stormraiser/GAN-weight-norm

Code for "On the Effects of Batch and Weight Normalization in Generative Adversarial Networks"

47
/ 100
Emerging

This project helps researchers and machine learning practitioners explore how different normalization techniques impact Generative Adversarial Networks (GANs). It takes image datasets (like LSUN or CIFAR-10) and trains GAN models, outputting generated images. The primary users are researchers focused on improving the stability and performance of image generation models.

181 stars. No commits in the last 6 months.

Use this if you are a researcher experimenting with the effects of batch and weight normalization on GAN training and image output quality.

Not ideal if you need a production-ready GAN for immediate use, as this is a research-focused implementation with acknowledged bugs and ongoing investigations.

Generative AI Image Synthesis Deep Learning Research GAN Training Computer Vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

181

Forks

35

Language

Lua

License

GPL-3.0

Last pushed

Jan 15, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/stormraiser/GAN-weight-norm"

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