Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Reimplementation of CycleGAN

License

NotificationsYou must be signed in to change notification settings

LynnHo/CycleGAN-Tensorflow-2

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Recommendation


New

  • 2018.04.13: We modify the codes: use the newest tensorflow 1.7 API, and remove the redundancies.

  • 2017.12.22: We add a simple PyTorch implementation, see the "pytorch" folder.

CycleGAN

Tensorflow implementation of CycleGAN.

Paper:Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial NetworksAuthor:Jun-Yan Zhuet al.

Exemplar results on testset

  • gif: horse -> zebra
  • row 1: horse -> zebra -> reconstructed horse, row 2: zebra -> horse -> reconstructed zebra
  • row 1: apple -> orange -> reconstructed apple, row 2: orange -> apple -> reconstructed orange

Prerequisites

  • tensorflow r1.7
  • python 2.7

Usage

cd CycleGAN-Tensorflow-PyTorch-master

Download Datasets

  • Download the horse2zebra dataset:
sh ./download_dataset.sh horse2zebra
  • Download the apple2orange dataset:
sh ./download_dataset.sh apple2orange
  • See download_dataset.sh for more datasets

Train Example

CUDA_VISIBLE_DEVICES=0 python train.py --dataset=horse2zebra

Test Example

CUDA_VISIBLE_DEVICES=0 python test.py --dataset=horse2zebra

[8]ページ先頭

©2009-2025 Movatter.jp