Keras

Keras
Original author(s) François Chollet
Developer(s) various
Stable release
1.1.1 / 1 November 2016 (2016-11-01)
Development status active
Written in Python
Platform cross-platform
Available in Python
Type Neural Networks
License MIT
Website keras.io

Keras is an open source neural network library written in Python. It is capable of running on top of either Tensorflow or Theano.[1] 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),[2] and its primary author and maintainer is François Chollet.

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 as well as a Slack channel. As of Sept 16, 2016, Keras is the second fastest growing deep learning framework after Google's Tensorflow.[3]

See also

References

  1. ↑ "This Is What Makes Keras Different, According To Its Author". forbes.com. Retrieved 2016-09-20.
  2. ↑ "Keras Documentation". keras.io. Retrieved 2016-09-18.
  3. ↑ "François Chollet on Twitter". Retrieved 2016-09-18.

External links

This article is issued from Wikipedia - version of the 11/21/2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.