This repository provides PyTorch implementations for both unpaired and paired image-to-image translation tasks. It includes models such as CycleGAN, pix2pix, and other methods like BiGAN/ALI and Apple's S+U learning. The code was developed by Jun-Yan Zhu and Taesung Park, with support from Tongzhou Wang.
Key Features
CycleGAN: Unpaired image-to-image translation using cycle-consistent adversarial networks.
pix2pix: Paired image-to-image translation via conditional adversarial networks.
BiGAN/ALI: Bidirectional Generative Adversarial Networks and Adversarially Learned Inference.
S+U Learning: A method for self-supervised and unsupervised learning in image translation.
Pretrained Models: Access to various pretrained models for immediate use.
Training Scripts: Scripts for training models on custom datasets.
Evaluation Tools: Tools to evaluate model performance and visualize results.
Android DevHub
.png)
.png)
.png)
.png)
