Cycle Consistent Adversarial Domain Adaptation (CyCADA)
A pytorch implementation of CyCADA.
If you use this code in your research please consider citing
@inproceedings{Hoffman_cycada2017,
authors = {Judy Hoffman and Eric Tzeng and Taesung Park and Jun-Yan Zhu,
and Phillip Isola and Kate Saenko and Alexei A. Efros and Trevor Darrell},
title = {CyCADA: Cycle Consistent Adversarial Domain Adaptation},
booktitle = {International Conference on Machine Learning (ICML)},
year = 2018
}
Setup
- Check out the repo (recursively will also checkout the CyCADA fork of the CycleGAN repo).
git clone --recursive https://github.com/jhoffman/cycada_release.git cycada
- Install python requirements
- pip install -r requirements.txt
Train image adaptation only (digits)
- Image adaptation builds on the work on CycleGAN. The submodule in this repo is a