StarGANv2 - Not Official PyTorch Implementation

***** StarGAN v2 official implementation will be available soon at https://github.com/clovaai/stargan-v2 *****

Caution!

Now, my implementation do not work well...
The implementation of models is same as the original ones, maybe. So, if you help me, please check the training loop in solver.py .

Dependencies

• Python 3.6+
• PyTorch 0.4.0+

Usage

1. Please download the Animal Faces-HQ dataset (AFHQ). And please move root.

bash scritpts/download_afhq.sh afhq

2. bash scripts/train_starganv2.sh

Generated results.

• 2000 iterations.

• 10000 iterations.

Citation

If you find this work useful for your research, please cite official paper:

StarGAN v2: Diverse Image Synthesis for Multiple Domains
Yunjey Choi*, Youngjung Uh*, Jaejun Yoo*, Jung-Woo Ha^1,2    
Clova AI Research, NAVER Corp. (* indicates equal contribution)
https://arxiv.org/abs/1912.01865

@article{choi2019starganv2,
  title={StarGAN v2: Diverse Image Synthesis for Multiple Domains},
  author={Yunjey Choi and Youngjung Uh and Jaejun Yoo and Jung-Woo Ha},
  journal={arXiv preprint arXiv:1912.01865},
  year={2019}
}

Acknowledgements

This repository is based on stargan official repository. Thanks.