Skip to content
Pytorch implementation of Conditional image-to-image translation (CVPR 2018)
Branch: master
Clone or download
Latest commit cdcb2e6 Aug 22, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
assets Delete 2.png Aug 3, 2018
data Update README.md Aug 3, 2018
LICENSE Create LICENSE Aug 7, 2018
README.md Update README.md Aug 3, 2018
networks.py Add files via upload Aug 3, 2018
train.py Update train.py Aug 22, 2018
utils.py Add files via upload Aug 3, 2018

README.md

pytorch-Conditional-image-to-image-translation

Pytorch implementation of Conditional image-to-image translation [1] (CVPR 2018)

  • Parameters without information in the paper were set arbitrarily. (I could not find the supplementary document)

Usage

python train.py --dataset dataset

Folder structure

The following shows basic folder structure.

├── data
    ├── dataset # not included in this repo
        ├── trainA
            ├── aaa.png
            ├── bbb.jpg
            └── ...
        ├── trainB
            ├── ccc.png
            ├── ddd.jpg
            └── ...
        ├── testA
            ├── eee.png
            ├── fff.jpg
            └── ...
        └── testB
            ├── ggg.png
            ├── hhh.jpg
            └── ...
├── train.py # training code
├── utils.py
├── networks.py
└── name_results # results to be saved here

Resutls

paper results

celebA gender translation results (100 epoch)

InputA - InputB - A2B - B2A (this repo)

Development Environment

  • NVIDIA GTX 1080 ti
  • cuda 8.0
  • python 3.5.3
  • pytorch 0.4.0
  • torchvision 0.2.1

Reference

[1] Lin, Jianxin, et al. "Conditional image-to-image translation." The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(July 2018). 2018.

(Full paper: http://openaccess.thecvf.com/content_cvpr_2018/papers/Lin_Conditional_Image-to-Image_Translation_CVPR_2018_paper.pdf)

You can’t perform that action at this time.