This project is a tensorflow implementation of the impressive work Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network.
The result on BSD100, Set14, Set5 will be reported later. The code is highly inspired by the pix2pix-tensorflow.
- The result from the paper:
| SRGAN result | Original | SRGAN result | Original |
 |
 |
 |
 |
| Our result | Original | Our result | Original |
 |
 |
 |
 |
- The result from my implementation:
- tensorflow (tested on r1.0, r1.2)
- TF slim library
- Ubuntu 16.04 with tensorflow GPU edition
# clone the repository from github
git clone https://github.com/brade31919/SRGAN-tensorflow.git
cd SRGAN-tensorflow/
# [optional] download the training dataset