Keras is an open source neural network library written in Python. It is capable of running on top of MXNet, Deeplearning4j, TensorFlow, Microsoft Cognitive Toolkit or Theano. Designed to enable fast experimentation with deep neural networks, it focuses on being minimal, modular and extensible. It was developed as part of the research effort of project ONEIROS (Open-ended Neuro-Electronic Intelligent Robot Operating System), and its primary author and maintainer is François Chollet, a Google engineer.
|Original author(s)||François Chollet|
|Initial release||27 March 2015|
2.1.2 / 1 December 2017
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 an end-to-end machine-learning framework. It presents a higher-level, more intuitive set of abstractions that make it easy to configure neural networks regardless of the backend scientific computing library. Microsoft has been working to add a CNTK backend to Keras as well, and the functionality is currently in beta release with CNTK v2.0 .
The library 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, a Gitter channel and a Slack channel.
- "This Is What Makes Keras Different, According To Its Author". forbes.com. Retrieved 2016-09-20.
- Deeplearning4j Keras Frontend
- "Keras Documentation". keras.io. Retrieved 2016-09-18.
- Chollet GitHub Comment
- CNTK Keras GitHub Issue
- alexeyo. "CNTK_2_0_Release_Notes". docs.microsoft.com. Retrieved 2017-06-14.
- "François Chollet on Twitter". Retrieved 2016-09-18.