https://github.com/jiamings/cramer-gan

Tensorflow Implementation on "The Cramer Distance as a Solution to Biased Wasserstein Gradients" (https://arxiv.org/pdf/1705.10743.pdf)
https://github.com/jiamings/cramer-gan

cramer-gan generative generative-adversarial-network generative-model tensorflow tensorflow-experiments tensorflow-models wasserstein-gan

Last synced: 8 days ago
JSON representation

Tensorflow Implementation on "The Cramer Distance as a Solution to Biased Wasserstein Gradients" (https://arxiv.org/pdf/1705.10743.pdf)

• Host: GitHub
• URL: https://github.com/jiamings/cramer-gan
• Owner: jiamings
• Created: 2017-05-31T23:45:07.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2017-12-10T21:02:24.000Z (almost 7 years ago)
• Last Synced: 2024-11-12T17:03:04.319Z (8 days ago)
• Topics: cramer-gan, generative, generative-adversarial-network, generative-model, tensorflow, tensorflow-experiments, tensorflow-models, wasserstein-gan
• Language: Python
• Homepage:
• Size: 220 KB
• Stars: 125
• Watchers: 7
• Forks: 24
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
## Cramer GAN

Another recent member in the GAN family!

Seems to be an improvement over Improved WGAN (Improved^2 GAN)?

To run an example for MNIST generation:

```

python cramer-gan.py

```

This is a modification of Improved WGAN, where the losses are changed according to the following:

![](cramer.png)