CenterNet-face-detection

Face detect and expression recognition in videos use CenterNet

Requirement

  • OpenCV
  • Python 3.6
  • Pytorch 0.4.1
  • torchvision 0.2.1

train and test

If you need to retrain your dataset,make sure put the dateset into the right path data/meetingpic/images,then run: python main.py If you want to test the demo, please download the pre-trained model from Baiduyun first, then put it in ./models/,and then run: python demo.py --demo /path/to/image/or/folder/or/video --load_model ../models/model_last.pth

Results

output/test1.png output/test2.png

Reference

https://github.com/xingyizhou/CenterNet