Keras
 | |
| Original author(s) | François Chollet |
|---|---|
| Developer(s) | various |
| Stable release | 1.1.1
/ 1 November 2016 |
| Repository | |
| Written in | Python |
| Platform | cross-platform |
| Available in | Python |
| Type | Neural Networks |
| License | MIT |
| Website | keras |
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
- ^ "This Is What Makes Keras Different, According To Its Author". forbes.com. Retrieved 2016-09-20.
- ^ "Keras Documentation". keras.io. Retrieved 2016-09-18.
- ^ "François Chollet on Twitter". Retrieved 2016-09-18.
External links
| Open source | |
|---|---|
| Proprietary |
|
 | This scientific software article is a stub. You can help Wikipedia by expanding it. |