Jump to content

Keras: Difference between revisions

From Wikipedia, the free encyclopedia
Browse history interactively
← Previous editNext edit →
Content deleted Content added
VisualWikitext
Keras only supports TensorFlow backend since release 2.4
Line 25: Line 25:
}}
}}


'''Keras''' is an [[Open-source software|open-source]] [[Artificial neural network|neural-network]] library written in [[Python (programming language)|Python]]. It is capable of running on top of [[TensorFlow]], [[Microsoft Cognitive Toolkit]], [[R (programming language)|R]], [[Theano (software)|Theano]], or [[PlaidML]].<ref>{{Cite web|url=https://keras.io/backend/|title=Keras backends|website=keras.io|access-date=2018-02-23}}</ref><ref name="why-keras">{{Cite web|url=https://keras.io/why-use-keras/|title=Why use Keras?|website=keras.io|access-date=2020-03-22}}</ref><ref>{{Cite web|url=https://keras.rstudio.com/|title=R interface to Keras|website=keras.rstudio.com|access-date=2020-03-22}}</ref> Designed to enable fast experimentation with [[Deep learning|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),<ref>{{Cite web|url=https://keras.io/#why-this-name-keras|title=Keras Documentation|website=keras.io|access-date=2016-09-18}}</ref> and its primary author and maintainer is François Chollet, a [[Google]] engineer. Chollet also is the author of the XCeption deep neural network model.<ref>{{cite arXiv
'''Keras''' is an [[Open-source software|open-source]] library that provides a [[Python (programming language)|Python]] interface for [[artificial neural network]]s. Keras acts as an interface for the [[TensorFlow]] library.
Up until version 2.3 Keras supported multiple backends, including [[TensorFlow]], [[Microsoft Cognitive Toolkit]], [[R (programming language)|R]], [[Theano (software)|Theano]], and [[PlaidML]].<ref>{{Cite web|url=https://keras.io/backend/|title=Keras backends|website=keras.io|access-date=2018-02-23}}</ref><ref name="why-keras">{{Cite web|url=https://keras.io/why-use-keras/|title=Why use Keras?|website=keras.io|access-date=2020-03-22}}</ref><ref>{{Cite web|url=https://keras.rstudio.com/|title=R interface to Keras|website=keras.rstudio.com|access-date=2020-03-22}}</ref> Designed to enable fast experimentation with [[Deep learning|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),<ref>{{Cite web|url=https://keras.io/#why-this-name-keras|title=Keras Documentation|website=keras.io|access-date=2016-09-18}}</ref> and its primary author and maintainer is François Chollet, a [[Google]] engineer. Chollet also is the author of the XCeption deep neural network model.<ref>{{cite arXiv
|title=Xception: Deep Learning with Depthwise Separable Convolutions
|title=Xception: Deep Learning with Depthwise Separable Convolutions
|last1=Chollet |first1=François
|last1=Chollet |first1=François
Line 31: Line 33:
|year=2016
|year=2016
}}</ref>
}}</ref>

In 2017, Google's TensorFlow team decided to support Keras in TensorFlow's core library.<ref>{{Cite web|url=https://www.tensorflow.org/api_docs/python/tf/keras|title=Module: tf.keras {{!}} TensorFlow|website=TensorFlow|language=en|access-date=2018-11-14}}</ref> 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.<ref>[https://github.com/fchollet/keras/issues/5050 Chollet GitHub Comment]</ref> [[Microsoft]] added a [[CNTK]] backend to Keras as well, available as of CNTK v2.0.<ref>[https://github.com/Microsoft/CNTK/issues/797 CNTK Keras GitHub Issue]</ref><ref>{{Cite web|url=https://docs.microsoft.com/en-us/cognitive-toolkit/ReleaseNotes/CNTK_2_0_Release_Notes|title=CNTK_2_0_Release_Notes|last=alexeyo|website=docs.microsoft.com|language=en-us|access-date=2017-06-14}}</ref>


==Features==
==Features==
Line 49: Line 49:
==References==
==References==
{{Reflist}}
{{Reflist}}

==Further reading==
* {{cite book |first=François |last=Chollet |first2=J. J. |last2=Allaire |authorlink2=Joseph J. Allaire |title=Deep Learning with R |location= |publisher=Manning |year=2018 |isbn=978-1-61729-554-6 }}


==External links==
==External links==

Revision as of 14:03, 2 October 2020

Keras
Original author(s)François Chollet
Developer(s)various
Initial release27 March 2015; 9 years ago (2015-03-27)
Stable release
2.4.0[1] / 17 June 2020; 4 years ago (2020-06-17)
Repository
Written inPython
PlatformCross-platform
TypNeural networks
LicenseMIT
Websitekeras.io

Keras is an open-source library that provides a Python interface for artificial neural networks. Keras acts as an interface for the TensorFlow library.

Up until version 2.3 Keras supported multiple backends, including TensorFlow, Microsoft Cognitive Toolkit, R, Theano, and PlaidML.[2][3][4] 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),[5] and its primary author and maintainer is François Chollet, a Google engineer. Chollet also is the author of the XCeption deep neural network model.[6]

Eigenschaften

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 to simplify the coding necessary for writing deep neural network code. The code is hosted on GitHub, and community support forums include the GitHub issues page, and a Slack channel.

In addition to standard neural networks, Keras has support for convolutional and recurrent neural networks. It supports other common utility layers like dropout, batch normalization, and pooling.[7]

Keras allows users to productize deep models on smartphones (iOS and Android), on the web, or on the Java Virtual Machine.[3] It also allows use of distributed training of deep-learning models on clusters of Graphics processing units (GPU) and tensor processing units (TPU).[8]

Traction

Keras claims over 250,000 individual users as of mid-2018.[3] Keras was the 10th most cited tool in the KDnuggets 2018 software poll and registered a 22% usage.[9]

See also

References

  1. ^ GitHub release, retrieved 2020-06-17
  2. ^ "Keras backends". keras.io. Retrieved 2018-02-23.
  3. ^ a b c "Why use Keras?". keras.io. Retrieved 2020-03-22.
  4. ^ "R interface to Keras". keras.rstudio.com. Retrieved 2020-03-22.
  5. ^ "Keras Documentation". keras.io. Retrieved 2016-09-18.
  6. ^ Chollet, François (2016). "Xception: Deep Learning with Depthwise Separable Convolutions". arXiv:1610.02357.
  7. ^ "Core - Keras Documentation". keras.io. Retrieved 2018-11-14.
  8. ^ "Using TPUs | TensorFlow". TensorFlow. Retrieved 2018-11-14.
  9. ^ Piatetsky, Gregory. "Python eats away at R: Top Software for Analytics, Data Science, Machine Learning in 2018: Trends and Analysis". KDnuggets. KDnuggets. Retrieved 30 May 2018.
Retrieved from "https://en.wikipedia.org/w/index.php?title=Keras&oldid=981468012"