eriklindernoren/Keras-GAN

Keras implementations of Generative Adversarial Networks.

51
/ 100
Established

This collection provides various Generative Adversarial Networks (GANs) that can generate new images from scratch, transform images from one style to another, or enhance image quality. It takes existing datasets of images as input and can produce synthetic images, translated images (e.g., from day to night), or higher-resolution versions of low-res images. Researchers, artists, or data scientists working with computer vision tasks who need to generate novel visual content or manipulate image domains would use this.

9,226 stars. No commits in the last 6 months.

Use this if you are a researcher or practitioner in computer vision looking for Keras-based implementations of various GAN architectures to experiment with image generation, style transfer, or super-resolution.

Not ideal if you are looking for a maintained, production-ready solution, as the repository is no longer actively developed.

image-generation computer-vision image-processing synthetic-data style-transfer
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

9,226

Forks

3,096

Language

Python

License

MIT

Last pushed

Dec 12, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/eriklindernoren/Keras-GAN"

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