ZhangGongjie/CycleGAN-Pytorch
Minimum Implementation of CycleGAN in PyTorch -- Generating Wintery Scenery in Singapore!
This tool helps researchers and students transform existing images into new styles, specifically demonstrated by converting Singaporean landscapes into winter scenes. You provide a collection of source images, and it outputs a new set of images showing those scenes with a dramatically different aesthetic, like snow and frosty trees. It's designed for those learning about image-to-image translation.
No commits in the last 6 months.
Use this if you are a deep learning student or researcher looking for a straightforward example to understand how CycleGAN transforms images between different visual domains.
Not ideal if you need a production-ready, highly optimized image style transfer solution or require advanced features beyond basic domain translation.
Stars
9
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 07, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ZhangGongjie/CycleGAN-Pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yunjey/domain-transfer-network
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
taesungp/contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV...
PaddlePaddle/PaddleGAN
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion...
tohinz/ConSinGAN
PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
sagiebenaim/DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017