junyanz/pytorch-CycleGAN-and-pix2pix

Image-to-Image Translation in PyTorch

53
/ 100
Established

Implements both CycleGAN (unpaired) and pix2pix (paired) translation using adversarial networks with cycle-consistency loss and conditional GANs respectively. Supports distributed training via DDP on multi-GPU setups and is compatible with PyTorch 2.4+. Includes modular templates for custom models and datasets, with extensive documentation covering training strategies and code architecture.

25,013 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

25,013

Forks

6,571

Language

Python

License

Last pushed

Aug 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/junyanz/pytorch-CycleGAN-and-pix2pix"

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