MUNIT-Tensorflow
Simple Tensorflow implementation of "Multimodal Unsupervised Image-to-Image Translation"
Requirements
- Tensorflow 1.4
- Python 3.6
Issue
- Author uses so many iterations (1M = 1,000,000)
- Author uses LSGAN, but do not multiply each of G and D by 0.5
Usage
βββ dataset
Β Β βββ YOUR_DATASET_NAME
Β Β βββ trainA
Β Β Β Β Β βββ xxx.jpg (name, format doesn't matter)
βββ yyy.png
βββ ...
Β Β βββ trainB
βββ zzz.jpg
βββ www.png
βββ ...
Β Β βββ testA
Β Β βββ aaa.jpg
βββ bbb.png
βββ ...
Β Β βββ testB
βββ ccc.jpg
βββ ddd.png
βββ ...
βββ guide.jpg (example for guided image translation task)
Train
- python main.py --phase train --dataset summer2winter --batch_size 1
Test
- python main.py --phase test --dataset summer2winter --batch_size 1 --num_style 3
Guided Image Translation
- python main.py --phase guide --dataset summer2winter --batch_size 1 --direction a2b --guide_img guide.jpg
Summary
Architecture
Model Overview
Results
Edges to Shoes/handbags Translation
Animal Image Translation
Street Scene Translation
Yosemite Summer to Winter Translation (HD)
Example-guided Image Translation
Related works
Reference
- MUNIT-Pytorch (Author implementation)
Author
Junho Kim