KerasLayer

Custom R6 layers can now inherit directly from <code>keras$layers$Layer</code> or other layers.

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

KerasLayer function

Format

<dl>
<dt><code>build(input_shape)</code></dt>
<dd>Creates the
layer weights (must be implemented by all layers that have weights)</dd><dt><code>call(inputs,mask)</code></dt>
<dd>Call the layer on an input tensor.</dd><dt><code>compute_output_shape(input_shape)</code></dt>
<dd>Compute the output shape
for the layer.</dd><dt><code>add_loss(losses, inputs)</code></dt>
<dd>Add losses to the layer.</dd><dt><code>add_weight(name,shape,dtype,initializer,regularizer,trainable,constraint)</code></dt>
<dd>Adds
a weight variable to the layer.</dd>
 
</dl>

Methods

(Deprecated) Base R6 class for Keras layers — KerasLayer

<dl>
<dt><code>build(input_shape)</code></dt>
<dd>Creates the
layer weights (must be implemented by all layers that have weights)</dd>

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

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

<dt><code>add_loss(losses, inputs)</code></dt>
<dd>Add losses to the layer.</dd>

<dt><code>add_weight(name,shape,dtype,initializer,regularizer,trainable,constraint)</code></dt>
<dd>Adds
a weight variable to the layer.</dd>
 
</dl>

(Deprecated) Base R6 class for Keras layers

KerasLayer: (Deprecated) Base R6 class for Keras layers

Description

Arguments

Value

Format

Methods