https://github.com/jiamings/wgan

Tensorflow Implementation of Wasserstein GAN (and Improved version in wgan_v2)
https://github.com/jiamings/wgan

generative generative-adversarial-network generative-model tensorflow tensorflow-experiments tensorflow-models

Last synced: 9 months ago
JSON representation

Tensorflow Implementation of Wasserstein GAN (and Improved version in wgan_v2)

Host: GitHub
URL: https://github.com/jiamings/wgan
Owner: jiamings
Created: 2017-02-02T04:25:09.000Z (about 9 years ago)
Default Branch: master
Last Pushed: 2018-08-03T05:26:24.000Z (over 7 years ago)
Last Synced: 2025-03-31T18:21:22.587Z (11 months ago)
Topics: generative, generative-adversarial-network, generative-model, tensorflow, tensorflow-experiments, tensorflow-models
Language: Python
Homepage:
Size: 10.7 KB
Stars: 240
Watchers: 9
Forks: 81
Open Issues: 2
Metadata Files:
- Readme: README.md

README

## Wasserstein GAN

Tensorflow implementation of Wasserstein GAN.

Two versions:
- wgan.py: the original clipping method.
- wgan_v2.py: the gradient penalty method. (Improved Training of Wasserstein GANs).

How to run (an example):

```
python wgan_v2.py --data mnist --model mlp --gpus 0
```