GitHub - foersterrobert/GANFTs: I trained a Generative Adversarial Network (GAN) using 10.000 images of CryptoPunks. In order to prevent mode collapse, I used the Wasserstein loss function together with gradient penalty. · GitHub

Repository navigation

GANFTs

Public

About

I trained a Generative Adversarial Network (GAN) using 10.000 images of CryptoPunks. In order to prevent mode collapse, I used the Wasserstein loss function together with gradient penalty.

6 stars

1 watching

Report repository

Name		Name	Last commit message	Last commit date
.streamlit		.streamlit
.gitignore		.gitignore
GANFTS.ipynb		GANFTS.ipynb
README.md		README.md
gan.gif		gan.gif
ganPunk.pth		ganPunk.pth
main.py		main.py
requirements.txt		requirements.txt
small.png		small.png
test.ipynb		test.ipynb

Repository files navigation

GANFTs

WGAN-GP: https://www.youtube.com/watch?v=pG0QZ7OddX4

About

I trained a Generative Adversarial Network (GAN) using 10.000 images of CryptoPunks. In order to prevent mode collapse, I used the Wasserstein loss function together with gradient penalty.

6 stars

1 watching

Report repository

Releases

Packages

Contributors

Languages