Skip to content

PyTorch implementation of "Image-to-Image Translation Using Conditional Adversarial Networks".

Notifications You must be signed in to change notification settings

mrzhu-cool/pix2pix-pytorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

pix2pix-pytorch

PyTorch implementation of Image-to-Image Translation Using Conditional Adversarial Networks.

Based on pix2pix by Phillip Isola et al.

The examples from the paper:

examples

Prerequisites

  • Linux
  • Python, Numpy, PIL
  • pytorch 0.4.0
  • torchvision 0.2.1

Getting Started

  • Clone this repo:

    git clone git@github.com:mrzhu-cool/pix2pix-pytorch.git cd pix2pix-pytorch

  • Get dataset

    unzip dataset/facades.zip

  • Train the model:

    python train.py --dataset facades --cuda

  • Test the model:

    python test.py --dataset facades --cuda

Acknowledgments

This code is a simple implementation of pix2pix. Easier to understand. Note that we use a downsampling-resblocks-upsampling structure instead of the unet structure in this code, therefore the results of this code may inconsistent with the results presented in the paper.

Highly recommend the more sophisticated and organized code pytorch-CycleGAN-and-pix2pix by Jun-Yan Zhu.

About

PyTorch implementation of "Image-to-Image Translation Using Conditional Adversarial Networks".

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •  

Languages