taki0112 / FUNIT-Tensorflow

Simple Tensorflow implementation of "Few-Shot Unsupervised Image-to-Image Translation" (ICCV 2019)

FUNIT-Tensorflow

: Few-Shot Unsupervised Image-to-Image Translation (ICCV 2019)

Paper | Official Pytorch code

Other Pytorch Implementation

Usage

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

Train

> python main.py --dataset flower

Test

> python main.py --dataset flower --phase test

Architecture

Our result

Paper result

Author

Junho Kim