U-GAT-IT — Official TensorFlow Implementation (ICLR 2020)

Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation

Requirements

See requirements.txt file

Use

1. Download the 204 epochs checkpoint (8Gb) and place it into a checkpoint at the root folder: https://www.dropbox.com/sh/63xqqqef0jtevmg/AADN7izdFHxueUbTSRBZrpffa?dl=0
2. Install the packages: pip install -r requirements.txt
3. Open and run the Jupyter Notebook: Test.ipynb
4. To test your own picture, set the path to the file on the Jupyter Notebook

From the original work of taki0112: https://github.com/taki0112/UGATIT

@inproceedings{
Kim2020U-GAT-IT:,
title={U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation},
author={Junho Kim and Minjae Kim and Hyeonwoo Kang and Kwang Hee Lee},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=BJlZ5ySKPH}
}

Author

Junho Kim, Minjae Kim, Hyeonwoo Kang, Kwanghee Lee