StyleGAN

Concise implementation of StyleGAN and ProgressiveGAN in PyTorch.

Code organization:

stylegan: neural net classes, dataloaders, training script, config file
notebooks: sampling and inversion demo using a trained StyleGAN model

Training:

Configure the training parameters in ./stylegan/config.py
Run:
```
python ./stylegan/train.py
```

References:

Karras, Laine, Aila - A style-based generator architecture for generative adversarial networks. [arXiv 2018] [CVPR 2019]
Karras, Aila, Laine, Lehtinen - Progressive growing of gans for improved quality, stability, and variation. [arXiv 2017] [ICLR 2018]
Zhang - Making convolutional networks shift-invariant again. [ICML 2019]
Mescheder, Geiger, Nowozin - Which training methods for GANs do actually converge?. [ICML 2018] [arXiv 2018]