https://github.com/mjahmadee/object_detection_and_counting

Object Detection and Counting
https://github.com/mjahmadee/object_detection_and_counting

counter fast-rcnn faster-rcnn faster-rcnn-pytorch object-detection rcnn

Last synced: 2 months ago
JSON representation

Object Detection and Counting

• Host: GitHub
• URL: https://github.com/mjahmadee/object_detection_and_counting
• Owner: MJAHMADEE
• License: mit
• Created: 2023-07-13T11:28:41.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-03-16T12:56:39.000Z (10 months ago)
• Last Synced: 2024-03-16T15:34:44.532Z (10 months ago)
• Topics: counter, fast-rcnn, faster-rcnn, faster-rcnn-pytorch, object-detection, rcnn
• Language: Jupyter Notebook
• Homepage:
• Size: 16.2 MB
• Stars: 3
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Object Detection and Counting with Faster R-CNN 🚗👀

![Python](https://img.shields.io/badge/Python-3.x-blue.svg)

![PyTorch](https://img.shields.io/badge/PyTorch-1.x-orange.svg)

![Computer Vision](https://img.shields.io/badge/Computer%20Vision-Object%20Detection-green.svg)

This repository demonstrates an implementation of Faster R-CNN for object detection and counting, applied on the PASCAL VOC dataset. The model is trained to recognize and count various object categories in images.

## Features 🌟

- Utilizes Faster R-CNN with a ResNet-50 backbone for object detection.

- Trained and evaluated on the PASCAL VOC dataset.

- Includes scripts for training, evaluation, and visualization of the model's predictions.

- Provides functionality to plot images with bounding boxes for detected objects and their labels.

## Setup and Installation 🛠️

1. Clone the repository.

2. Ensure Python and PyTorch are installed.

3. Download the required dataset and place it in the specified directory.

4. Install all the dependencies listed in `requirements.txt`.

## Dataset 📁

The model is trained and tested on the PASCAL VOC dataset, which includes a wide range of object categories and annotated images.

## Training the Model 🚀

- The training script initializes the Faster R-CNN model and sets up the dataset for training and validation.

- A custom training loop is implemented to monitor the training process, including loss calculation and optimization.

## Evaluating the Model 🧪

- The evaluation script loads the trained model and performs object detection on the test dataset.

- Performance metrics are calculated to assess the accuracy of the model.

## Visualization 📊

- Visualization functions are provided to display the images with bounding boxes around detected objects, alongside their predicted classes and scores.

## Contributing 🤝

Contributions to the project are welcome. Feel free to fork the repository, make changes, and submit a pull request.

## License 📜

The project is open-sourced under the MIT License.

## Acknowledgements 🙌

- The PyTorch team for providing an excellent deep learning framework.

- The PASCAL VOC dataset maintainers for providing a rich dataset for object detection tasks.

For more details, please visit the [GitHub repository](https://github.com/MJAHMADEE/Object_Detection_and_Counting/).