https://github.com/gcucurull/cond-wgan-gp

Pytorch implementation of a Conditional WGAN with Gradient Penalty
https://github.com/gcucurull/cond-wgan-gp

cwgan-gp deep-learning gans pytorch pytorch-gan wgan-gp

Last synced: 4 months ago
JSON representation

Pytorch implementation of a Conditional WGAN with Gradient Penalty

• Host: GitHub
• URL: https://github.com/gcucurull/cond-wgan-gp
• Owner: gcucurull
• Created: 2019-12-30T16:25:05.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2020-01-02T17:03:03.000Z (almost 6 years ago)
• Last Synced: 2025-06-27T10:08:14.863Z (4 months ago)
• Topics: cwgan-gp, deep-learning, gans, pytorch, pytorch-gan, wgan-gp
• Language: Python
• Size: 461 KB
• Stars: 38
• Watchers: 2
• Forks: 7
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Pytorch Conditional WGAN with Gradient Penalty

Pytorch implementation of a Conditional [WGAN](https://arxiv.org/abs/1701.07875) with [Gradient Penalty (GP)](https://arxiv.org/abs/1704.00028).

This implementation is adapted from the Conditional GAN and WGAN-GP implementations in this [amazing repository](https://github.com/eriklindernoren/PyTorch-GAN) with many different GAN model.

# Usage

Just run

```

python main.py

```

It will create an `images` directory and save generated images every few iterations.

It can be trained with MNIST (default) or Fashion-MNIST just by adding the flag `--dataset fashion`.



    





    Example of the images generated by the model, conditioned by class.



Generated samples evolution as training progresses: