junyanz/pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch
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.
Stars
25,013
Forks
6,571
Language
Python
License
—
Category
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.
Related frameworks
huggingface/pytorch-pretrained-BigGAN
🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
torchgan/torchgan
Research Framework for easy and efficient training of GANs based on Pytorch
eriklindernoren/Keras-GAN
Keras implementations of Generative Adversarial Networks.
metal3d/keras-video-generators
Keras generators to generate sequences from videos as input
NVlabs/MUNIT
Multimodal Unsupervised Image-to-Image Translation