/SR_Framework

A generic framework which implements all famouts super-resolution models

Primary LanguagePython

SR_Framework

A generic super-resolution framework which implements the following networks (Updating...)

Implement some useful functions for article figures. Like the following:

  • 1. generate_best: Automatically compare your method with other methods and visualize the best patches.

compare.jpg

  • 2. Frequency_analysis: Convert an image to 1-D spectral densities.

frequency.jpg

  • 3. relation: Explore relations in fuse stage.(eg. torch.cat([t1, t2, t3, c4], dim=1) and then fuse them with 1x1 convolution)

relation.jpg

  • 4. feature_map: Visualize feature map.(average feature maps along channel axis)

feature_map.jpg