Open main menu

Wikipedia β

Keras is an open source neural network library written in Python. It is capable of running on top of TensorFlow, Microsoft Cognitive Toolkit, Theano, or MXNet.[1] Designed to enable fast experimentation with deep neural networks, it focuses on being user-friendly, modular, and extensible. It was developed as part of the research effort of project ONEIROS (Open-ended Neuro-Electronic Intelligent Robot Operating System),[2] and its primary author and maintainer is François Chollet, a Google engineer.

Keras
Keras Logo.jpg
Original author(s) François Chollet
Developer(s) various
Initial release 27 March 2015; 3 years ago (2015-03-27)
Stable release
2.1.6 / 23 April 2018; 30 days ago (2018-04-23)
Repository Edit this at Wikidata
Written in Python
Platform Cross-platform
Type Neural Networks
License MIT
Website keras.io

In 2017, Google's TensorFlow team decided to support Keras in TensorFlow's core library. Chollet explained that Keras was conceived to be an interface rather than a standalone machine-learning framework. It offers a higher-level, more intuitive set of abstractions that make it easy to develop deep learning models regardless of the computational backend used.[3] Microsoft added a CNTK backend to Keras as well, available as of CNTK v2.0.[4][5]

Contents

FeaturesEdit

Keras contains numerous implementations of commonly used neural network building blocks such as layers, objectives, activation functions, optimizers, and a host of tools to make working with image and text data easier. The code is hosted on GitHub, and community support forums include the GitHub issues page, and a Slack channel.

Keras allows users to productize deep models on smartphones (iOS and Android), on the web, or on the Java Virtual Machine.[6]

It also allows use of distributed training of deep learning models on clusters of Graphics Processing Units (GPU).

TractionEdit

Keras has over 200,000 users as of November 2017.[6][non-primary source needed]

See alsoEdit

ReferencesEdit

  1. ^ "Keras backends". keras.io. Retrieved 2018-02-23. 
  2. ^ "Keras Documentation". keras.io. Retrieved 2016-09-18. 
  3. ^ Chollet GitHub Comment
  4. ^ CNTK Keras GitHub Issue
  5. ^ alexeyo. "CNTK_2_0_Release_Notes". docs.microsoft.com. Retrieved 2017-06-14. 
  6. ^ a b "Why use Keras?". keras.io. Retrieved 2018-02-23. 

External linksEdit