yunjey/domain-transfer-network
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
Implements adversarial domain transfer using a three-stage pipeline: pretraining a feature extractor, then jointly training a generator and discriminator with pixel-level reconstruction and domain confusion losses. Built on TensorFlow 0.12 with support for cross-domain tasks like SVHN-to-MNIST digit translation and photo-to-emoji conversion, requiring only unpaired images from source and target domains.
862 stars. No commits in the last 6 months.
Stars
862
Forks
200
Language
Python
License
MIT
Category
Last pushed
Jun 06, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yunjey/domain-transfer-network"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
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
ZPdesu/SEAN
SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)