https://github.com/znxlwm/pytorch-cyclegan

Pytorch implementation of CycleGAN.
https://github.com/znxlwm/pytorch-cyclegan

cyclegan gan generative-adversarial-network generative-model image-translation pytorch

Last synced: 2 months ago
JSON representation

Pytorch implementation of CycleGAN.

• Host: GitHub
• URL: https://github.com/znxlwm/pytorch-cyclegan
• Owner: znxlwm
• Created: 2017-08-24T06:13:27.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2017-09-06T04:17:01.000Z (over 7 years ago)
• Last Synced: 2024-09-05T15:48:30.212Z (5 months ago)
• Topics: cyclegan, gan, generative-adversarial-network, generative-model, image-translation, pytorch
• Language: Python
• Size: 6.71 MB
• Stars: 40
• Watchers: 4
• Forks: 8
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# pytorch-CycleGAN

Pytorch implementation of CycleGAN [1].

* you can download datasets: https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/

* you can see more information for network architecture and training details in https://arxiv.org/pdf/1703.10593.pdf

## dataset

* apple2orange

  * apple training images: 995, orange training images: 1,019, apple test images: 266, orange test images: 248

* horse2zebra

  * horse training images: 1,067, zebra training images: 1,334, horse test images: 120, zebra test images: 140

## Resutls

### apple2orange (after 200 epochs)

* apple2orange

 Input 

 Output 

 Reconstruction 































* orange2apple

 Input 

 Output 

 Reconstruction 































* Learning Time

  * apple2orange - Avg. per epoch: 299.38 sec; Total 200 epochs: 62,225.33 sec

### horse2zebra (after 200 epochs)

* horse2zebra

 Input 

 Output 

 Reconstruction 































* zebra2horse

 Input 

 Output 

 Reconstruction 































* Learning Time

  * horse2zebra - Avg. per epoch: 299.25 sec; Total 200 epochs: 61,221.27 sec

## Development Environment

* Ubuntu 14.04 LTS

* NVIDIA GTX 1080 ti

* cuda 8.0

* Python 2.7.6

* pytorch 0.1.12

* matplotlib 1.3.1

* scipy 0.19.1

## Reference

[1] Zhu, Jun-Yan, et al. "Unpaired image-to-image translation using cycle-consistent adversarial networks." arXiv preprint arXiv:1703.10593 (2017).

(Full paper: https://arxiv.org/pdf/1703.10593.pdf)