VarCode-ai / yolox-face-detection

How to train and use Yolox on custom dataset

Yolox Face Detection

How to train and use Yolox on WiderFace dataset
View Jupyter Notebook »

View Test · Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. Roadmap
5. Contributing
6. License
7. Contact
8. Acknowledgments

About The Project

YOLOX is an anchor-free version of YOLO with strong performance for object detection. In this repository I train Yolox on WiderFace dataset with Google Colab to develop a face detection algorithm.

(back to top)

Built With

• Yolox
• Wider Face Dataset

(back to top)

Getting Started

Look at Jupyter Notebooks to see training details and how to make this algorithm from scratch.

Installation

1. Clone the repo

   git clone https://github.com/VarCode-ai/yolox-face-detection.git
   cd yolox-face-detection

2. Install YOLOX

   pip3 install -U pip && pip3 install -r requirements.txt
   
   pip3 install -v -e .
   
   pip3 install "git+https://github.com/philferriere/cocoapi.git#egg=pycocotools&subdirectory=PythonAPI"
   
   pip3 install cython

3. Download JPEGImages of Wider Face dataset

   cd datasets\VOCdevkit\VOC2022\JPEGImages
   python download_images.py

(back to top)

Usage

Real time detection

python tools/demo.py webcam -f exps/example/yolox_voc/yolox_voc_s.py -c YOLOX_outputs/yolox_voc_s/latest_ckpt.pth --conf 0.25 --nms 0.45 --tsize 640 --device [cpu/gpu]

Images

python tools/demo.py image -f exps/example/yolox_voc/yolox_voc_s.py -c YOLOX_outputs/yolox_voc_s/latest_ckpt.pth --path assets/001.jpg --conf 0.25 --nms 0.45 --tsize 640 --save_result --device [cpu/gpu]

Video

python tools/demo.py video -f exps/example/yolox_voc/yolox_voc_s.py -c YOLOX_outputs/yolox_voc_s/latest_ckpt.pth --path assets/will_smith_slap.mp4 --conf 0.25 --nms 0.45 --tsize 640 --save_result --device [cpu/gpu]

For more examples, please refer to the Documentation

(back to top)

Train from pre-trained weights

Weights trained for 6 epochs

Code for resume training

python tools/train.py -f exps/example/yolox_voc/yolox_voc_s.py -d 1 -b 4 -c YOLOX_outputs/yolox_voc_s/latest_ckpt.pth --resume

(back to top)

License

Distributed under the Apache-2.0 License. See LICENSE for more information.

(back to top)

Contact

Vincenzo Varriale - @vincenzovarriale - [e-mail]

Project Link: https://github.com/VarCode-ai/yolox-face-detection

(back to top)