Simple Tensorflow implementation of Diverse Image-to-Image Translation via Disentangled Representations (ECCV 2018 Oral)
├── 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 --concat True
python main.py --phase test --dataset summer2winter --concat True --num_attribute 3
python main.py --phase guide --dataset summer2winter --concat True --direction a2b --guide_img ./guide.jpg
--concat
True
: for the shape preserving translation (summer <-> winter) (default)False
: for the shape variation translation (cat <-> dog)--n_scale
n_scale = 3
(default)n_scale > 1
, a.k.a. multiscale discriminator
often gets better results--n_dis
n_dis = 4
(default)n_dis = 6
--n_d_con
n_d_con = 3
(default)n_d_con = 1
--num_attribute (only for the test phase)
num_attribute > 1
, then output images are variously generated
Junho Kim