The Wayback Machine - https://web.archive.org/web/20200602232700/https://github.com/jiamings/wgan
Skip to content

/ wgan

Tensorflow Implementation of Wasserstein GAN (and Improved version in wgan_v2)
tensorflow generative generative-adversarial-network generative-model tensorflow-models tensorflow-experiments
Python
  1. Python 100.0%
Branch: master
Find file
Clone or download

Clone with HTTPS

Use Git or checkout with SVN using the web URL.

Open in Desktop Download ZIP

Latest commit

@jiamings
jiamings update
Latest commit ecc04ba Aug 3, 2018

Files

Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
lsun
mnist remove batch norm for improved wgan Apr 30, 2017
.gitignore first commit Feb 2, 2017
README.md add readme Apr 30, 2017
layers.py factor code Feb 2, 2017
visualize.py update Aug 3, 2018
wgan.py
wgan_v2.py fix bug Apr 30, 2017

README.md

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
You can’t perform that action at this time.