Register
Login
Resources
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Product
Data Engine LLMs Platform Enterprise
Pricing Explore
Connect to our Discord channel

README.md 1.5 KB

You have to be logged in to leave a comment. Sign In

DualGAN

DualGAN: unsupervised dual learning for image-to-image translation

architecture of DualGAN

day2night

How to setup

Prerequisites

Linux

Python

numpy

scipy

NVIDIA GPU + CUDA 8.0 + CuDNNv5.1

TensorFlow 1.0

Getting Started

Clone this repo:

git clone https://github.com/duxingren14/DualGAN.git

cd DualGAN

Train the model:

python main.py --phase train --dataset_name dataset_name

Test the model:

python main.py --phase test --dataset_name dataset_name

A portion of Datasets are available from:

facades: http://cmp.felk.cvut.cz/~tylecr1/facade/

sketch: http://mmlab.ie.cuhk.edu.hk/archive/cufsf/

maps: https://mega.nz/#!r8xwCBCD!lNBrY_2QO6pyUJziGj7ikPheUL_yXA8xGXFlM3GPL3c

oil-chinese: http://www.cs.mun.ca/~yz7241/, jump to http://www.cs.mun.ca/~yz7241/dataset/dualgan-dataset.zip

material-transfer: http://www.cs.mun.ca/~yz7241/

day-night: http://www.cs.mun.ca/~yz7241/

Experimental results:

day2night day2night

day2night

day2night

day2night

day2night

Acknowledgments

Codes are built on the top of pix2pix-tensorflow and DCGAN-tensorflow. Thanks for their precedent contributions!

Tip!

Press p or to see the previous file or, n or to see the next file

Comments

Loading...