---

This repository provides the tensorflow implementation of the following paper:
The GAN that Warped: Semantic Attribute Editing with Unpaired Data
Garoe Dorta Vicente Neill D.F. Campbell Ivor J.A. Simpson

Requirements

• Tensorflow 1.8
• Python 3.6

Usage

Downloading the dataset

> python download.py celebA

├── dataset
   └── celebA
       ├── train
           ├── 000001.jpg 
           ├── 000002.jpg
           └── ...
       ├── test (It is not celebA)
           ├── a.jpg (The test image that you wanted)
           ├── b.png
           └── ...
       ├── list_attr_celeba.txt (For attribute information) 

Train

• python main.py --phase train

Test

• python main.py --phase test
• The celebA test image and the image you wanted run simultaneously

Results (128x128)

Women

Men

Reference

• WarpGAN paper

The framework referenced the StarGAN-Tensorflow has been completed, but I can't get the same result as the paper. So you can refer to it. If you find some problem in the code, please contact me: wwkang94@alumni.sjtu.edu.cn