Skip to content

Latest commit

 

History

History
38 lines (24 loc) · 1.05 KB

README.md

File metadata and controls

38 lines (24 loc) · 1.05 KB
Raw

SRCNN

An implementation of SRCNN

Requirements

Theano v0.9

NeuralNet

Result

The model is trained using the scheme described in the paper with some small simplifications.

Original Image

Origin

Bicubic interpolation

Bicubic

SRCNN interpolation

SRCNN

Usages

To train SRCNN using the current training scheme

python train_srcnn.py

To test SRCNN with an image

python upsample.py image_destination

Credits

C. Dong, C. C. Loy, K. He, and X. Tang, "Image super-resolution using deep convolutional networks," IEEE transactions on pattern analysis and machine intelligence, vol. 38, pp. 295-307, 2016.