https://github.com/musyoku/wasserstein-gan

Chainer implementation of Wasserstein GAN
https://github.com/musyoku/wasserstein-gan

chainer dcgan gan wgan

Last synced: 8 months ago
JSON representation

Chainer implementation of Wasserstein GAN

• Host: GitHub
• URL: https://github.com/musyoku/wasserstein-gan
• Owner: musyoku
• Created: 2017-01-31T13:57:20.000Z (almost 9 years ago)
• Default Branch: master
• Last Pushed: 2017-06-05T07:57:14.000Z (over 8 years ago)
• Last Synced: 2024-11-03T14:35:29.135Z (about 1 year ago)
• Topics: chainer, dcgan, gan, wgan
• Language: Python
• Size: 56.6 KB
• Stars: 95
• Watchers: 5
• Forks: 9
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
## Wasserstein GAN

- Code for the [paper](https://arxiv.org/abs/1701.07875)

- [実装について](http://musyoku.github.io/2017/02/06/Wasserstein-GAN/)

- See also:

	- [Unrolled Generative Adversarial Networks](https://arxiv.org/abs/1611.02163)

	- [Chainer implementation of Unrolled GAN](https://github.com/musyoku/unrolled-gan)

### Requirements

- Chainer

## Mixture of Gaussians Dataset

![image](https://github.com/musyoku/musyoku.github.io/blob/085c1d022e49dcaf81cda3a2f53bf2febbb61991/images/post/2017-02-04/gaussian_mixture.png?raw=true)

## MNIST

generated images

![image](https://github.com/musyoku/musyoku.github.io/blob/085c1d022e49dcaf81cda3a2f53bf2febbb61991/images/post/2017-02-04/mnist.png?raw=true)

## Animeface Dataset

loss

![image](https://github.com/musyoku/musyoku.github.io/blob/f581cb7cd343e6247d1ee23a169bcfbd321c5d51/images/post/2017-02-04/loss_curve.png?raw=true)

generated images

![image](https://github.com/musyoku/musyoku.github.io/blob/f581cb7cd343e6247d1ee23a169bcfbd321c5d51/images/post/2017-02-04/anime_gen.png?raw=true)