Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/douglasrizzo/mygan

Last synced: 10 days ago
JSON representation

Host: GitHub
URL: https://github.com/douglasrizzo/mygan
Owner: douglasrizzo
Created: 2024-02-03T20:06:44.000Z (11 months ago)
Default Branch: master
Last Pushed: 2024-02-04T14:58:25.000Z (11 months ago)
Last Synced: 2024-12-17T19:28:33.817Z (23 days ago)
Language: Python
Size: 5.52 MB
Stars: 0
Watchers: 2
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

        # Simple GAN implementations

Implementations of DCGAN and WGAN in PyTorch.

## Usage

Make sure you are already logged on to WandB, the scripts will create projects called "wgan_celeba" for you to track progress.

- Run `python -m mygan` to train a WGAN on CelebFaces.

## Samples

The table below displays samples generated from the same noise vectors at different epochs in training.

| 0               | 35                 | 75                 | 109                 | 135                 |

|-----------------|--------------------|--------------------|---------------------|---------------------|

| ![0](assets/image.png) | ![35](assets/image-1.png) | ![75](assets/image-2.png) | ![109](assets/image-3.png) | ![137](assets/image-4.png) |

You can see some cool samples [in this WandB report](https://wandb.ai/tetamusha/wgan_celeba/reports/GAN-training-on-image-datasets--Vmlldzo2NzMxODkx).

## References

- 

- 

-