GlobalPooling

GlobalMaxPooling1D

GlobalAveragePooling1D

GlobalMaxPooling2D

GlobalAveragePooling2D

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.

Taylor Arnold

kerasR

R Interface to the Keras Deep Learning Library

Andrie de Vries

GlobalPooling function

<dl><dt>input_shape</dt>
<dd>nD tensor with shape: <code>(batch_size, ..., input_dim)</code>.
The most common situation would be a 2D
input with shape
<code>(batch_size, input_dim)</code>.</dd>
<dt>data_format</dt>
<dd>A string, one of channels_last (default)
or channels_first</dd></dl>

Arguments

Taylor B. Arnold, <a href="/link/taylor.arnold%40acm.org?package=kerasR&version=0.8.1" data-mini-rdoc="kerasR::taylor.arnold@acm.org">taylor.arnold@acm.org</a>

Author

Global pooling operations — GlobalPooling

<dl>

<dt>input_shape</dt>
<dd>nD tensor with shape: <code>(batch_size, ..., input_dim)</code>.
The most common situation would be a 2D
input with shape
<code>(batch_size, input_dim)</code>.</dd>


<dt>data_format</dt>
<dd>A string, one of channels_last (default)
or channels_first</dd>

</dl>

Taylor B. Arnold, <a href='mailto:taylor.arnold@acm.org'>taylor.arnold@acm.org</a>

GlobalPooling: Global pooling operations

Description

Usage

Arguments

Author

References