StyleGAN.pytorch

[ChineseGirl Dataset]

Thanks to dataset provider:Copyright(c) 2018, seeprettyface.com, BUPT_GWY contributes the dataset.

Features

• Progressive Growing Training
• Exponential Moving Average
• Equalized Learning Rate
• PixelNorm Layer
• Minibatch Standard Deviation Layer
• Style Mixing Regularization
• Using official tensorflow pretrained weights
• Gradient Clipping
• Truncation Trick
• Multi-GPU Training
• FP-16 Support
• Conditional GAN

How to use

Requirements

• yacs
• tqdm
• numpy
• torch
• torchvision
• tensorflow(Optional, for ./convert.py)

Running the training script:

Train from scratch:

python train.py --config configs/sample.yaml

Using trained model:

Resume training from a checkpoint (start form 128x128):

python train.py --config config/sample.yaml --start_depth 5 --generator_file [] [--gen_shadow_file] --discriminator_file [] --gen_optim_file [] --dis_optim_file []

Style Mixing

python generate_mixing_figure.py --config config/sample.yaml --generator_file [] 

Convert from official format

python convert.py --config configs/sample_ffhq_1024.yaml --input_file PATH/karras2019stylegan-ffhq-1024x1024.pkl --output_file ffhq_1024_gen.pth

Generated samples

[FFHQ Dataset](128x128)

Using weights tranferred from official tensorflow repo.

[FFHQ Dataset](1024x1024)

[WebCaricatureDataset](128x128)

Thanks

Please feel free to open PRs / issues / suggestions here.

Reference

• stylegan[official]: https://github.com/NVlabs/stylegan
• pro_gan_pytorch: https://github.com/akanimax/pro_gan_pytorch
• pytorch_style_gan: https://github.com/lernapparat/lernapparat