keras: R Interface to 'Keras'

Interface to 'Keras' <>, a high-level neural networks 'API'. 'Keras' was developed with a focus on enabling fast experimentation, supports both convolution based networks and recurrent networks (as well as combinations of the two), and runs seamlessly on both 'CPU' and 'GPU' devices.

Version: 2.1.4
Depends: R (≥ 3.2)
Imports: reticulate (≥ 1.5), tensorflow (≥ 1.5), tfruns (≥ 1.0), magrittr, zeallot, methods, R6
Suggests: ggplot2, testthat, knitr, rmarkdown
Published: 2018-02-24
Author: JJ Allaire [aut, cre], Fran├žois Chollet [aut, cph], RStudio [ctb, cph, fnd], Google [ctb, cph, fnd], Yuan Tang [ctb, cph], Daniel Falbel [ctb, cph], Wouter Van Der Bijl [ctb, cph], Martin Studer [ctb, cph]
Maintainer: JJ Allaire <jj at>
License: MIT + file LICENSE
NeedsCompilation: no
SystemRequirements: Keras >= 2.0 (
Materials: NEWS
In views: HighPerformanceComputing, ModelDeployment
CRAN checks: keras results


Reference manual: keras.pdf
Vignettes: About Keras Layers
About Keras Models
Using Pre-Trained Models
Keras Backend
Writing Custom Keras Layers
Frequently Asked Questions
Guide to the Functional API
Getting Started with Keras
Guide to the Sequential Model
Training Callbacks
Training Visualization
Why Use Keras?
Package source: keras_2.1.4.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
OS X El Capitan binaries: r-release: keras_2.1.4.tgz
OS X Mavericks binaries: r-oldrel: keras_2.1.2.tgz
Old sources: keras archive

Reverse dependencies:

Reverse depends: kerasformula
Reverse suggests: lime, OSTSC, reinforcelearn, tensorflow, tfdatasets


Please use the canonical form to link to this page.