raahii/infogan-pytorch

:art: A PyTorch implementation of InfoGAN.

13
/ 100
Experimental

This project helps machine learning researchers or practitioners explore how different aspects of an image, like a digit's type, rotation, or thickness, are represented in a generated image. You provide a dataset of images and define latent variables, then it generates new images while letting you control specific, interpretable features. It's for anyone experimenting with generative models and seeking to understand the underlying factors of variation in image data.

No commits in the last 6 months.

Use this if you are a machine learning researcher or student who wants to generate images and understand which hidden features (like digit type or rotation) are responsible for specific visual characteristics in the generated output.

Not ideal if you are looking for an out-of-the-box solution to generate highly realistic, complex images for production use, or if you don't have a background in machine learning models and training.

generative-modeling image-synthesis feature-disentanglement machine-learning-research interpretable-AI
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Python

License

Last pushed

Mar 25, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/raahii/infogan-pytorch"

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