Code Monkey home page Code Monkey logo

srcnn-keras's Introduction

Keras implementation of SRCNN

The original paper is Learning a Deep Convolutional Network for Image Super-Resolution

My implementation have some difference with the original paper, include:

  • use Adam alghorithm for optimization, with learning rate 0.0003 for all layers.
  • Use the opencv library to produce the training data and test data, not the matlab library. This difference may caused some deteriorate on the final results.
  • I did not set different learning rate in different layer, but I found this network still work.
  • The color space of YCrCb in Matlab and OpenCV also have some difference. So if you want to compare your results with some academic paper, you may want to use the code written with matlab.

Use:

Create your own data

open prepare_data.py and change the data path to your data

Excute: python prepare_data.py

training and test:

Excute: python main.py

Result(training for 200 epoches on 91 images, with upscaling factor 2):

Results on Set5 dataset:

srcnn-keras's People

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.