KerasWrapper

Instead of inheriting from the proxy class <code>KerasWrapper</code> and using
<code>create_wrapper</code> to create instances, new R6 custom classes are encouraged to
inherit directly from <code>keras$layers$Wrapper</code> and use <code>create_layer</code> to create
instances.

internal

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

KerasWrapper function

Format

<dl>
<dt><code>build(input_shape)</code></dt>
<dd>Builds the wrapped layer.
Subclasses can extend this to perform custom operations on that layer.</dd><dt><code>call(inputs,mask)</code></dt>
<dd>Calls the wrapped layer on an input tensor.</dd><dt><code>compute_output_shape(input_shape)</code></dt>
<dd>Computes the output shape
for the wrapped layer.</dd><dt><code>add_loss(losses, inputs)</code></dt>
<dd>Subclasses can use this to add losses to the wrapped layer.</dd><dt><code>add_weight(name,shape,dtype,initializer,regularizer,trainable,constraint)</code></dt>
<dd>Subclasses can use this to add weights to the wrapped layer.</dd>
 
</dl>

Methods

(Deprecated) Base R6 class for Keras wrappers — KerasWrapper

<dl>
<dt><code>build(input_shape)</code></dt>
<dd>Builds the wrapped layer.
Subclasses can extend this to perform custom operations on that layer.</dd>

<dt><code>call(inputs,mask)</code></dt>
<dd>Calls the wrapped layer on an input tensor.</dd>

<dt><code>compute_output_shape(input_shape)</code></dt>
<dd>Computes the output shape
for the wrapped layer.</dd>

<dt><code>add_loss(losses, inputs)</code></dt>
<dd>Subclasses can use this to add losses to the wrapped layer.</dd>

<dt><code>add_weight(name,shape,dtype,initializer,regularizer,trainable,constraint)</code></dt>
<dd>Subclasses can use this to add weights to the wrapped layer.</dd>
 
</dl>

(Deprecated) Base R6 class for Keras wrappers

KerasWrapper: (Deprecated) Base R6 class for Keras wrappers

Description

Arguments

Value

Format

Methods