Skip to content

PyTorch implementation of SRCNN and EDSR neural networks for Super Resolution Single Frame tasks

Notifications You must be signed in to change notification settings

FilippoVajana/pytorch-SuperResolution

Repository files navigation

Deep PyTorch Super Resolution

A PyTorch 1.1.0 implementation of SRCNN and EDSR neural networks for Super Resolution Single Frame tasks.

Usage

Since the documentation is a WIP I suggest taking a look at the following files to figure out how to use my code:

  1. init_data.py: starting from source data it performs some preprocessing (eg. RGB-to-GreyScale) and organizes examples and labels into a folder hierarchy.

  2. init_models.py: performs training and testing of the two models and collects performance logs during all the operations.

  3. benchmark.py: using pre trained models and performance data generated by the previous script, it compares the models and plots useful informations.

About

PyTorch implementation of SRCNN and EDSR neural networks for Super Resolution Single Frame tasks

Topics

Resources

Stars

Watchers

Forks

Packages

No packages published

Languages