Image Super-Resolution Using Very Deep Residual Channel Attention Networks Implementation in Tensorflow

ECCV 2018 paper

Orig PyTorch Implementation

This repo contains my implementation of RCAN (Residual Channel Attention Networks).

Here're the proposed architectures in the paper.

• Channel Attention (CA)

• Residual Channel Attention Block (RCAB)

• Residual Channel Attention Network (RCAN), Residual Group (GP)

All images got from the paper

• Python
• Tensorflow 1.x
• tqdm
• h5py
• scipy
• cv2

# hyper-paramters in config.py, you can edit them!
$ python3 train.py --data_from [img or h5]

$ python3 test.py --src_image sample.png --dst_image sample-upscaled.png

• OOM on my machine :(... I can't test my code, but maybe code runs fine.

Example\Resolution	192x192x3 image (sample)	768x768x3 image (generated)
Example1 (X4 scaled)

1. None

HyeongChan Kim / @kozistr