https://github.com/Codersadis/SRCNN-MXNET

MXNET implementation for SRCNN
https://github.com/Codersadis/SRCNN-MXNET

Last synced: 2 months ago
JSON representation

MXNET implementation for SRCNN

• Host: GitHub
• URL: https://github.com/Codersadis/SRCNN-MXNET
• Owner: Codersadis
• Created: 2017-09-07T15:56:29.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2017-09-08T09:53:00.000Z (over 7 years ago)
• Last Synced: 2024-10-30T22:41:22.714Z (2 months ago)
• Language: Python
• Size: 18.7 MB
• Stars: 5
• Watchers: 2
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-MXNet - [1 - loth/SuperResolutionCNN) (<a name="Vision"></a>2. Vision / 2.8 Image Enhancement)

README

        
## SRCNN-MXNET 

This repo reproduces a prototype of the classical algorithm for Single Image Super resolution (SISR) with convolutional neural network based on MXNET. 

### Prequesity

- MXNET 0.11.0

- MKL/Numpy/h5py/scipy

### Test Environment

- CPU version of MXNET

- Win 10 64-bit & 8G 

### MISC

- The uploaded checkpoint may not provide high performance since only 1,000 iterations were done.

### Reference

- Dong C, Loy C C, He K, et al. Image super-resolution using deep convolutional networks[J]. IEEE T. PAMI, 2016, 38(2): 295-307.