How to Create Neural Network for Recognizing Masks
[Part2] - Training & recognition

Description

Neural network that could process images, video footage and recognize people wearing masks

Parts

[Part1] - Labeling

[Part2] - Training & recognition

Tech stack:

1. Python 3.6+
2. Tensorflow 2 nightly
3. OpenCV-python
4. Modified YoloV3

Installation

$ activate yolo3 # in linux "source activate yolo3"
(yolo3) $ pip install -r requirements.txt
(yolo3) $ pip install -e .

Running the app

// ==================== Training ========================
python src/train_eager.py -c configs/mask_500.json

// ==================== Picture =========================
python src/pred.py -c configs/mask_500.json -i imgs/1.jpg

// ===================== Video ==========================
python video.py -c configs/mask_500.json -i video.mp4

// ==================== Benchmark =======================
python src/eval.py -c configs/mask_500.json

Contact company

• Fulcrum
  • Email: hello@fulcrum.rocks
  • Website: fulcrum.rocks
  • Blog: blog.fulcrum.rocks

Contact developer

• Serhii Kalachnikov
  • Email: serhii@fulcrum.rocks
  • Linkedin: Serhii Kalachnikov

Contributors

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

MIT License