keras_array

Convert an R vector, matrix, or array object to an array that has the optimal
in-memory layout and floating point data type for the current Keras backend.

Interface to 'Keras' <https://keras.io>, 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.

Tomasz Kalinowski

keras

R Interface to 'Keras'

Daniel Falbel

JJ Allaire

François Chollet

RStudio 

Google 

Yuan Tang

Wouter Van Der Bijl

Martin Studer

Sigrid Keydana

keras_array function

<dl><dt>x</dt>
<dd>Object or list of objects to convert</dd>
<dt>dtype</dt>
<dd>NumPy data type (e.g. float32, float64). If this is unspecified
then R doubles will be converted to the default floating point type for the
current Keras backend.</dd></dl>

Arguments

Keras array object — keras_array

<dl>

<dt>x</dt>
<dd>Object or list of objects to convert</dd>


<dt>dtype</dt>
<dd>NumPy data type (e.g. float32, float64). If this is unspecified
then R doubles will be converted to the default floating point type for the
current Keras backend.</dd>

</dl>

Keras array object

keras_array: Keras array object

Description

Usage

Value

Arguments

Details