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 acm.org>
BugReports: http://github.com/statsmaths/kerasR/issues
License: LGPL-2
URL: https://github.com/statsmaths/kerasR
NeedsCompilation: no
SystemRequirements: Python (>= 2.7); keras <https://keras.io/> (>= 2.0.1)
Materials: NEWS
CRAN checks: kerasR results

Downloads:

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: kerasR_0.6.1.zip, r-devel-gcc8: kerasR_0.6.1.zip, r-release: kerasR_0.6.1.zip, r-oldrel: kerasR_0.6.1.zip
OS X binaries: r-release: kerasR_0.6.1.tgz, r-oldrel: kerasR_0.6.1.tgz
Old sources: kerasR archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=kerasR to link to this page.