Skip to content

Using modified BiSeNet for face parsing in PyTorch

License

Notifications You must be signed in to change notification settings

valgur/face-parsing.PyTorch

 
 

Repository files navigation

face-parsing.PyTorch

Contents

Training

  1. Prepare training data:

    python preprocess_data.py
  2. Train the model using CelebAMask-HQ dataset: Just run the train script:

    CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 train.py

If you do not wish to train the model, you can download our pre-trained model and save it in res/cp.

Demo

  1. Evaluate the trained model using:
# evaluate using GPU
python test.py

Face makeup using parsing maps

face-makeup.PyTorch

  Hair Lip
Original Input Original Input Original Input
Color Color Color

References

About

Using modified BiSeNet for face parsing in PyTorch

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 66.7%
  • Cuda 20.7%
  • C++ 11.5%
  • C 1.1%