Home

Awesome

UFDN - Pytorch Implementation

Description

This is a PyTorch implementation of my paper A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation (UFDN) accepted by NIPS 2018. Please feel free to use/modify them, any bug report or improvement suggestion will be appreciated.

Model

For more detailed information, please refer to the paper.

Application

Requirements

Execution Environment
Packages

Setup

Download pretrained model & dataset

Dataset is available here. To run the code, please download and place it under data/. Human face dataset is currently unavailible due to CelebA's prohibition of futher publication, we will make it availible if we get the premission in the future. Pretrained model is also available here, you can download it if you'd like to try.

Train your own model

To train UFDN, make sure all requirements are satisfied and run

python3 train_face.py <path/to/config>

See example config for more options avialible. Please refer to the paper's supplementary for config used in the main paper.

Training log & inference

To see learning curve and some translation/generation result, use tensorboard to access training log (location specified in config). E.g. tensorboard --logdir=log/

Notes

Reference

Please cite the article:

"A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation" Alexander H. Liu, Yen-Cheng Liu, Yu-Ying Yeh, Yu-Chiang Frank Wang, NIPS'18

Please also cite the article if you find the face dataset helpful:

"Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation" Yen-Cheng Liu, Yu-Ying Yeh, Tzu-Chien Fu, Sheng-De Wang, Wei-Chen Chiu, Yu-Chiang Frank Wang, CVPR'18 (spotlight)