Object Detection and Recognition Model

This repository contains code for an object detection and recognition model. The project includes scripts for creating datasets, training models, and detecting objects in images.

Project Structure

project_directory

├── dataset_creator.py ├── trainer.py ├── detector.py ├── process_images.py ├── README.md

Create venv -

python -m venv (name for vevn)

Activate

.\activate\scripts\name of venv

• dataset_creator.py: Script for creating and managing datasets used for training the model.
• trainer.py: Script for training the object detection and recognition model.
• detector.py: Script for running the object detection model on images.

Requirements

To run this project, you'll need to have the following installed:

• Python 3.8+
• OpenCV
• TensorFlow
• NumPy

You can install the required packages using pip:

  pip install opencv-python-headless tensorflow numpy

1. Dataset Creation

Use the dataset_creator.py script to create and manage datasets for training your model.

2. Training the Model

Train the object detection model using the trainer.py script. Ensure your dataset is prepared and located in the appropriate directory.

3. Detecting Objects

Run the detector.py script to detect objects in images. Update the script with the path to your images.