GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → YeongHyeon → Super Resolution_cnn

YeongHyeon / Super Resolution_cnn

Licence: mit
Implementation of 'Image Super-Resolution using Deep Convolutional Network'

Programming Languages

python
139335 projects - #7 most used programming language

Labels

tensorflowarchitecturesuper-resolutioninterpolation

Projects that are alternatives of or similar to Super Resolution cnn

Pytoflow
The py version of toflow → https://github.com/anchen1011/toflow
Stars: ✭ 83 (+207.41%)
Mutual labels:  super-resolution, interpolation
Bicubic-interpolation
Bicubic interpolation for images (Python)
Stars: ✭ 88 (+225.93%)
Mutual labels:  interpolation, super-resolution
Toflow
TOFlow: Video Enhancement with Task-Oriented Flow
Stars: ✭ 314 (+1062.96%)
Mutual labels:  super-resolution, interpolation
Scn
Scale-wise Convolution for Image Restoration
Stars: ✭ 26 (-3.7%)
Mutual labels:  super-resolution
Snowball
Android Clean Code Sample Project
Stars: ✭ 26 (-3.7%)
Mutual labels:  architecture
Cdc Kafka Hadoop
MySQL to NoSQL real time dataflow
Stars: ✭ 13 (-51.85%)
Mutual labels:  architecture
Awesome Scalability
The Patterns of Scalable, Reliable, and Performant Large-Scale Systems
Stars: ✭ 36,688 (+135781.48%)
Mutual labels:  architecture
Pytorch Implemented Deep Sr Itm
A Pytorch implemented Deep SR-ITM (ICCV2019)
Stars: ✭ 23 (-14.81%)
Mutual labels:  super-resolution
Karchi
Repository that showcases 3 different Android app architectures, all with Java and Kotlin versions: "Standard Android", MVP and MVVM. The exact same app is built 6 times following the different patterns.
Stars: ✭ 20 (-25.93%)
Mutual labels:  architecture
Docker Architecture Demo
⛵️ Docker architecture demo
Stars: ✭ 10 (-62.96%)
Mutual labels:  architecture
Training extensions
Trainable models and NN optimization tools
Stars: ✭ 857 (+3074.07%)
Mutual labels:  super-resolution
Spring Boot Elasticsearch Lire Docker
Spring-boot+ElasticSearch+LIRE+SwaggerUI RESTful.
Stars: ✭ 7 (-74.07%)
Mutual labels:  architecture
React Styleguide
ReactJS style guide for component-based projects.
Stars: ✭ 14 (-48.15%)
Mutual labels:  architecture
Flutter Cinema
Learn to create flutter app with BLoC Architecture
Stars: ✭ 26 (-3.7%)
Mutual labels:  architecture
Java Best Practices
Best practices in Coding, Designing and Architecting Java Applications
Stars: ✭ 909 (+3266.67%)
Mutual labels:  architecture
Rxfeedback.swift
The universal system operator and architecture for RxSwift
Stars: ✭ 928 (+3337.04%)
Mutual labels:  architecture
Androidarchitecture
Recommended architecture by Android
Stars: ✭ 883 (+3170.37%)
Mutual labels:  architecture
Evc Swift
Engine - View - Controller template
Stars: ✭ 9 (-66.67%)
Mutual labels:  architecture
Go Zero
go-zero is a web and rpc framework written in Go. It's born to ensure the stability of the busy sites with resilient design. Builtin goctl greatly improves the development productivity.
Stars: ✭ 13,156 (+48625.93%)
Mutual labels:  architecture
Awesome Software Architecture
A curated list of resources on software architecture
Stars: ✭ 857 (+3074.07%)
Mutual labels:  architecture
View All Similar Projects ➔

[TensorFlow] Super-Resolution CNN

TensorFlow implementation of 'Image Super-Resolution using Deep Convolutional Network'. PyTorch version is also provided in Related Repository.

Architecture

The architecture of the Super-Resolution Network (SRCNN).

The architecture constructed by three convolutional layers, and the kernel size are 9x9, 1x1, 3x2 respectively. It used RMS loss and stochastic gradient descent opeimizer for training in this repository, but original one was trained by MSE loss (using same optimizer). The input of the SRCNN is Low-Resolution (Bicubic Interpolated) image that same size of the output image, and the output is High-Resolution.

Results

Reconstructed image in each iteration (1k, 10k, 100k iterations).

Comparison between the input (Bicubic Interpolated), reconstructed image (by SRCNN), and target (High-Resolution) image.

Requirements

  • Python 3.6.8
  • Tensorflow 1.14.0
  • Numpy 1.14.0
  • Matplotlib 3.1.1

Reference

[1] Image Super-Resolution Using Deep Convolutional Networks, Chao Dong et al., https://ieeexplore.ieee.org/abstract/document/7115171/
[2] Urban 100 dataset, Huang et al., https://sites.google.com/site/jbhuang0604/publications/struct_sr

First commit: 21.April.2018
Version Update: 28.August.2019

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].