Git Product home page Git Product logo

cae's Introduction

Convolutional Auto-encoders

This repo is aiming to provide a set of Convolutional Auto-encoder implementations (CAEs) for Deep Learning.

Convolutional Auto-encoder did not draw so much attention since it's proposed. However, I think that this model offered a very nice unsupervised feature learning model from neural network persepective.

Following dependencies are required:

  • Python 2.7.8
  • numpy
  • scipy
  • theano

You can also use Anaconda directly, this python distribution will offer you all dependencies.

##Updates

  • ConvNet layer [20141021]
  • Original ConvNet Auto-encoder [20141021]
  • Tested for AWS GPU instance [20141025]
  • Example for classification [20141025]
  • Add some support functions for ConvNet Layer [20141027]

##To-do

  • Multiple activation function support
  • Support functions for ConvNet Layer and ConvNet AE
  • Sparse ConvNet Auto-encoder
  • Stacked ConvNet Auto-encoder

##Notes

  • All experiment in this repo are conducted on GPU, in order to run it faster, you are suggested to have a GPU on your machine.

  • If you forked this repo, use and modifiy update.sh to avoid updating unnecessary files and data.

  • Tested on AWS GPU instance, the performance looks like Tesla K20C.

##Contacts

Hu Yuhuang
Advanced Robotic Lab
Department of Artificial Intelligence
Faculty of Computer Science & IT
University of Malaya
Email: [email protected]

cae's People

Contributors

duguyue100 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.