wangguanan/Pytorch-Image-Translation-GANs

Pytorch implementations of most popular image-translation GANs, including Pixel2Pixel, CycleGAN and StarGAN.

Pytorch-Image-Translation-GANs

Pytorch implementations of most popular image-translation GANs, including Pixel2Pixel, CycleGAN and StarGAN.

Dependencies

• Anaconda (Python 2.7)
• PyTorch 0.4.0

Prepare Datasets

Datasets

• Pixel2Pixel (Facade).
• CycleGAN (Apple2Orange).
• StarGAN (CelebA): download 'CelebA/Img/img_align_celeba.zip' and 'CelebA/Anno/list_attr_celeba.txt'.

Experimental Results

Pixel2Pixel

CycleGAN

StarGAN

Acknowledgement

This project is going with the GAN Theory and Practice part of the Deep Learning Course: from Algorithm to Practice.

Contacts

If you have any question about the project, please feel free to contact with me.

E-mail: guan.wang0706@gmail.com