Skip to content

Latest commit

 

History

History
34 lines (24 loc) · 919 Bytes

README.md

File metadata and controls

34 lines (24 loc) · 919 Bytes

Pytorch-LapSRN

A unofficial implementation of paper Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution, the official MatConvNet implementation is here:LapSRN. The Network Architecture of this code is based on section.2 in the supplementary material of this peper.

Prerequisites

  • Linux
  • Python
  • NVIDIA GPU >= 4GB
  • pytorch
  • torchvision

Usage

  • Clone this repo:
[email protected]:BUPTLdy/Pytorch-LapSRN.git
  • Train the model
python train.py --cuda
  • Test the model

There is a pretrained model in the model folder, you can test the model directly.

python test.py --cuda