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.


kerasR 0.6.1 (2017-06-01)

This version adding a testing suite for of the core functions in the library and conforming with the goodpractice::gp() recommendations. Also adds hooks to TravisCL and AppVeyor for integrated testing.

kerasR 0.5.0 (2017-04-26)

Adding the following functions to make it easier to initalize and check that keras is properly installed; these also make it possible to restart the python engine if needed.

  • keras_available()
  • keras_init()

kerasR 0.4.1 (2017-03-20)

This is the inital working version that was publicly pushed to GitHub. Older versions only ran locally on the development machine. Currently all of the layers in the keras library other than the functional layers are wrapped and exported.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.6.1 by Taylor Arnold, 10 months ago


Report a bug at http://github.com/statsmaths/kerasR/issues

Browse source code at https://github.com/cran/kerasR

Authors: Taylor Arnold [aut, cre]

Documentation:   PDF Manual  

LGPL-2 license

Imports reticulate

Suggests knitr, rmarkdown, testthat, covr

System requirements: Python (>= 2.7); keras <https://keras.io/> (>= 2.0.1)

See at CRAN