Prepare training data: -- download CelebAMask-HQ dataset
-- change file path in the prepropess_data.py and run
python prepropess_data.py
$ 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.
# evaluate using GPU
python test.py
| Hair | Lip | |
|---|---|---|
| Original Input | ![]() | ![]() |
| Color | ![]() | ![]() |
11 commits
Python
66.6%
Cuda
20.8%
C++
11.5%
C
1.1%
Prepare training data: -- download CelebAMask-HQ dataset
-- change file path in the prepropess_data.py and run
python prepropess_data.py
$ 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.
# evaluate using GPU
python test.py
| Hair | Lip | |
|---|---|---|
| Original Input | ![]() | ![]() |
| Color | ![]() | ![]() |
11 commits
Python
66.6%
Cuda
20.8%
C++
11.5%
C
1.1%