Skip to content
Image Super-Resolution Using Very Deep Residual Channel Attention Networks Implementation in Tensorflow
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
assets
output
.gitignore
LICENSE Initial commit Sep 28, 2018
README.md
config.py update: seed to 1 Oct 5, 2018
dataset.py update: refactor codes May 25, 2019
metric.py
model.py update: refactor codes May 25, 2019
test.py
tfutil.py fix: weight & bias fixing for pre/post processing, mean_shift function, Oct 11, 2018
train.py fix: true_divide problem Nov 6, 2018
util.py update: image rotation for augmentation, #4 Oct 12, 2018

README.md

rcan-tensorflow

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

ECCV 2018 paper

Orig PyTorch Implementation

License: MIT Total alerts Language grade: Python

Introduction

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

Here're the proposed architectures in the paper.

  • Channel Attention (CA) CA

  • Residual Channel Attention Block (RCAB) RCAB

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

All images got from the paper

Dependencies

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

DataSet

DataSet LR HR
DIV2K 800 (192x192) 800 (768x768)

Usage

training

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

testing

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

Results

  • 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) img img

To-Do

  1. None

Author

HyeongChan Kim / @kozistr

You can’t perform that action at this time.