Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/zllrunning/face-parsing.pytorch
Using modified BiSeNet for face parsing in PyTorch
https://github.com/zllrunning/face-parsing.pytorch
bisenet celeba-hq-dataset face-parsing face-segmentation pytorch semantic-segmentation
Last synced: 30 days ago
JSON representation
Using modified BiSeNet for face parsing in PyTorch
- Host: GitHub
- URL: https://github.com/zllrunning/face-parsing.pytorch
- Owner: zllrunning
- License: mit
- Created: 2019-04-18T01:51:21.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2023-05-21T14:00:45.000Z (over 1 year ago)
- Last Synced: 2024-10-14T10:02:22.774Z (30 days ago)
- Topics: bisenet, celeba-hq-dataset, face-parsing, face-segmentation, pytorch, semantic-segmentation
- Language: Python
- Homepage:
- Size: 2.99 MB
- Stars: 2,267
- Watchers: 35
- Forks: 453
- Open Issues: 42
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# face-parsing.PyTorch
### Contents
- [Training](#training)
- [Demo](#Demo)
- [References](#references)
## Training
1. Prepare training data:
-- download [CelebAMask-HQ dataset](https://github.com/switchablenorms/CelebAMask-HQ)
-- change file path in the `prepropess_data.py` and run
```Shell
python prepropess_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](https://drive.google.com/open?id=154JgKpzCPW82qINcVieuPH3fZ2e0P812) and save it in `res/cp`.
## Demo
1. Evaluate the trained model using:
```Shell
# evaluate using GPU
python test.py
```
## Face makeup using parsing maps
[**face-makeup.PyTorch**](https://github.com/zllrunning/face-makeup.PyTorch)
Hair
Lip
Original Input
Color
## References
- [BiSeNet](https://github.com/CoinCheung/BiSeNet)