basiclab/GNGAN-PyTorch

Official implementation for Gradient Normalization for Generative Adversarial Networks

34
/ 100
Emerging

This project helps machine learning researchers and practitioners working with Generative Adversarial Networks (GANs) to generate high-quality synthetic images. By implementing Gradient Normalized GAN (GN-GAN), it takes datasets like CIFAR-10, STL-10, CelebA-HQ, or LSUN Church and outputs trained models capable of producing realistic new images from those distributions. This is primarily for those looking to improve GAN training stability and output quality.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer developing or experimenting with GANs and want to improve the stability and performance of your image generation models.

Not ideal if you are looking for a plug-and-play solution to generate images without deep technical understanding of GAN architectures or training processes.

generative AI image synthesis deep learning research computer vision model training
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

72

Forks

13

Language

Python

License

Last pushed

Oct 11, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/basiclab/GNGAN-PyTorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.