Wizaron / Shift-Net_pytorch

Pytorch implementation of Shift-Net: Image Inpainting via Deep Feature Rearrangement

Shift-Net_pytorch

This repositity is our Pytorch implementation for Shift-Net, it is just for those who are interesting in our work and want to get a skeleton Pytorch implemention. We DO NOT guarantee the efficiency and performance.

The torch version Shift-Net is the right choice if you would like to reproduce the fine results.

Prerequisites

• Linux or OSX.
• Python 2 or Python 3.
• CPU or NVIDIA GPU + CUDA CuDNN.
• Tested on pytorch 0.3

Getting Started

Installation

• Install PyTorch and dependencies from http://pytorch.org/
• Install python libraries visdom and dominate.

pip install visdom
pip install dominate

• Clone this repo:

git clone https://github.com/Zhaoyi-Yan/Shift-Net_pytorch
cd Shift-Net_pytorch

tain and test

• Download your own inpainting datasets.

• Train a model:

python train.py

• To view training results and loss plots, run python -m visdom.server and click the URL http://localhost:8097.
• Test the model

python test.py

The test results will be saved to a html file here: ./results/.

Acknowledgments

We benefit a lot from pytorch-CycleGAN-and-pix2pix