SDIT-Tensorflow

: Scalable and Diverse Cross-domain Image Translation (ACM-MM 2019)

Paper | Official Pytorch code

Usage

├── dataset
   └── YOUR_DATASET_NAME
       ├── train
           ├── class1 (class folder)
               ├── xxx.jpg (class1 image)
               ├── yyy.png
               ├── ...
           ├── class2
               ├── aaa.jpg (class2 image)
               ├── bbb.png
               ├── ...
           ├── class3
           ├── ...
       ├── test
           ├── zzz.jpg (any content image)
           ├── www.png
           ├── ...

    └── celebA
       ├── train
           ├── 000001.png 
           ├── 000002.png
           └── ...
       ├── test
           ├── a.jpg (The test image that you wanted)
           ├── b.png
           └── ...
       ├── list_attr_celeba.txt (For attribute information) 

Train

• python main.py --dataset celebA --phase train

Test

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

Comparison

Paper results

Author

Junho Kim