Simple Tensorflow implementation of "Multimodal Unsupervised Image-to-Image Translation"
- Tensorflow 1.4
- Python 3.6
- Author uses so many iterations (1M = 1,000,000)
- Author uses LSGAN, but do not multiply each of G and D by 0.5
├── dataset
└── YOUR_DATASET_NAME
├── trainA
├── xxx.jpg (name, format doesn't matter)
├── yyy.png
└── ...
├── trainB
├── zzz.jpg
├── www.png
└── ...
├── testA
├── aaa.jpg
├── bbb.png
└── ...
└── testB
├── ccc.jpg
├── ddd.png
└── ...
├── guide.jpg (example for guided image translation task)
- python main.py --phase train --dataset summer2winter --batch_size 1
- python main.py --phase test --dataset summer2winter --batch_size 1 --num_style 3
- python main.py --phase guide --dataset summer2winter --batch_size 1 --direction a2b --guide_img guide.jpg
- MUNIT-Pytorch (Author implementation)
Junho Kim