aitorzip/PyTorch-CycleGAN

A clean and readable Pytorch implementation of CycleGAN

51
/ 100
Established

This tool helps convert images from one visual style or domain to another without needing paired examples. For instance, you can transform photos of horses into zebras, or vice-versa, using separate collections of horse and zebra pictures. It takes two distinct sets of images and produces new images that look like they belong to the target domain. This is ideal for researchers or artists exploring image-to-image translation.

1,323 stars. No commits in the last 6 months.

Use this if you need to translate the style or appearance of images between two distinct visual domains where you don't have exact, matching pairs of images for training.

Not ideal if you require precise, pixel-level transformations based on paired examples, or if your image manipulation needs are simple photo editing.

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

How are scores calculated?

Stars

1,323

Forks

299

Language

Python

License

GPL-3.0

Last pushed

Apr 20, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aitorzip/PyTorch-CycleGAN"

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