by tegg89

Image Super-Resolution Using Deep Convolutional Networks in Tensorflow

464 Stars 249 Forks Last release: Not found MIT License 40 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:


Tensorflow implementation of Convolutional Neural Networks for super-resolution. The original Matlab and Caffe from official website can be found here.


  • Tensorflow
  • Scipy version > 0.18 ('mode' option from scipy.misc.imread function)
  • h5py
  • matplotlib

This code requires Tensorflow. Also scipy is used instead of Matlab or OpenCV. Especially, installing OpenCV at Linux is sort of complicated. So, with reproducing this paper, I used scipy instead. For more imformation about scipy, click here.


For training,


For testing,
python --is_train False --stride 21


After training 15,000 epochs, I got similar super-resolved image to reference paper. Training time takes 12 hours 16 minutes and 1.41 seconds. My desktop performance is Intel I7-6700 CPU, GTX970, and 16GB RAM. Result images are shown below.

Original butterfly image: orig
Bicubic interpolated image: bicubic
Super-resolved image: srcnn


We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.