riejohnson/cfg-gan-pt

CFG-GAN (Composite Functional Gradient learning of GAN) in pyTorch

33
/ 100
Emerging

This project helps machine learning researchers or practitioners explore and train Generative Adversarial Networks (GANs) using a specific technique called CFG-GAN. It takes existing image datasets (like MNIST or LSUN bedroom images) as input and outputs trained GAN models that can generate new, realistic images similar to the training data. This tool is designed for those working on advanced image generation or synthetic data creation.

No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner interested in experimenting with or applying composite functional gradient methods for training generative adversarial models to create synthetic images.

Not ideal if you are looking for a simple, out-of-the-box solution for image generation without deep technical involvement, or if you are not familiar with PyTorch and GAN training concepts.

generative-modeling synthetic-data image-synthesis machine-learning-research adversarial-networks
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

8

Forks

2

Language

Python

License

MIT

Last pushed

Jun 05, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/riejohnson/cfg-gan-pt"

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