Python
Simple Tensorflow implementation of StarGAN (CVPR 2018 Oral)

Requirements

• Tensorflow 1.8
• Python 3.6

> python download.py celebA

Usage

Downloading the dataset

> python download.py celebA

├── dataset
   └── celebA
       ├── train
           ├── 000001.jpg 
           ├── 000002.jpg
           └── ...
       ├── test
           ├── 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

Pretrained model

• Download celebA_checkpoint

Summary

Results (128x128, wgan-gp)

Women

Men

Author

Junho Kim