Awesome
DRIT-Tensorflow
Simple Tensorflow implementation of Diverse Image-to-Image Translation via Disentangled Representations (ECCV 2018 Oral)
<img src='./assets/final.gif' width="800px">Pytorch version
Requirements
- Tensorflow 1.8
- python 3.6
Usage
Download Dataset
├── 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)
Train
python main.py --phase train --dataset summer2winter --concat True
Test
python main.py --phase test --dataset summer2winter --concat True --num_attribute 3
Guide
python main.py --phase guide --dataset summer2winter --concat True --direction a2b --guide_img ./guide.jpg
Tips
- --concat
True
: for the shape preserving translation (summer <-> winter) (default)False
: for the shape variation translation (cat <-> dog)
- --n_scale
- Recommend
n_scale = 3
(default) - Using the
n_scale > 1
, a.k.a.multiscale discriminator
often gets better results
- Recommend
- --n_dis
- If you use the multi-discriminator, then recommend
n_dis = 4
(default) - If you don't the use multi-discriminator, then recommend
n_dis = 6
- If you use the multi-discriminator, then recommend
- --n_d_con
- Author use
n_d_con = 3
(default) - Model can still generate diverse results with
n_d_con = 1
- Author use
- --num_attribute (only for the test phase)
- If you use the
num_attribute > 1
, then output images are variously generated
- If you use the
Summary
Comparison
Architecture
Train phase
Test & Guide phase
Results
Related works
Author
Junho Kim