org.deeplearning4j.nn.conf.layers

Class CapsuleStrengthLayer

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

org.deeplearning4j.nn.conf.layers.samediff.AbstractSameDiffLayer

org.deeplearning4j.nn.conf.layers.samediff.SameDiffLayer

org.deeplearning4j.nn.conf.layers.samediff.SameDiffLambdaLayer

org.deeplearning4j.nn.conf.layers.CapsuleStrengthLayer

All Implemented Interfaces:

Serializable, Cloneable, TrainingConfig

public class CapsuleStrengthLayer
extends SameDiffLambdaLayer

An layer to get the "strength" of each capsule, that is, the probability of it being in the input. This is the vector length or L2 norm of each capsule's output. The lengths will not exceed one because of the squash function. Input should come from a Capsule Layer and be of shape [mb, capsules, capsuleDims] CapsNet is from Dynamic Routing Between Capsules

Author:

Ryan Nett

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	CapsuleStrengthLayer.Builder

Field Summary

Fields inherited from class org.deeplearning4j.nn.conf.layers.samediff.SameDiffLayer

weightInit

Fields inherited from class org.deeplearning4j.nn.conf.layers.samediff.AbstractSameDiffLayer

biasUpdater, gradientNormalization, gradientNormalizationThreshold, regularization, regularizationBias, updater

Fields inherited from class org.deeplearning4j.nn.conf.layers.Layer

constraints, iDropout, layerName

Constructor Summary

Constructors

Constructor and Description
CapsuleStrengthLayer(CapsuleStrengthLayer.Builder builder)

Method Summary

Modifier and Type	Method and Description
SDVariable	defineLayer(SameDiff SD, SDVariable layerInput) The defineLayer method is used to define the foward pass for the layer
InputType	getOutputType(int layerIndex, InputType inputType) For a given type of input to this layer, what is the type of the output?

Methods inherited from class org.deeplearning4j.nn.conf.layers.samediff.SameDiffLambdaLayer

defineLayer, defineParameters, initializeParameters

Methods inherited from class org.deeplearning4j.nn.conf.layers.samediff.SameDiffLayer

feedForwardMaskArray, instantiate, validateInput

Methods inherited from class org.deeplearning4j.nn.conf.layers.samediff.AbstractSameDiffLayer

applyGlobalConfig, applyGlobalConfigToLayer, getLayerParams, getMemoryReport, getPreProcessorForInputType, getRegularizationByParam, getUpdaterByParam, initializer, initWeights, isPretrainParam, onesMaskForInput, paramReshapeOrder, setNIn

Methods inherited from class org.deeplearning4j.nn.conf.layers.Layer

clone, initializeConstraints, resetLayerDefaultConfig, setDataType

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface org.deeplearning4j.nn.api.TrainingConfig

getGradientNormalization, getGradientNormalizationThreshold, getLayerName

Constructor Detail

CapsuleStrengthLayer

public CapsuleStrengthLayer(CapsuleStrengthLayer.Builder builder)

Method Detail

defineLayer

public SDVariable defineLayer(SameDiff SD,
                              SDVariable layerInput)

Description copied from class: SameDiffLambdaLayer

The defineLayer method is used to define the foward pass for the layer

Specified by:

defineLayer in class SameDiffLambdaLayer

Parameters:

SD - SameDiff instance to use to define the vertex

layerInput - Layer input variable

Returns:

The output variable (orresponding to the output activations for the layer)

getOutputType

public InputType getOutputType(int layerIndex,
                               InputType inputType)

Description copied from class: Layer

For a given type of input to this layer, what is the type of the output?

Overrides:

getOutputType in class SameDiffLambdaLayer

Parameters:

layerIndex - Index of the layer

inputType - Type of input for the layer

Returns:

Type of output from the layer