Face Parsing.PyTorch Save

Using modified BiSeNet for face parsing in PyTorch

Project README

face-parsing.PyTorch

Contents

Training

  1. Prepare training data: -- download CelebAMask-HQ dataset

    -- change file path in the prepropess_data.py and run

python prepropess_data.py
  1. 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

Open Source Agenda is not affiliated with "Face Parsing.PyTorch" Project. README Source: zllrunning/face-parsing.PyTorch
Stars
2,115
Open Issues
41
Last Commit
11 months ago
License
MIT

Open Source Agenda Badge

Open Source Agenda Rating