keras: R Interface to 'Keras'

Interface to 'Keras', a high-level neural networks API which runs on top of 'TensorFlow'. '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: 2.0.5
Imports: reticulate (≥ 1.0), tensorflow (≥ 1.3), tfruns, magrittr, methods, R6
Suggests: ggplot2, testthat, knitr, rmarkdown
Published: 2017-07-30
Author: JJ Allaire [aut, cre], Fran├žois Chollet [aut, cph], RStudio [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: TensorFlow >= 1.1 (
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
Guide to the Sequential Model
Guide to the Functional API
Guide to the Sequential Model
TensorBoard Visualization
Training Callbacks
Package source: keras_2.0.5.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
OS X El Capitan binaries: r-release: keras_2.0.5.tgz
OS X Mavericks binaries: r-oldrel: keras_2.0.5.tgz


Please use the canonical form to link to this page.