CSAILVision/gandissect

Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/

49
/ 100
Emerging

This project helps AI researchers and practitioners understand what's happening inside a Generative Adversarial Network (GAN). You input a trained GAN model, and it outputs visual reports and interactive tools that show how different parts of the GAN respond to human-interpretable concepts like objects or textures. This is for machine learning researchers and engineers who want to debug, improve, or interpret the behavior of their GANs.

1,766 stars. No commits in the last 6 months.

Use this if you need to visualize the inner workings of your GAN, identify specific features it generates, or diagnose why it produces certain image artifacts.

Not ideal if you are looking for a tool to train GANs from scratch or to simply use a pre-trained GAN for image generation without needing to analyze its internal components.

AI research Generative AI model interpretation computer vision deep learning diagnostics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

1,766

Forks

279

Language

Python

License

MIT

Last pushed

May 23, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CSAILVision/gandissect"

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