt7xFL774Ygd0JharVCr68Y9/HDEoiufF7rDFeCCUkYnGWhMTI7ySQpnq9XrcDy/suV2US1IHlPPOJFIbJiNIfDfwFU/v2yFhcr2fGX9rtdqtcphXh5/eXIEYF8/voY63ECYc8TpzZ4upcQbteB14Ot3eLeWlkczf5OSkpqenVSgU1NXVFVDc03PMR/JCjii/9foBwpiBgYHwtqw3suAMPiQjzQxIPXGkEEbb4T/fSfx/+fJl3Xvvverq6tLKyopKpVLch73vSWILYwDier3rVChyUlndO7sl9hgCr0M1EvWq999/v/L5fJTO1Wq12IfcaDT0r//6r3EW1Pb2diyqb+Qnh4hXgQhBCX18vIZCHx0dKZfL6ejo6I6tYJ2I8bympBgLxsMrohAWXkfxPWZ1KO6FCIQHfJ8jDdIeToi5F8Xr+RiptHLjlEqlOjZcYJT4P+PwpgjsWltfX4+iCDiAmzdv6p577tE999wTqIMdVI7UWAfkgjEmlXxgYCBCLgyxGzmUD8gvKcaSSqVULBZVKpWiBt6RE59nbZmXTCajCxcuaH5+XuPj4yGnHKqQZNWReYyOO7bXY63f9H7k/z8vFMNjBB7OF8Nfd/ZxfX09LN3U1JSmpqY6NoRj3fh9c3NTe3t70TuZKiqpTZy4B2axgGIUdNCAgCodan+TaR//PBBN0muECfjvTDPeAYOCl/aWvCi59yRD0SB3fNeS52m9+ghP6wUTeCW/ktsB8V4+Zp4p6QkZL/OXTqcDYtJj3OP+a9euaXV1Vbu7u9Fkz8MO5Af4TGjCiRPe1ZK/89xugJ0bALk0Go2oVqOmYGRkRJIiRkb5b5c66urq0vT0tM6dO6fZ2Vl1d5+0wi0Wix1HuDqR63KeNOSvd50Kj8zleUdJHflSt3YILgTU1tZWR9HCXXfdpR/96EcBc9kdxcICl3p7T5q0UYrHMSMsisdXjgyAiV73DGFzdHSkmzdvxgInC0dcSREqBMINF4LmBs7nAuFFoRyKOfR0LyopvDhHxAARERju5R08GWM6ne4oUvFncnLLe1lTecX6+nz65otk+StXo9HQ4uKipqamgvUnvcZ9QRQYuHq9HmgKGYLwI99Pjth5DJCd58qRB7z02tpaOAI3KJ539zwy+fGhoSFVq1UtLS2pXC7H/mUvO5XUIeMe9uG573SdGkV2S47SeEI9Sfx47o42pWzQvu+++/Sd73xHxWJR6XS7eR0WsdFoxNZJ0i4Iqn+fxyUYGPeuCFQmk9HZs2eVTqd17do1NRqNEBRPS0ht8gIhc2HjQsn8mTk/CI8stZlz9zaQYigz8ScKSnsdoB+b7zmHSGp3HSHtARxGmHgWTqp0wXdugLExllu3bsW5xfyNHCrKgqKDfiSpWq1qfX1d+Xw+ykuTKK2rqyu85NHRUYRWKNX29nbsm8ZoY2j29vYia8G9MCqcoHh0dBTwHyXzcAqD4HM0PDysiYkJjY2NqaenRzdv3tTKyorK5XI0v/cQ5HY5a3TDofftrlOjyFIbMkltyOjWPBk7s4j7+/taXFzU4OCgxsbGdOHCBZ0/f16lUim8L5B2b29Py8vLGh8f19jYWOxIogADL0TlDjErcJp/eIH+/n6dOXNGg4ODevHFF7W8vNxR+eT9shBuXxjvAgKxREqH0zHcezk7iyHDGztRhgLixZvNZgecdSgNfAZpgESGhoY0NDSkzc3NWANvkMc6kXNFoYkrYZyZK4/dEXrSUqAP5uzg4CAKMyCZPNfuBpB58IYA3MNTQfRB9xJdFNaP16HUlLXnXhBTng3wXD6xLeHQzMxMFLrs7+9rbW0tuoog7y773MOzHBjyJDGZvE5FjCy1q2AcPpAzTrJ2zh6zUYAGeTs7OxocHNQDDzwQ1VKwkpT5ra6uamNjI3KYXmnkcZ7UWawCwzowMKBcLqdsNqvZ2VkVCgW98sor2tjYiM+wPRIv6BAJmIYSoeRAaiAs+XPm5fj4OAySx7V4IS9C8Koz8pigEqnNbu/u7kZLH0lh2PL5vKamppTNZsN7YSwgvlAG/4cnJy+MMqPE5XI5FO3w8DAyC06YOaQkTeehCvLS3d0dLZ/K5bLW1tb0wx/+MMougf8YP+SA+5DtoIKLeR0aGtLY2FikFovFYsDpZNWhV7k5r5LJZDQ3N6e77rpLqVRKi4uLQXDxj886keleXeokgn8iaq19sE6WcHnqxb0aC0zMy8JevnxZZ8+e1SuvvBKCx4HYOzs72tjYUKPRCKg3MjISpZuOBtg0QQcSUgUDAwPRf2t7e1ubm5uxAM1mMxhxUll4Uy/0Z6eSpyy83JN5Qagd7kNu0erGPwek5PN4bM8X+/ZKkIHH7Ds7OxoaGorTAan5dgEGubh3RNhQcjdI3LfRaES5Jt+DUYb8geDjIv516FqpVKLartlsamFhQWtraxoYGIhtrcw5ho254fgYdwqED6lUKloyra+va2NjI7Y1Aqm7urqCb2GcKGF3d7fOnz8fJ1DwzPV6PY6sYb48Hy51lnUiS06I3uk6NYrMZHickITXKHCy9rTZbKpararVaunSpUvh5e69915du3atg4XNZrNqtU5OYdzY2NDExERUcrEzhvE4g03uGeg2MDCgixcvqtVqqVQqxefo+UQqh+4bvkHh6Ogo4kueDfgrtSuyqHBiHCi8Qz7u7wjF5wZo5rCce3lbGTy3x9kc9k0cizKwNvzjPp7iwisBjdk6Cjl5dHSk0dHRDkabRn/MBd/p5BrGgxa0rBl16ZCOkJj1el3Dw8OhUFSl0cgeQ+7xPVssb926pWKxGKdJeG7cwyb3yBR/TE1NaXx8XPl8XteuXdPS0lIUf/iB58h7MnPjxChr8xNR2ZUkCvxBpNf29kWo8Sa1Wi12s4yPj6tYLEYzNz/8mte2t7e1tLQU7WOYLC+uIBYaGhpSPp/X8PCwhoaGtLW1pRs3bmhvby86RCRTLMS3eARYU2JRvL2kgNYe58KKEtd6rtvZdLYAMocO4T3dRAEEng2UgrdGKbkP8BYlcqTkJFZya6d0EouyPxrGHkKLuS4Wix37or3YA6TgBtt3VVGZR1hBvp5iE87BYjyMd3BwMFhn5qxWqwUC8E6dmUxG1WpVpVIpQgG8dldXV0cvMb6j2WxGh5N8Pq98Ph8NMDC8IDXf3cX43IiyDqyFK/ntrlOjyCgSA3ev4tBT6iS6urpONmkPDQ2pUqmoXC7rzJkzunr1qq5cuaL+/n7V6/WY0P7+/mgkVywWtbi4qLNnz3ZU0QC32LRAsTtQieM5V1ZWtL29HUdvUszgbXzYosgmfoTL0y0edzpMwzjQKA7l9jJD4CLzJCni+EajoXT6ZJME90dpKeog9+xkizPWxPG+xzlpRN34Yux4BmJVUI+X3pIzR0lBK3wfSANPf3h4GBAVAo259oPoWq1WFJdQ++1EHqHP4eHhawpb4FTK5bLK5XLHxhrmDpThBhOPOTIyoqmpqegqu7i4qO3tbe3t7UX+2OEzhpnv9/QicuHO607XqVFkhBoYycO5crvHcmUGGhEz9fX16cKFC/r3f/93nTlzJqARkAzoXa/Xdf369WCKYSLZSC6pI5bs7u7W1taWarWaRkdHtb6+HpsbKERAaCCYgNV4ZhhMih+8XthjzGTrVQSQuNvbA6Ek7ikpPsHDSArGmt1a/F9qHxyGsiNYMPR41uRYmfv9/f3owuLemFgQ0oo8rXsg3o9nBOp7dxYqonhW3s+6ZrNZHR+fNEE4Pj7Wzs5OMM2sHeueyWQi1yydeFPuTa8xlA9FRg495ZREi/39/ZqZmdHMzIwmJia0s7Oj9fV1LS8v31aJXb6ZU/7veuHG4k7XqVHkpNXxpDgWXWrvkuJ91OiyKK+88oqGh4f14IMP6qMf/ahefvllFYtFXb9+PRoF0L1QUhxOnclkdNddd2l0dDTK+DjJHhhOTFav11WpVGJslG86s0wXDhQin8+rv78/4BvCTLyEkPFsXovtnhbG04sP/DN4OCcE+d3TQYODg9F0ELaYK9kNhfs7cnB2me+mQMZLRnt6eqIe2bd+enMDlNbLYm/duqWXX35ZmUwmtnXu7+9HZRXvc6hNU3nQFKEPRojtmjwfSMb7iDFnOAUQCwec37p1S6VSKXgQ7kdsfN999+muu+5Ss9nU2tpaKLCXraKYTuomayhcxlHinwhFll67gdrhtEMyV3YsVrValXTSLJ8uD9PT03r/+9+vCxcu6K/+6q+0uroacQxK2mqdNLBfX1/XO97xDs3MzAQchNkmB+hpEE9FOBwdGhqKdqxAtZGREV28eFGLi4sqlUpBviTjIiqXGBfei0V31OJ5UBoIAJmJp4l/gZzs7EJpQR18rr+/v2OjCik3LxPEcHiFFgU33kAQRQG+Su0Gcu7tEdBkWNNsnrRZpj8WnpFcsfMYqVR7rzQEY7PZjDUGVZGiZNMIawB/gLzxfRsbG6rX64Gsjo6Ognn2MK+7u1tjY2O69957NTk5GSWdHC/jZBlrmEwvJQufmF/nhk49tGaBPZhHML0KiMu7M3oaitYpKysrKhQKSqfTmpyc1IMPPqjFxUV9/etfj1h5bm5OPT0nvZJ3dnb0yiuv6NKlS3r00Ue1tram4+PjsOZ4GH46c0u8JCmIMWAqh5BNTk7GuEdGRl5jnJxxxpjxfSwsBi7piREC4KnnqF2ZuX9fX1+kmohF8Yo+305kMd/MMz8JR46Pj8N4ocw8B54T5hrlwUCwtjDWXLzXC1ycfacP28HBQSgxyki4QLN68uSQnnRA6e3t7Th3K51OR0OKSqWi1dVV3bp1K8IF+BAMBYhiYGBAY2NjmpmZ0eDgoLa3t3XlyhVtbW2FfMB3eDzsxiBJaDkB6SnXO12nQpGl1ya7na0DrgGJsMLkTh1u05RvaWlJY2Nj8Z6f+7mf05UrV/T8889rZWUlFKq3t1f5fF4bGxv65je/qVTq5Bymer3ecXYUXpPJZXGAVngkPMzo6Kjm5+ej9JGSPGd/gZSSIofp+WDgppN9zuR7AQG/+xGiLhxeXOK9wfhuOowyPhScOLRQKMT8YjyZA0558JpxjALoAX4DZWU+ec13leG1QAoowfHxcRxdg4Hh6CJvdA/Mdk/d19cXrWzr9XrEvV7ZB6PfaDQ6yn4HBwcjdeUFINLJ+di5XE6FQkGFQkHDw8NBrgLt4U48b59cy6SSYlBdD069IvsAeQAXVi63aD4RHg9SR7u2tqZcLhex57lz5/TYY49pcXFRlUpFCwsLymazmpmZUS6XU7N5spXuueee0zve8Y4OYgbrCIOMACOAztKygYJ4++bNm5GL9LayKBGCmoSWeHV+R+jwVMwbBgGlYM4Q3lQq1VHs0Wqd5NC7u7tjk4fU3gYIkuB5+A4vrWQbH8YAwUQZUWi8LMYKz84aHhwcxPEuGEiU342Xx5RufPP5vIrFoorFYigOGzCIm0FdzGN/f38gLe9Mkk6f7FenYIQ90V5MAh/C3NAcIZvNan5+Xvl8Xtvb23r11VdVKpViGy0MOcbJL35n/u+Uano9JZZOUYkmQgiU9OKFJIT2fKanqrDSOzs70ep0c3MzTkt4+OGH9ba3vU1dXV1xuh4bKzKZjAYHB7W6uqqFhYWO1ipOTMCek/KCJAHqj4yM6IEHHtDs7Ky2trY6jp3BIJBKkjpJKi9VlDq3KHoZJoqLcKHM3AOBZR7ZZECM5t4H70adsW/r5D6eInLmGniKsjJfzrBT3pnc6ggkZV6B3DyvPx/3Yt4466mnp0fz8/O6++67lU6nVa/XVavVwuMCgWG2j46OIi2FkaDoxjmHcrkc3j+575vwx+P7ycnJODGCvDOHvznJJbUVVupsa4zigsY8l8ycvp4ynypFdmIHpeFyK+0L7vGiFzLQJG1tbU2VSkUrKyvq7u7WBz7wAZ09eza8RqPR0Pb2dqQejo9P9sBubm6GxZUUnhZ2FsX0BvADAwPBWm5tbWllZSX6MqFECESr1XqNd+J9KA0KmOzXlIRZCANhBlCfdBpEFj+ZKwSGPC1GBOPDmngZKXMhnWQMKLBBCTzWdu8KIvBn4L14QQxIT09PR9tePucdX1ib4+PjqHlnrMnto4eHh1FKms1mY25IlxUKBY2OjkpSKCH5d9a4u7u7I33EvI6Pj+vs2bPKZrOqVqsRQhWLxdhMgkFGTqT2Bgsnbh1hufIzX/578jo1igyE4sE8ReO5Nn+vK4cbAUnBPC4vL+vGjRsR/91/MAEGRQAAIABJREFU//163/veFwtTq9WCzYbt3tzc1OLiYlhsIBaxFMd4Imx9fX0aHx/XY489poceekhra2taWVmJLXMQHigMsSzeBsEDMru35ieLzn2cNAGGHx2dNNrDKDBevA7PQqEKCsL7fCsfRBvwnLF4TM69iaV53/7+fgixe28U1qE6nIef7EDcjOFIpVKBqnwOffsnCkoOvb+/P7w2z8d3c6LFyMhINKVnr/DW1lbE9Mgea7K9vS2pHQ6l0+no/OHpTNKUzIE/L3PHnCW9rCMnV+43ut5UjHz9+vVIyRwdHemRRx7R6OiovvSlL+ncuXO6ceOGPvnJT0YK6I/+6I/04Q9/WLu7u/q1X/s1vfDCC697f4SLh8VaO2T2lAhkjlckIUjAlOPj40gd7O7uanNzM3YAvec979F//dd/6fnnn49NFNVqVZOTk7G1cXV1VfPz85qfn5fUrgEnLuQEQEkaHBzU2972Np05c0ZXrlzRSy+9pK2trQ6hIw2CV/CzjpkDngmPz4JL7aNOvWk6Hov74l3d6HH4N0JIQ3W8NgUfwHm2D5InHRoa6jAEeGZfH4yKV1pJipiZfygV6wn8d9KPOSN+97ZL1E6PjIx0dD8hzzs+Pi5JsdWQcWPo8LIYZdKFa2trWlpa0ubmZhQMsUebeJme36zJwMCAzpw5o3vuuSdi9eXl5VhXHImHgx4Hu8dNEl5vNuXk15v2yI899pgefvhhPfLII5Kkz372s/rHf/xHXbp0Sf/4j/+oz372s5KkD33oQ7p48aIuXryoz3zmM/qTP/mTN7w3QuAP4LDZrRhQDU/EPy8e8Vrd7e1tLSwsxIbuhYUFjY6O6oMf/GAUf7RarWg6TkO2/f19vfzyy0F6ZDIZFQqFaOnDWb3ZbFYTExNaX1/XN7/5Tb3wwguxD9ohlbO0vkfZn5dY0tsDSYqqKASW96OEkDbE0swB98hmsx0expULQ8H98cRscED4GYs/i4cZDukh5lgzJ6oobQRlJWsH+IynphB6YDiIhXQRv3OsKvE9Mbqk4DR6enqi7Dafz2tvb0/Xrl3TjRs3YuMNO8pu3bqlWq2mUqmkSqUSY6Ps9sKFC9FPrFwua3NzU7VareN8Z8YpdZ5YgXx6ZiZZIIJuOD90p+v/mrV+/PHH9bM/+7OSpKefflr/9E//pM9+9rN6/PHH9ed//ueSpO9+97vK5XKamprS+vr6G97TFdqZOxSAh+Y1vMOdkurkgtPptJaXlwN+bW5u6oEHHtAv/dIv6c///M+jMosdSaRStra29K//+q86f/68hoaGND8/r+np6SCsms1mpCrYheNVaHhjjxdR5J6envA2EEX8xIDxfs9T88zMFZ4rudXx8PAw6o9TqZRyuZwqlUooGWkaT5kRQxOHHh8fx5GhzL17YtJYvsGfOJYiFc8N+6kYeG+IN7yy736iGwf3OD4+DpLSO5HiAR2uk3UYGhqK3uZOrKVSJ6d0rqysaH19PQo9UGLquqvVasBtQqJsNqvLly/rvvvu0+DgYKQq2e8MuYZM+7ow3mQo6NmapFJLr994T3qTitxqtfTNb35TrVZLf/Znf6annnpKk5OToZzr6+tR9DA7O6ulpaX47PLysmZnZ1+jyJ/+9Kf1mc98RpI0NjYmqfPEAB7IC0Ucgrh18lRUEvoBazc2NjQ4OBhHxoyMjEQ66m//9m9j4tPpdDQN2Nvb0+rqqg4ODnT+/Hltb2/rxo0bKhQKGh8f1/HxSU0v6QUm3POsfs6U1HnCIzEt+3E9zgR2osTd3e1zfB2FcA8vmEB5vfoqn8937FAiB+twN5PJhFeXFFv8II6AtL4ebmwhgzzVw4Xhw5ChzMyTZyu8dTD/97GRYsJYHBwcBDsOHOb0CsIBUBAGcGtrS+vr61pZWdHa2pp2d3eDDScePzw8VKVSCRQBMhoYGNDdd9+t8fFxra6u6urVq1pbW4tiESe4kjDZPbDLuSu1e2DmweX/dtebUuR3v/vdWl1d1fj4uP7hH/5BP/7xj1/znjeL5bmeeuopPfXUU5IUR5J4YJ+0UP6alzb6g+LNiMf4P3W3a2trmpiYCFg8NzenD33oQ1pZWdELL7ygnp6eYGzz+bzm5ua0srISz5dKpSIvDDnFZnfIIooY/MgRSR29pKWThaUeO5Vq10E76+vP5RsniGN904TXaTMe5pL9tUNDQ7GpH2Un10szOGeWb926FbXNe3t7ymazHcSj70NOpVJRLIIiQZb5XmbYXk+BQR7x3BCEXr3nOfXDw0PV63Vls9mI4YHRPT09ymaz4eEhEjEKVGhRO08ZJd6b5yCNRZ049emSND4+rjNnzkQPMWr4yV97FxOHyt4gANjN3HlhU9JTJ1+73fWmYuTV1VVJ0tbWlr761a/qne98pzY2NjQ1NSVJmpqair5OKysrQRBJ6lCGO11ufbxs8XbBfpK2ZzIQBH+NxQfuUT/LQlUqFc3MzOhTn/qU5ufng12mNnZgYEATExM6OjqKApO3vOUtmp2d7egm0Wq1wopTuO9wmtJBLso+8azsVSZGdrYUOMrv3A+BQ4hAL9SRe8756OikkQEEDowuikSZI/CUaiSegTQMCADUgwKhJBguUlKkvHxjB4wyRhrDBfIiTSQp2tFKCriMN2aNUM58Ph9dPSACkRdQANB8aWkp4t6trS3t7u4G+QV0995aXV1dGhsb09jYmGZnZ/XWt75V4+Pj2tnZUbFYVLlc7thgkZRPHIpnWrjc27oT82yM68edrjdU5EwmE5VLmUxGH/jAB/TSSy/p2Wef1RNPPCFJeuKJJ/S1r31NkvTss8/qV3/1VyVJjz76qGq12hvGx1gkJ2OcEJE6E+IIDH/z3Buvu5K1Wi1tb2+rVqvp5s2bevXVV7W5ualXX31V1WpVMzMz+j//5/9oeHg4+jhxvg9NBer1ul566SWl02lduHAhNj4g1F5W6VAOJWARKcLgOTAWCDjv9VjXC0r4TryuHwbnKS0UxRv4p1KpyJcSj2Pw8KC8D2+NcXQImCw3dGIHr8t7UHQ8sMN7YD0pKwhAjDKeGoXHWFAYUi6XQxF5BuD/wcFB9JCu1+tRNgmpWa1WVSwWwwhK6mgcD2JBDuk6cu7cOd1zzz3q7+9XqVTS2tpaR+cR78XlCukG2lNySfjtfAUy4FzQna43hNaTk5P66le/evLm7m795V/+pf7+7/9e3/ve9/TlL39ZTz75pBYXF/XJT35SkvS3f/u3+vCHP6yrV69qd3dXv/7rv/5GX9EBqd0Le6yQfGAEFeuW3DiOkOERqPTp7e3V0tKS+vr6NDc3p+XlZZ07d06XL1/W888/r3K5HIpfqVTU1XWyKymbzWpzc1Pf//73wysyJz09PWG9gYNexEGJJPAbYUcJSIdsb2+rWq12kEp4FpQXUgz2+NatW1F9RVyPElKRRO/qg4MDTUxMqFwux35nLztkE76kDgXOZDIqlUqRQsPD4dElheJ64wLy8Dxvsq0ODRMg3pg75pXv8H3o1EpLivp2DpQDRhPfMhcYxr29PVUqFRWLxTiaJhla1Gq1jjJMxlKv15XJZDQ1NaXh4eFABFRwsTHDQ0F3KL7rLBkbo6hcrrw4BrIQd7reUJGvX7+uhx566DWvl8tlvf/977/tZ37jN37jjW7bcSWDfX/d/+6XC4SnapxUkhTEDYKwv7+vSqWipaWlUKZsNqv7779fv/Zrv6ZvfOMbeu655yKtQeM5Nq4Xi0W9+uqrmp2dDQIGoeRyL824IGSkNgvP+FqtlmZmZrS4uBjeC+8Dy+qpNbw/Qrq7u6tsNquRkZFoXQP8dmWv1+vK5/Md38U9MZp9fX1hBKhmIy732JvwAYXnyFHvm40nhXVGuZkjtoJiFCG2MMZsgUQJaFPLmh8dHalcLkdhimc1uIeTi3hmqq9IPTabzY6dVK5woMVUKhUbS7a2tnR4eKjFxUWtr69HWyHCBJfVJIHrIRI/4Q+SDstJ3f9PWOv/jcthMR7ZKXsuTzP5hUAllR9hlhSxYk9PjzY3N6McEGGbn5/XL//yL0uS/vmf/zksf7PZVKFQ0PT0dEA1ThAktoLM8HJNwgE8jZf4UXlFsQJeGXLICyQcZQDbfMcVsBRl9vQT3gWlqtVqKhQKHSWExL4cqg6E9xpqQgM8LsoMaZdKpToOKUcJ8IYIrOeFMUbAecII3wqJV5YU8+dVdrxOjt1JP8ZDiNFoNILcwoDyvU5SgeRQyp6eHuXzeT344IO6++67Y37hVCipTbY98u2RzB//Z00wFKytKzTy79zPna5TochYRa4kvHaBSCbMWSh/HaFNsoEoLW1Ql5eXdXBwoAsXLuill16KSq6Pf/zj2tnZ0YsvvqidnZ2AhpwA0Wq1dO3atYBanCSQjFGJBxk/TfYQTpR2Z2dHqdTJyQRbW1shAIQLzhQzNzwXaZ7BwUHl83lVq9Vo00q+2rdEoryDg4ORfkKZ+F48HKdLUhXm8Jk1y2QyMTZIPbYGEnI415Hsn81a9ff3a2xsLNAIRoV2xHQawTtzjrJvj8Rgojx4/UajobW1NdVqtYDAXgZLRiBZLEPBSy6Xi9LeXC6nV199VdevX48dTrQXcnlGDt2rIqvIrsfKni71z5C9eCOy61QosnR76JAkrJzVQ3iSCs4DM5G+k4bXyaECFw8PD3XmzJko/p+ZmdEv/MIvaGNjQ0tLS0qn05GWAmJDiuBFgKxDQ0PRxVFqd9W4XWxIZ41SqaSbN29qenq6g7zyKi28IKkbFKbVaimXyymfz0dPsJWVlbDuvosmlUqpXq/H3lxavgLVWQcQAwenoWxJAUVBiX1BI5xYyMZ+BBOPB/tMQYvvZb5165ZyuVyEKm6Mh4aGopy2Wq12QNXu7u6ouMPYUNhCDIs3Rk6c+edyeE4p5oULF/TQQw/p+PhYCwsLunr1qq5evRrN7ZEhni0pry7b7rExhu6F/TPMr6/jna5TpciubM7ouXJK7fgCwb4d3c89IUuSE4QC8jeU5ezZs2q1WhofH9dHPvIR/fVf/3WQUK1WKzpUFgoF1et1NRoNLSwsqFKp6PDwULOzs1FJ1NXVFd4MxXRGGwXp6+uLopozZ87o+vXrryHukk3wUKCRkRFNT09rYmKiI0dLy1/iZYe8VLAVCoWObZZwCNRV0/geQcKwwkb7xgbvNFmv1+PonLNnz+rBBx8Mtp5tgcBx5ooKPPK19OnieUkzHR8f60c/+lF8H4hgf39fxWJRtVotPLU3o/f2uBhVb+TvMoasZDIZTU9P6/Llyzpz5ozK5bIWFxejgATPTv4c2fOY2BXV43d+Qjj6GG6Xen09byydEkX2OMEfOPm7P0ySAEvWr/r98BRYSz4PS8kC37hxI/LNDz30kN7znveoVqvpG9/4RkBgz4MSkx0eHsaRItvb25qZmdHk5KQKhYJ6e3sjxwxz7SWVeKparaarV6/qzJkzGh0dVbFY7GC3ebbj4+OIjTnrCm/qh8dhqEgF4V2Aq8ViUYODg8FUe+xKWADUBqkQy7pRdQa7q6tL4+Pj6urq0tbWVtSMs4fY2+8ODg6GN261WrHBHyPn/bYoIyU1NT09HR5WantOXiMtx/hJXUE4MucYAyCuE6bNZvtcr7vvvlutVivqrvHslGbeLobFCEmdHUHcGyf5IO7jmyvcsf1EQOskHX8nBltq928ijkCIuA+vSQomlv8DZ7xiiDykb4ujyudd73qXisWi/uVf/iU6NErS8PCwUql2fpB+y3T1RKEnJiaUyWSiXhfyi3QQgjA4OKhisahMJqOxsbGOA7ndY0L0eKEJaZV0Oq1SqRTIwdlx5ou4DyXhmFTYbrwBiiMpFGJnZ0cjIyMxLgygG8pMJqNMJqNLly5FvE27nWw2G9zA5ORkKBLembllrMTHpJUo0snn88rlcgHf8YrMFdwAPzEmbCslXJE6T3TwghyKTB566CHNzMyoVCrF8TFbW1uqVCodh7p7MwBkjK6hxPBJuePZnBl3OYXU5JleD16fKkVOWiInSTxt4Qx1kq5PToZDZ499nNEmH8r3w1Sm02ldvnxZjz/+uOr1ul544YVYOJSPrYADAwORqyaVATs6NzcXO62AqjSrQ1ilE9ayWCx2HGNDrMei4qHZC40hoNZ5e3s7vDLPS5yKwEBm1Wo1SW2W1quhOB2DOJq4HiFHuFAIxkaO/q1vfWvE2Ol0OgwjPbAoo0SpkgfosYEDL+0pmomJCU1PT2thYUG3bt3S0tJSwPxUKqVqtdpx1jWG1effQznnUZrNk33pExMTeuSRR3Tp0iVVq1UtLy9rfX1d6+vrwZKDsqTONKeHIC6LblTdYSU9dNKZuVe+03VqFNnbwEidcbCzeP53T7h7Qp33uII4pe+pKZ8cb2Z+/fr18Gx33XWXfvEXf1GtVkvf//73AwrjEYaHh6MoA6tbLpd1cHAQZYCXLl2Kqio8FLXW7ALCm6fTaRUKBa2vr0fcy70xMjDwwHMKFLyvs6ePJHXEcrDc5XI5tinydxSYXmagiK2trSguwZj4yRkoUKFQCHhOio4TDymuIfXmXgcmOp1u77H24pt6va6hoSFtb29rfn5e999/vxYWFnT27Nlg59fW1vTiiy9qbW1NmUwmOl+ixE6UJnO0hC2c5vlTP/VTkqRKpaJSqaTV1dU458tj4yQEToaCHh4mQ0XfHcblyp3MyNzpOjWK7Cyf1PbQCGtSwYk7nEBgkXxnjdSOp4EvwBq/DwtB3rXVaml5eVnd3d1qNBp68MEH9fGPf1ytVkv/9V//FULqRflsZEin2+dRed+oubm58NyMj/GmUqnYLURTuvHx8TiNwvOaLDI9mn1zBkoPUvDSS5AHiGZ+fl7pdDr6WEFgUY+N8OdyOaVSJ9ViW1tbUVIK0kGwi8ViEE0o4NDQUEe4AonmqTNQEd7eYTH5WQ4MaLVOyjlXVlY0MTGh8+fPB2RfXFzUzs5ORzwOQvGsAfKSzOfC5p87d07veMc7NDg4qGvXrmllZUXLy8tR3YZxSCqYF3cgQxj2ZNiIXN8pvvbL0cKdrlOjyF4R4/AiSUT4JEmdsTXvceLLJ889uysvf/PCA8bS29urbDarH//4x5qfn9fHPvYxHR8f6+WXX45dODC92Ww2KqpgmWu1mjY3N7W9va3d3V2Nj4/HwkLS+BGi5EzHx8dj943vgiKu8j3DMLB4aofQFIx4vyiedWNjQxcuXNDk5KReeeUVDQ0NhTJj7IaHh+MYFU7K6O4+achOJRSCRuFEoVBQNpvV6OhokFBUl1ELjYATI7JZ35XC2V0vd202mxEWTE5OKpVKdfSr5ghYToRgjC5DnrpCDoaHhzU7O6uHH35Yly5dUqlUis4fa2trsV0VSO0yyu/uQJLELa/fSXmTzLnrg+epb3edGkV2aOzwxB+AiQJysdjJ2NprrZPwyS8mzL08BmFvb0/d3d2qVqt6+eWXdXR0pEKhoPn5eX3wgx+UJF27di1SEN5yFbaWJnGkdVZWVoIwIsZFiFHIiYkJ5XK5gIa0IsKTIkSQRuRg3aN5GyLmAgXAo0Fk7e7u6t5771U6ndaVK1eiOmlgYECDg4OanZ1VrVaLvG2z2QwYT7UazzE4OKihoaFoZoc37u3t7dhkgtCCnGjBRDzssSfxuqQol+V7JUWRB6EGa0BazbkP96B8N79TkPLAAw/o0UcfVSqVilp7uIxmsxmGIeloXGldfh3C+/iSKVN3Rsi180OuH7e7To0iS52HWjlBlVRy3uuK657VrZlX0/CPifWkPO/xpmjEdYeHh5Eu2dvb0+TkpD74wQ/q7/7u73TlypWo4MIroSzAW7zX9va21tfXVa1Wlc/nw2MBZ4eGhnT//ferUqnoxo0bunz5sgYGBoJVl9r5aGJCSk6pQMrlckFQ0WctSQ7Sogj2d2dnRxcuXNDg4KBu3rwpSbGvd25uTgsLC3FSA4J9eHgYlVhUZk1MTMS+50KhEIfFUd3lHUB8rkEvKJjnUZ3QpFEAmyIgylAmCESQCSWdKHmy4IKcNQbz0qVLeuyxx5TNZrWwsKDV1VVtbGxEXIzRpjbBd7UlWfckoeYO405VWo4anYz1uP5O16lRZMgNqTPmkF5rSV2ZvVDBJytZcsfk8XlnFl1guC+LhWVfWlrS/v6+Ll++rJGREc3Nzemnf/qntbe3F+V6x8ftXsh4T8gq7s2eZfLVPT09Gh0djVjvxz/+sXZ3d3XfffdpZGQkzg4ChiKYLDSnPFDZ5EaDA+eYN1r+Tk1NhbdkfP39/br//vujW0tfX5/Gxsa0uLioV199NdoGe4cQTn3o7e3V6OioCoVCnCONAYTIg/RibpJNA7y6CkacsIMOKMS6GIZms9nREIAceT6f1+TkpK5cuRKy5YpDnvrixYvKZrNaWlrS+Pi43vnOdyqXywVDXSqVtLCwEAexUVTisa07EVCRM9aunM7rJBWf9GKS63CZvZ3yc50aRUbY3QJJnSy11Am1PdaUOic1acEQZu6BECXZXxbDK5aot+7r69Pm5qay2awymYzuvffegH4//OEPVa/XdfPmTU1NTUXFEUJJC12vty4Wi5IUsTbbDB988MHITZPPpEYZL9TX16fR0VHNzMyEoHDY+8zMjHZ2duKUSuJeKtIkRecLSdFogJ09vb29evjhh3V4eKj/+I//0LVr18KYwE6zlW9oaEijo6MRLlBeSfsePLn3iGaNmW/mnjWjzpx6bFAaaIROJbD/hAxsW/ROmRgIkAk537m5OV2+fFlLS0saGRnR29/+9oiLOQZ1YWEhsg8eg7s8Mi6ex7MjLqv+3a6U/tNJMQ8JX88Th/684Tv+ly6UkcnAEvFa8nep02P7AyeFI2n5PA7x/LJDeGc5+f5KpaK1tTUVCoVgoX/qp34q4s3r169re3tba2tr0YYGSE7jdzYSQFbt7u7q/2nv2mLaPM//z8ZgjjHGHAMEjAJL1lWITG1SZVt3aDelk9qbrs3FtLSdOm1Su8PNgiJN6uVytUaalEldNW1SJhqtypZKVUS6dHcNZQlQCMFAOBQbMCYcjSEE+/1foN/D4zeGpv8cYJEfyQqxv8P7vd/7nH7P4Q0Gg0n+7ejoKMbHx+U8orsAkhDyeDwuISoyBQvnmRMObGyI7nQ6MTc3J4KA9dFE0isrK9HT04PW1laJX4+PjyMajUrKo/a1nU6ngGEejwder1eEoO5AQo1PZmYbHy3ktFmtt9bR1V0rKyuCOxAk41gWFxcxMzMjVkJubi6ysrKSSkdpJWRmZkoLo9zcXFRXV2Pfvn2YnJyUjddCoZAIQjsNUwNdfCec580Y0M7Bts1xDfZqjEe7RVvyz5a/PkSyJ4AD5wRo80JrT83gtnltx/hoxlGyc+Fok0VLRjIwJ3RpaQnz8/MYGRmRxuZVVVV44oknxJTv7++XkjiGZpaWlkRDkwnp2xIIYtua4eFhTE5Oiv9WWFgoPcZ0w3kA0rKI7gX92pWVFUxOTsp5tDy4JWlBQYGYpQUFBdI9hRu/x2IxBAIBOBzrPcpYdKAtpqysLBQWFsLr9UqqJwUaf8/IyEBhYSGA9QbyWtsy51r39mLxgd6Gle+fQoSajiAWLQ4KRroQGijURf2819raGoLBIEpKStDQ0AC3241IJIJIJIKxsTEEg0Hxi2dnZ+8II1G7kmwtayPTtrLRWJD9uwbDtHL5n8ns0qSRTY1WAxAGpO9jgxj8Tjfg0xIPQNI5dvBdm97ARv42X6ox6xVSBL/q6+tx4MABAZfY0D8SiYjGonYxZiMJQLd/0Y3/CCZRo5HhWeXERBKaxHxGIttMhKBAIZBEN8AYI43YKVhWV1dx48YNxONxlJWVITc3VxJfOK98F2QWMjG3b+F8Ex8gqp5IJCRBhQzHubX7erEBAtNHdYIIALEoOAYKNwpG+tuRSETQd2agacssEomIIPb5fLLFEENNdCG4F7NmIq1U9LrUSSypTGJ+nyr8ZCsj7R5qBH8z2jGMrCWdBgW06csH1A3ZNGpoAwI6mUSj2BocA5JNGa3xqYG0sGBMdmRkBLFYDHV1dcjIyEBpaSkOHTqE8vJyfPLJJwgEAhLHXF1dRUFBgWhIAlYAJOZJc4+JJvT5mHhQWFgoXS54LW6JQrNRMwi3QWUyCXOBV1dXMTMzA6dzYx+ktbU18fH3798vftzExESSsCMzaiGitQe1LH1hzhs1KUNbOq3Tbi5IoURBRlOaxScMuwGQXHMmtDDsxhCZ0+mUTDAt6DnempoaVFZW4vbt27LND5vuMUtOtzlOhULr+bG1LOcmFVrNa/DadgRFr0XeN1UWGGlHMbKeAK1BNaPy9618Bhvu54ToQgrbhLd9Yn50sB9Yl7pkLmq7xcVFMSMbGxtRUVGB1tZWfPLJJ1L5pDOguIsjF4o28blI4/G4dBlh72xqmMXFRVncDodDmupnZmZKjTPHznZEmZmZmJ2dFeAuMzNTmrIXFhbKsRpl5Xh1VxKmo2ZnZ2N2dlYqvGhVAJA2RbrTCTUi0XU2N2BzBYbYHA6HJJrQx9UFLfRVbf+SAjeRSCTtE1VeXi5dMbkmEokEvF6vpKAuLy/j5s2bWFpakt7UzM3Wa8K23PT19HrVc2iHRrWG1UpHh6xsLEjfZzPaEYysmYd/6we3/QibbIRbf2+n4RGV1i9GI48k/p+/81pES10ul3TzqK6uRk9PD/bs2YOKigpUVFTg+eefx969e2VzdXblNMZIyiG3h6Fm083oNSPSZCV66nQ6pc6ZWpzfk5HZb4spjhoYmpubSwr1cdHV1tZKKyNur8LyP5YZssk/txGNxWKyjQ5TKoGNPZzIvPyO5jXNaSaz6G4iRJt1WyG+Lw3csegiIyNDWi8NDw9jaGhIBBQTWnTzfK/Xi8rKStTU1GBxcVE2IaA2ZuhuK7xFC3t7TWo/NxUD2qGnrdayvgYtmVS0Ixg5FSggr+rmAAAXqklEQVSlJ0BrYvsBtdnNYzWwpb/nNTRYxnP1grbNcQ04UGLqLUqWl5dlR775+XlMT0/D4/Fg37598Pv9qK2tRXd3NwKBABYWFsR8YtYXTVUteOiX8Tl06Ib53axgWlpakvgsz3O73ZiZmZFx0w8m+qs7e/J52MrV6XSiqqpKnjs/P18ESklJiYBbt2/fxuDgoLwLlkTyHehsKzIz3yvNdzIufWeasmwGz2ejtUDty8ov+tButxsLCwuYmJjA9PS04AGlpaVYWFiQfuZutxvl5eVoaGhAWVkZotEoBgYGpAUQmZhCRaf72muDbp6OjNhrV7tntnLS2lpfW1sctgm+Ge0IRgaS0Wr7gTSz2hOh43kavreZ0WZ4fV+eo8ehr0/JC2w0saO5B0BM0Pn5ecmR9ng8kqr41a9+VZoN9Pb24vPPP5eYJ30xoqw6a0hrK4aJmNLIkA1b3nJRkdH5LNRcXBQ0x+kaOJ1OEUIM+9y6dQv9/f2Se11YWCgbwbOTJLcFWllZweDgoNyLxxQUFGBsbEwsBDaBp1/L0kWGbPgbK6iYmcV76JBiJBJBSUmJIOD0ixkeJMN6vd6kTDJgXUCUlJTIFjqLi4uyH9jc3Byi0egd/bNSKRLNfJrBtAunQVob++F1KIiodDTTa0HCtbcZ7RhG5iC1iWujzEAyw9lmjpZiJG2WM1smFbxvV63oSaMA0fFaXoMmGBmcqZFFRUWYn59HYWEhfD4fiouL8dRTT2HPnj0IBAKSMcTWszQFqZ3oK5Mp+VL5zEzPpOlKra7Da9QiOjyl+3/pnQs5jtzcXMl1JrCnBSxrrgkusSdWKBSSUFpJSQlKSkqwe/duTE5OSqM73ssYI80EmHBDQUGm17XK1LxcD2R4CgWCYGNjYxgZGcHq6ipKS0uRk5OD6elpDA0N4datW8jJyUFFRQXq6uqkUSE3cZuYmJA+bsze0viI7f+mMrs1mq39YxsY02vd9rl5D+2P63tsRjuGkQHcMXitRbUprRncZlouXPs3LUG12cNYZCo/3I5d24gjkVx+yMxEqulrVldXC8DS0NCAuro6jIyMoLe3F4FAQHZzZEiI2oihFYaU6EOTSbXJz/JAxj5panNB6bJNMgWZVe+PrH1n3ZyQe0bpii36+exwyUqtmZkZAZPY2J9MTxNbt44tLi6Wrp4UUnxWmuy6RRDneG5uTlwS7u0VjUYlJBcKhXD9+nVJaKmsrMTevXvh9/uxvLyMqakpTE5OYmZmRjqy6CgFUX6OQ6+bVHkMOsSl17M2kfU60mtVr9PN/tbXtmnHMLKtcel3aMRUMxJwZ3dCG0DQFS56QvkCeI3N/HH9N5nCfiEUMHrPIYI+BQUFAjStrKygtLQUxcXF8Hg8aGhowO7du+H3+3H9+nWJX966dUu0MM1mrVE5DuZ0U3MtLy+LyU3UWp/P5+EYHQ6HmKAABGzi87Hgga1eGdNmAwS2AKYvzGvyeWdnZ1FUVISioiJhQJ/PJ+9xYWEBkUhEfG8Kk9u31zeOY+46Y+IURjr0SMCMzz82NiZzE4/HpQzU5XKhrKwMjz32GBobG1FSUoKhoSFMTk4iGo0mIdQ6RERfXuMtqUxqG0W3/V29bjT2oV02vT7J4Bqg3AzoJd0VI3s8Hvz5z3/G1772NRhj8NprryEQCOC9995DbW0tRkZG8NJLL0mr0VOnTuG5555DLBbDK6+8go6Oji2vr80GHT+zU9VscEv70Fr6cTJpZtpgg9bYqQAMW/NSS2hmt18QhQHNXZrZ3KGPpX/RaFQ2Ji8uLkZjYyMqKysxPDyMwcFBBINBCRPpLVqYakjfOJFIJGUzsSJIb4pOrQdsJNFwgbOJIICkMJgGxIgu8zvOLRmImphMRc2XSCQQDofh9XrFfOfipUVQXFyMhYUF2Z9pz5490jCPIBx3kSCYxTXB67GZ3tzcHMbGxmRumb7K3UAKCgrw+OOPo7GxEW63G319fZKCGYlEkvp58Z1q18rWjHot2BahXj/6PNuctjWsjRGlskrv2bQ+deoULly4gB/96EeCIJ44cQL//ve/cfLkSRw/fhzNzc1obm7GkSNHUF9fj/r6ehw8eBCnT5+WlilfRPpB7O/0g3Cy9aQAuMOE0SBDqvP1xGsfRk+Ylo6bvVxbUrNRHZmJJhu7dhJwcTgcskkci/GLioqkpUw8Hsfc3JwwGtFqYKNtDxFhmtQUJJT2uoxTg2A0QTleWj1EhSmMKJAAJPntessYmsJkUIbCZmdnZY6qqqoQDocBbPSgjsViuHbtGrKzs2U3RY7P6XRKNRM1Op+F88AYO8NxNN+BdWumtrZWQMYDBw4AWK8hv3nzJmKxGCKRCGZmZmT3SR3e4XPZmtAGRfn+uU60Qki1ju31biccaZDV9sfvSSPv2rUL3/rWt/DKK6/IS5yfn8cLL7yAb3/72wCAv/71r/jPf/6D5uZmvPDCC/jb3/4GAGhra5Oyua12ZEw1YNuksBlWM5WWjvak63iwvp+eXC76VOEsTjA1YyqfxzaxOCYmRlAzE9lmo3Vu31JaWopdu3ahrKwMfr8fiUQCs7OzCIfDmJqaEu0xMzMjPiuZj2OjoNBzyLgrtTmfSVcgcY5sRudioiDSxQ5E7Ck02BiBz19UVCRxWTIf90gi0MVx6mw0plfy3bPnGME8h8Mh9dnxeDypR1leXh4OHDggFWBsM1RdXY3GxkYAwODgIAYGBjA2NibnUvjpfGxaNFo7a4whFbCqM7JspWADWfpve/3o9cl1pK2hzegLGdnv9yMSieAvf/kLGhsbceXKFfzqV79CWVmZMCebqwNAZWWlhCYAIBgMorKycktG1gyhEWFOltaGGnDgv9q01cfYZrJmYB5nm0P2uPQxukJLv0jNPNpkIpMlEht7BbGjB7OXuKEY86hXVlaQn5+PiooK1NfXIxqNIhQKIRaLSQN2vfUnd7XQmlpbBsyl1swCbCzWgoICAe107bDWujrTiAuLc59IbGRbsbjg1q1b2Lt3L2KxmOSFM2MKWFcG7LbCTqMOhwOLi4sA1pvdEVTjvDscDmlwSF88kUjIns8ABHmnjxyPx6V76Y0bNzAyMiJ1xvSfycR8XxrosjEXIJlhNePpUkbNnHo96AQWWynpta8BMBuL2Yy+kJFdLhcOHDiAN998E59++inefvttNDc333HcVvZ7Knr99dfxs5/9DABQXFycxGg6qVxrTE6YPlZLRA0ucAHo/5M0o2stq38jaZ89lcTkOVq7a6nMEAqZmSYy83m5iyE1LsGq0tJS2bVi7969ElKiH86YZywWk5xual+GT5jWyTi1Hdph3JhhK+6JxVJAZowxJMZnY4KKw+EQAcJnXVpaksorj8cjvbq05gXWmTkvLw81NTUYHR3F1NSUvAO32y255WQE+tYULF6vVxooMJONfi6TOjweD4wx0g6IFV7UxGwwz/WlcQTtKtkuF3/TDEnSa0knfHAtpSIdAtXX4W96PJvRFzJyMBhEMBjEp59+CgD4xz/+gebmZoTDYTGZy8vLMTU1BQAIhUKorq6W86uqqhAKhe647jvvvIN33nkHAHDlyhUAdzYrs5lMgxDa/LYlmB0v1ufrv3k8/68nLxXZkphkhya4ALVU571YUcTwUkFBAVZWVnDz5k1p/VNUVAQAiEajUr5Izcm6XrfbDb/fL2ZuNBoVcIz3p5CYnp6W5oA8liGb2dlZaTfEzcMByH5OzKzidekiEBlnMgxBL5q0xhhMTU0hMzNTEmPIiGzAF4vFJEec/rTX6xXAjuE0xoupOYmWl5SUJHXkZE45r+t2u3Hjxo2krh7MYNP7Get3rjVyKu1LouDS69ReT9ry22xd2drWNsG1krgnsIsbmTU0NKC/vx/f+9730Nvbi97eXhw7dgwnT57EsWPH8K9//QsAcP78ebzxxhtoaWnBwYMHMT8/v6VZTdID1Q9sw/O2z2D7H/xOM7r9G7ChwbXE14CFHadNFaLSvrs263UROUmbbZop2EidWo/Mt7i4mNQAH1i3jvLz88XkZPcQal2OhxlZFCZVVVVJlWLV1dXIzc0V/1IDXhQqrB5iHrXD4RAGYgN+WgdLS0sIhUIwxqCsrEwqsVjtpcNxLKOkts/Ozsbu3buxe/duQceBjc3hOZcswNA+J2PuFB5Mz1xeXkZ1dTVcLhd6e3sRDoclHZYb2DNJxX6vGnCyMRcbW+H71r5uKsWg3Ubb7N4sjqytQL47banadFeo9ZtvvokzZ84gKysLQ0NDePXVV+F0OnH27Fn89Kc/xejoKF566SUAwIcffojnnnsOg4ODiMViePXVV7/w+puZv6km0Y4383ytbbWZq30PfT17AvkyddtYW/trXzHVy9STr60H23/W8UOGjVjsPj8/L4stOztbQjhcuKzfZWoja3Z1KEgvThY/0HwmGkvmjcfXO0MWFRXJxm4NDQ1YWFjA6uoqJiYmJGOLTMjnIGDE5nRsw0NG9vl88Hg8YqWw3pp7Z3Ec9OHz8/OTepox4YRNIPSG5hSGbOnjcrkQCATQ3t4u3VG4W2IoFBJfneY3rSPdeke/M64x4iI26Ko/qSIjNliqAVct4O3qKK43LUSIa9yTjwwAXV1deOKJJ+74/plnnkl5/BtvvHE3l00iPoStzbR5bWtJ/m4DX7weJyiV72FPnC1NbZNYg162UOD3dgWV/l2PTTMzv9PhJPrVzPZiM7u1tTVJoOCCpmlJxtZFBQSuGKLShQjU6g6HQ1IgMzIyxNfmNevq6uQaFAoct8vlwszMDHw+H1wuF65duyYmvW5Sz9RM+uxOp1PKMGnuMvSlQ23EBWgN6Ppyxr0dDgf6+vowMjKCrq4ueDweqfkOhUJS2cTj7QZ3qdagDUSlYkAbjNXrzbbESKlMdH0/e73Y329FOyKzSzOb7ReQ9ETp//N8W5ryGlpaai1vT7Z+aVpzalNOM6Q+hsSFZo9LPxdjuzyGTQFo1jLkE41GhUnn5+elA4cu3GfzOS5QhnN4Tc4DNRldCG7Yrquqbt68KR0rmSjCGDeBIW71Qu2WlZUl8d+lpSUEg0EYY5KSRaamplBWVibbvgDrC3ppaUnSPu2sNW5dy97aFOLalGdIbWFhAaOjowiHw9LhNBgMYnFxEaOjo0kZYamsLdta4zvXfjLfpb1ebPfJFuIaoNXPzvNSMaq27mxL85585IdFto9sM5V+MGDzjBoubFtza1Q6lSmjv6OPZH9vCwH9QvjCbJNKj5FEptNlivo61B7MmWZdL5Md6DNzkercaY6D3/Nvnh+Pr3fP0OY6mYjoMgVITk6OxGQBSEufyspKST8lo3HjM5YL8vkZ+/Z4PCI4+GFrXYfDIW2SsrKykJ+fL9ckqMa6aAJrtFZmZ2dRWFgIv9+P3NxchMNhxGIxTExMyDVpmmrfV4eybEvLdpVSWXpcN1o52K6WZsBUa8h2H/U9uP70fe4JtX7YZDOzTanMEK1RgQ2/w45B2+ayvoa+lz3xWkrre6Z6gfYz6OOB5IoXfT7vp90H3psLUedO8370fW0XgwxKIUCgiP4yzU/6oCzMoAnLYgT+y8Z+u3btEp+6vLxcElx8Ph/q6+vhdDoRCAQQj8dRWloqmpBgFWO8AKTwgnPJ0BHjzyyc4BxQi1MYTU9PIzs7G4899hgAoL29HZ2dnQiFQpI0oxNfOLd0S/ibtuhsC4rvQZu7ek3ZCkG/T9si0354KsuS526Gkm9FO5KRbR+Bk7aZr+tw3IlQ6xeTCkjQZEvLzcAHW0Jv5cPo41JlmG0Wt7alrz0uLkiHwyGpmfQjtQvhdG7kJzscDvFDyVRMcdSlegTdCIA5HA4JTa2trWFmZkZqjcPhsFQ5UVP7fD4UFBQAWA9Dzs/Py0bmFBQMKTHhhCEjFnM4nU4JcbE2WOdfs+wxkUjgK1/5CvLy8hAOh9HT04Pu7m7Mzs4m7bChY8T6PdotlrjedH5/KnfNdq9soW5babbW1aSvk8oXt8+7Z7DrYZD9QJv5ssCdea5aAqY6D0CSpiPZE2Wfm0pS2sdr3zeVtNbHahxAPysXhw1w6IWgQRVjTFLnSZIWeGtra5KZRZSYfrjL5ZLwEpv3GbMRwqLWYhxZNzEg+Obz+bC2tobPP/8cU1NTqKurk84hhw8fRjAYxNDQkLQOYhJLTk6OaH4mmbBlL10JHcpzOBySB01gra6uDolEAtPT0wiFQhgeHsa1a9ckL52hKxvL0BaatuC0JWQL7FTrTQtjWhL6XWnFYDO8Xq98RrpA+tr2GvsicgD4cilZD4AWFhYQCAS2exgA1rPMuANEehzrtFPGslPGAWzfWGpqalBaWpryN7Pdn/b29m0fw04by04Zx04ay04Zx04bCwCzdUlFmtKUpv8JSjNymtL0CFAGgLe2exAAcPXq1e0egtBOGctOGQewc8ayU8YB7Kyx7AiwK01pStO9Udq0TlOaHgHadkb+wQ9+gL6+PgwMDOD48eMP9F7vvvsuwuEwuru75Tuv14vW1lb09/ejtbVVtgEF1nuVDQwMoKurC01NTfd1LFVVVbh06RKuXbuGnp4e/PKXv9yW8bjdbrS1taGzsxM9PT146623AAC1tbW4fPkyBgYG0NLSImmhWVlZaGlpwcDAAC5fvoyampr7Mg6S0+nE1atX8cEHH2zrOIaHh/HZZ5+ho6MD7e3tALZvrdwtbR9k7nSawcFB4/f7TWZmpuns7DT79+9/YPf75je/aZqamkx3d7d8d/LkSXP8+HEDwBw/ftz8/ve/NwDMkSNHzIcffmgAmIMHD5rLly/f17GUl5ebpqYmA8Dk5+ebQCBg9u/fvy3jycvLMwCMy+Uyly9fNgcPHjTvvfeeefnllw0Ac/r0afPzn//cADC/+MUvzOnTpw0A8/LLL5uWlpb7Oi+/+c1vzJkzZ8wHH3xgAGzbOIaHh43P50v6brvWyl1+HvoN5XPo0CFz4cIF+X9zc7Npbm5+oPesqalJYuS+vj5TXl5ugHXm6uvrMwDMn/70J3P06NGUxz2Izz//+U/zzDPPbOt4cnJyzJUrV8yTTz5pIpGIycjIuOM9XbhwwRw6dMgAMBkZGSYSidy3+1dWVpqPPvrIfOc73xFG3o5xAKkZeaeslVSfbTWtN2vU9zDpyzYRfBBUU1ODpqYmtLW1bct4nE4nOjo6MDU1hYsXL+LGjRuYm5uTvGN9Lz2OeDwunUDvB7399tv47W9/K6mTPp9vW8YBAMYYtLa24r///S9ef/11ADtjrWxGOybXeqfQ3eS13k/Ky8vD+++/j1//+tfSRfJhjyeRSKCpqQkejwfnzp3Dvn37Hvg9bfrhD3+IqakpXL16FU8//fRDv79N3/jGNzA+Po6SkhJcvHgRfX19dxzzsNfKVrStGvluG/U9SGITQQD/ryaC90Iulwvvv/8+zpw5g3Pnzm37eObn5/Hxxx/jqaeeks3P7XvpcWRkZMj2LvdKhw8fxvPPP4/h4WG0tLTgu9/9Lk6dOvXQx0EaHx8HAEQiEZw7dw5PPvnktr6bL6JtZeT29nbU19ejtrYWmZmZOHr0KM6fP/9Qx3D+/HkcO3YMAO5oIviTn/wEAL5UE8EvQ++++y6uX7+OP/zhD9s2Hu5FBQDZ2dl49tlncf36dXz88cd48cUXU46D43vxxRdx6dKlex4DAJw4cQLV1dXw+/04evQoLl26hB//+McPfRzAegOF/Px8+fv73/8+enp6tnWt3A09VKfc/hw5csQEAgEzODhoTpw48UDv9fe//92Mj4+b1dVVMzY2Zl577TVTVFRkPvroI9Pf328uXrxovF6vHP/HP/7RDA4Oms8++8x8/etfv69jOXz4sDHGmK6uLtPR0WE6OjrMkSNHHvp4Hn/8cXP16lXT1dVluru7ze9+9zsDwPj9ftPW1mYGBgbM2bNnTVZWlgFg3G63OXv2rBkYGDBtbW3G7/ff9/f09NNPC9i1HePw+/2ms7PTdHZ2mp6eHlmX27VW7uaTzuxKU5oeAdr2hJA0pSlN905pRk5Tmh4BSjNymtL0CFCakdOUpkeA0oycpjQ9ApRm5DSl6RGgNCOnKU2PAKUZOU1pegTo/wBWqtVVY9F8OAAAAABJRU5ErkJggg==\n",
+            "text/plain": [
+              "<Figure size 432x288 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "zc1WZJZjw852"
+      },
+      "source": [
+        "**THANK YOU**"
+      ]
+    }
+  ]
+}
\ No newline at end of file

From 267a0c4325b78450e9c64a37fe6240b65d42298f Mon Sep 17 00:00:00 2001
From: Ganesh Shet <72651335+ganesh-shet@users.noreply.github.com>
Date: Tue, 20 Jul 2021 12:14:37 +0530
Subject: [PATCH 4/4] Create Ganesh_G_Shet_Brain_tumor_detection.md

---
 Ganesh_G_Shet_Brain_tumor_detection.md | 112 +++++++++++++++++++++++++
 1 file changed, 112 insertions(+)
 create mode 100644 Ganesh_G_Shet_Brain_tumor_detection.md

diff --git a/Ganesh_G_Shet_Brain_tumor_detection.md b/Ganesh_G_Shet_Brain_tumor_detection.md
new file mode 100644
index 000000000..096169b9a
--- /dev/null
+++ b/Ganesh_G_Shet_Brain_tumor_detection.md
@@ -0,0 +1,112 @@
+# Brain-Tumor-Detector
+Building a detection model using a convolutional neural network in Tensorflow & Keras.<br>
+Used a brain MRI images data founded on Kaggle. You can find it [here](https://www.kaggle.com/navoneel/brain-mri-images-for-brain-tumor-detection).<br>
+
+**About the data:**<br>
+The dataset contains 2 folders: yes and no which contains 253 Brain MRI Images. The folder yes contains 155 Brain MRI Images that are tumorous and the folder no contains 98 Brain MRI Images that are non-tumorous.
+
+# Getting Started
+
+**Note:** sometimes viewing IPython notebooks using GitHub viewer doesn't work as expected, so you can always view them using [nbviewer](https://nbviewer.jupyter.org/).
+
+## Data Augmentation:
+
+**Why did I use data augmentation?**
+
+Since this is a small dataset, There wasn't enough examples to train the neural network. Also, data augmentation was useful in taclking the data imbalance issue in the data.<br>
+
+Further explanations are found in the Data Augmentation notebook.
+
+Before data augmentation, the dataset consisted of:<br>
+155 positive and 98 negative examples, resulting in 253 example images.
+
+After data augmentation, now the dataset consists of:<br>
+1085 positive and 980 examples, resulting in 2065 example images.
+
+**Note:** these 2065 examples contains also the 253 original images. They are found in folder named 'augmented data'.
+
+## Data Preprocessing
+
+For every image, the following preprocessing steps were applied:
+
+1. Crop the part of the image that contains only the brain (which is the most important part of the image).
+2. Resize the image to have a shape of (240, 240, 3)=(image_width, image_height, number of channels): because images in the dataset come in different sizes. So, all images should have the same shape to feed it as an input to the neural network.
+3. Apply normalization: to scale pixel values to the range 0-1.
+
+## Data Split:
+
+The data was split in the following way:
+1. 70% of the data for training.
+2. 15% of the data for validation.
+3. 15% of the data for testing.
+
+# Neural Network Architecture
+
+This is the architecture that I've built:
+
+![Neural Network Architecture](convnet_architecture.jpg)
+
+**Understanding the architecture:**<br>
+Each input x (image) has a shape of (240, 240, 3) and is fed into the neural network. And, it goes through the following layers:<br>
+
+1. A Zero Padding layer with a pool size of (2, 2).
+2. A convolutional layer with 32 filters, with a filter size of (7, 7) and a stride equal to 1.
+3. A batch normalization layer to normalize pixel values to speed up computation.
+4. A ReLU activation layer.
+5. A Max Pooling layer with f=4 and s=4.
+6. A Max Pooling layer with f=4 and s=4, same as before.
+7. A flatten layer in order to flatten the 3-dimensional matrix into a one-dimensional vector.
+8. A Dense (output unit) fully connected layer with one neuron with a sigmoid activation (since this is a binary classification task).
+
+**Why this architecture?**<br>
+
+Firstly, I applied transfer learning using a ResNet50 and vgg-16, but these models were too complex to the data size and were overfitting. Of course, you may get good results applying transfer learning with these models using data augmentation. But, I'm using training on a computer with 6th generation Intel i7 CPU and 8 GB memory. So, I had to take into consideration computational complexity and memory limitations.<br>
+
+So why not try a simpler architecture and train it from scratch. And it worked :)
+
+# Training the model
+The model was trained for 24 epochs and these are the loss & accuracy plots:
+
+
+![Loss plot](Loss.PNG)
+
+
+![Accuracy plot](Accuracy.PNG)
+
+The best validation accuracy was achieved on the 23rd iteration.
+
+# Results
+
+Now, the best model (the one with the best validation accuracy) detects brain tumor with:<br>
+
+**88.7%** accuracy on the **test set**.<br>
+**0.88** f1 score on the **test set**.<br>
+These resutls are very good considering that the data is balanced.
+
+**Performance table of the best model:**
+
+| <!-- -->  | Validation set | Test set |
+| --------- | -------------- | -------- |
+| Accuracy  | 91%            | 89%      |
+| F1 score  | 0.91           | 0.88     |
+
+
+# Final Notes
+
+What's in the files?
+
+1. The code in the IPython notebooks.
+2. The weights for all the models. The best model is named as 'cnn-parameters-improvement-23-0.91.model'.
+3. The models are stored as *.model* files. They can be restored as follows:
+
+
+```
+from tensorflow.keras.models import load_model
+best_model = load_model(filepath='models/cnn-parameters-improvement-23-0.91.model')
+```
+
+4. The original data in the folders named 'yes' and 'no'. And, the augmented data in the folder named 'augmented data'.
+
+
+Contributes are welcome!
+<br>Thank you!