Giter Site home page Giter Site logo

parallel-cnn's Introduction

Parallel Convolutional Neural Networks

아래의 두 연산 즉, CNN 을 구성하는 Convolutional & Max-pooling layer 의 수행 연산을 병렬로 처리하기 위해 multi-process & multi-thread 기술을 사용

Convolution(합성곱) 연산

Max-pooling 연산


목표

  1. 주어진 Input Matrix에 대하여 Filter를 이동해 가면서 순서대로 합성곱 연산을 하는 것이 아닌 각 위치(3*3 단위)에서의 합성곱 연산을 병렬로 수행하여 Output Matrix 를 생성하는 것이 목표

2. 마찬가지로 앞 과정에서 만들어진 Output Matrix 에 대하여 각 위치(2*2 단위)에서의 Max-pooling 연산을 병렬로 수행하여 최종적인 결과 Matrix 를 생성하는 것이 목표

parallel-cnn's People

Contributors

obyeonghyeon avatar

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

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.