/pix2pix-keras

Image-to-Image Translation with Conditional Adversarial Networks (Pix2pix) implementation in keras

Primary LanguagePythonMIT LicenseMIT

pix2pix-keras

Pix2pix implementation in keras.

Original paper: Image-to-Image Translation with Conditional Adversarial Networks (pix2pix)
Paper Authors and Researchers: Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros

To run

# clone repo and step into root dir
git clone https://github.com/williamFalcon/pix2pix-keras.git
cd pix2pix-keras/pix2pix

# download facades dataset   
python utils/facades_dataset.py

# setup conda(or virtual env)
conda create -n pix python=3.4  
source activate pix

# install requirements
pip install requirements.txt

# start training
python main.py 

About this implementation

A full write-up about this implementation is available at my blog https://www.williamfalcon.com/deeplearningimplementations/pix2pix-keras