kerasR: R Interface to the Keras Deep Learning Library

Provides a consistent interface to the 'Keras' Deep Learning Library directly from within R. 'Keras' provides specifications for describing dense neural networks, convolution neural networks (CNN) and recurrent neural networks (RNN) running on top of either 'TensorFlow' or 'Theano'. Type conversions between Python and R are automatically handled correctly, even when the default choices would otherwise lead to errors. Includes complete R documentation and many working examples.

Version: 0.6.1
Depends: R (≥ 2.10)
Imports: reticulate (≥ 0.7)
Suggests: knitr, rmarkdown, testthat, covr
Published: 2017-06-01
Author: Taylor Arnold [aut, cre]
Maintainer: Taylor Arnold <taylor.arnold at>
License: LGPL-2
NeedsCompilation: no
SystemRequirements: Python (>= 2.7); keras <> (>= 2.0.1)
Materials: NEWS
CRAN checks: kerasR results


Reference manual: kerasR.pdf
Vignettes: R Interface to the Keras Deep Learning Library
Package source: kerasR_0.6.1.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
OS X El Capitan binaries: r-release: kerasR_0.6.1.tgz
OS X Mavericks binaries: r-oldrel: kerasR_0.6.1.tgz
Old sources: kerasR archive


Please use the canonical form to link to this page.