Keras

Source: Wikipedia, the free encyclopedia.
Keras
Original author(s)François Chollet
Developer(s)ONEIROS
Initial release27 March 2015; 10 years ago (2015-03-27)
Stable release
3.9.0[1] / 4 March 2025; 39 days ago (4 March 2025)
Repository
Written in
JAX or PyTorch (and more)
LicenseApache 2.0
Websitekeras.io Edit this on Wikidata

Keras is an

artificial neural networks. Keras was first independent software, then integrated into the TensorFlow library, and later supporting more. "Keras 3 is a full rewrite of Keras [and can be used] as a low-level cross-framework language to develop custom components such as layers, models, or metrics that can be used in native workflows in JAX, TensorFlow, or PyTorch — with one codebase."[2] Keras 3 will be the default Keras version for TensorFlow 2.16 onwards, but Keras 2 can still be used.[3]

History

The name 'Keras' derives from the Ancient Greek word κέρας (Keras) meaning 'horn'.[4]

Designed to enable fast experimentation with

Xception deep neural network model.[7]

Up until version 2.3, Keras supported multiple backends, including TensorFlow, Microsoft Cognitive Toolkit, Theano, and PlaidML.[8][9][10]

From version 2.4 up until version 3.0, only TensorFlow was supported. Starting with version 3.0 (as well as its preview version, Keras Core), however, Keras has become multi-backend again, supporting

JAX, and PyTorch.[11] It now also supports OpenVINO!
.

Features

Keras contains numerous implementations of commonly used neural-network building blocks such as layers,

objectives, activation functions, optimizers, and a host of tools for working with image and text data to simplify programming in deep neural network area.[12] The code is hosted on GitHub, and community support forums include the GitHub issues page.[13]

In addition to standard neural networks, Keras has support for

pooling.[14]

Keras allows users to produce deep models on smartphones (

tensor processing units (TPU).[15]

See also

  • Comparison of deep-learning software

References

  1. ^ "Release 3.9.0". 4 March 2025. Retrieved 25 March 2025.
  2. ^ "Keras: Deep Learning for humans". keras.io. Retrieved 2024-04-30.
  3. ^ "What's new in TensorFlow 2.16". Retrieved 2024-04-30.
  4. ^ Team, Keras. "Keras documentation: About Keras 3". keras.io. Retrieved 2024-02-10.
  5. ^ "Keras Documentation". keras.io. Retrieved 2016-09-18.
  6. ^ "Farewell and thank you for the continued partnership, Francois Chollet!". Google Developers Blog. Retrieved 2025-03-19.
  7. arXiv:1610.02357 [cs.CV
    ].
  8. ^ "Keras backends". keras.io. Retrieved 2018-02-23.
  9. ^ a b "Why use Keras?". keras.io. Retrieved 2020-03-22.
  10. ^ "R interface to Keras". keras.rstudio.com. Retrieved 2020-03-22.
  11. ^ Chollet, François; Usui, Lauren (2023). "Introducing Keras Core: Keras for TensorFlow, JAX, and PyTorch". Keras.io. Retrieved 2023-07-11.
  12. ISBN 9788894787603
    .
  13. ^ https://github.com/keras-team/keras
  14. ^ "Core - Keras Documentation". keras.io. Retrieved 2018-11-14.
  15. ^ "Using TPUs | TensorFlow". TensorFlow. Archived from the original on 2019-06-04. Retrieved 2018-11-14.
Retrieved from "https://en.wikipedia.org/w/index.php?title=Keras&oldid=1284899399"
This page is based on the copyrighted Wikipedia article: Keras. Articles is available under the CC BY-SA 3.0 license; additional terms may apply.Privacy Policy