org.deeplearning4j.nn.conf.layers.samediff

Class AbstractSameDiffLayer

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

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

All Implemented Interfaces:

Serializable, Cloneable, TrainingConfig

Direct Known Subclasses:

SameDiffLayer, SameDiffOutputLayer

public abstract class AbstractSameDiffLayer
extends Layer

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	AbstractSameDiffLayer.Builder<T extends AbstractSameDiffLayer.Builder<T>>

Field Summary

Fields

Modifier and Type	Field and Description
protected IUpdater	biasUpdater
protected GradientNormalization	gradientNormalization
protected double	gradientNormalizationThreshold
protected List<Regularization>	regularization
protected List<Regularization>	regularizationBias
protected IUpdater	updater

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

constraints, iDropout, layerName

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	AbstractSameDiffLayer()
protected	AbstractSameDiffLayer(AbstractSameDiffLayer.Builder builder)

Method Summary

Modifier and Type	Method and Description
void	applyGlobalConfig(NeuralNetConfiguration.Builder b)
void	applyGlobalConfigToLayer(NeuralNetConfiguration.Builder globalConfig)
abstract void	defineParameters(SDLayerParams params) Define the parameters for the network.
SDLayerParams	getLayerParams()
LayerMemoryReport	getMemoryReport(InputType inputType) This is a report of the estimated memory consumption for the given layer
InputPreProcessor	getPreProcessorForInputType(InputType inputType) For the given type of input to this layer, what preprocessor (if any) is required? Returns null if no preprocessor is required, otherwise returns an appropriate InputPreProcessor for this layer, such as a CnnToFeedForwardPreProcessor
List<Regularization>	getRegularizationByParam(String paramName) Get the regularization types (l1/l2/weight decay) for the given parameter.
IUpdater	getUpdaterByParam(String paramName) Get the updater for the given parameter.
abstract void	initializeParameters(Map<String,INDArray> params) Set the initial parameter values for this layer, if required
ParamInitializer	initializer()
protected void	initWeights(int fanIn, int fanOut, WeightInit weightInit, INDArray array)
abstract Layer	instantiate(NeuralNetConfiguration conf, Collection<TrainingListener> trainingListeners, int layerIndex, INDArray layerParamsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDataType)
boolean	isPretrainParam(String paramName) Is the specified parameter a layerwise pretraining only parameter? For example, visible bias params in an autoencoder (or, decoder params in a variational autoencoder) aren't used during supervised backprop. Layers (like DenseLayer, etc) with no pretrainable parameters will return false for all (valid) inputs.
INDArray	onesMaskForInput(INDArray input) This method generates an "all ones" mask array for use in the SameDiff model when none is provided.
char	paramReshapeOrder(String param) Returns the memory layout ('c' or 'f' order - i.e., row/column major) of the parameters.
void	setNIn(InputType inputType, boolean override) Set the nIn value (number of inputs, or input channels for CNNs) based on the given input type

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

clone, getOutputType, 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

Field Detail

regularization

protected List<Regularization> regularization

regularizationBias

protected List<Regularization> regularizationBias

updater

protected IUpdater updater

biasUpdater

protected IUpdater biasUpdater

gradientNormalization

protected GradientNormalization gradientNormalization

gradientNormalizationThreshold

protected double gradientNormalizationThreshold

Constructor Detail

AbstractSameDiffLayer

protected AbstractSameDiffLayer(AbstractSameDiffLayer.Builder builder)

AbstractSameDiffLayer

protected AbstractSameDiffLayer()

Method Detail

getRegularizationByParam

public List<Regularization> getRegularizationByParam(String paramName)

Description copied from class: Layer

Get the regularization types (l1/l2/weight decay) for the given parameter. Different parameters may have different regularization types.

Specified by:

getRegularizationByParam in interface TrainingConfig

Specified by:

getRegularizationByParam in class Layer

Parameters:

paramName - Parameter name ("W", "b" etc)

Returns:

Regularization types (if any) for the specified parameter

getLayerParams

public SDLayerParams getLayerParams()

setNIn

public void setNIn(InputType inputType,
                   boolean override)

Description copied from class: Layer

Set the nIn value (number of inputs, or input channels for CNNs) based on the given input type

Specified by:

setNIn in class Layer

Parameters:

inputType - Input type for this layer

override - If false: only set the nIn value if it's not already set. If true: set it regardless of whether it's already set or not.

getPreProcessorForInputType

public InputPreProcessor getPreProcessorForInputType(InputType inputType)

Description copied from class: Layer

For the given type of input to this layer, what preprocessor (if any) is required?
Returns null if no preprocessor is required, otherwise returns an appropriate InputPreProcessor for this layer, such as a CnnToFeedForwardPreProcessor

Specified by:

getPreProcessorForInputType in class Layer

Parameters:

inputType - InputType to this layer

Returns:

Null if no preprocessor is required, otherwise the type of preprocessor necessary for this layer/input combination

applyGlobalConfigToLayer

public void applyGlobalConfigToLayer(NeuralNetConfiguration.Builder globalConfig)

defineParameters

public abstract void defineParameters(SDLayerParams params)

Define the parameters for the network. Use SDLayerParams.addWeightParam(String, long...) and SDLayerParams.addBiasParam(String, long...)

Parameters:

params - Object used to set parameters for this layer

initializeParameters

public abstract void initializeParameters(Map<String,INDArray> params)

Set the initial parameter values for this layer, if required

Parameters:

params - Parameter arrays that may be initialized

instantiate

public abstract Layer instantiate(NeuralNetConfiguration conf,
                                  Collection<TrainingListener> trainingListeners,
                                  int layerIndex,
                                  INDArray layerParamsView,
                                  boolean initializeParams,
                                  org.nd4j.linalg.api.buffer.DataType networkDataType)

Specified by:

instantiate in class Layer

initializer

public ParamInitializer initializer()

Specified by:

initializer in class Layer

Returns:

The parameter initializer for this model

getUpdaterByParam

public IUpdater getUpdaterByParam(String paramName)

Description copied from class: Layer

Get the updater for the given parameter. Typically the same updater will be used for all updaters, but this is not necessarily the case

Specified by:

getUpdaterByParam in interface TrainingConfig

Overrides:

getUpdaterByParam in class Layer

Parameters:

paramName - Parameter name

Returns:

IUpdater for the parameter

isPretrainParam

public boolean isPretrainParam(String paramName)

Description copied from class: Layer

Is the specified parameter a layerwise pretraining only parameter?
For example, visible bias params in an autoencoder (or, decoder params in a variational autoencoder) aren't used during supervised backprop.
Layers (like DenseLayer, etc) with no pretrainable parameters will return false for all (valid) inputs.

Specified by:

isPretrainParam in interface TrainingConfig

Specified by:

isPretrainParam in class Layer

Parameters:

paramName - Parameter name/key

Returns:

True if the parameter is for layerwise pretraining only, false otherwise

getMemoryReport

public LayerMemoryReport getMemoryReport(InputType inputType)

Description copied from class: Layer

This is a report of the estimated memory consumption for the given layer

Specified by:

getMemoryReport in class Layer

Parameters:

inputType - Input type to the layer. Memory consumption is often a function of the input type

Returns:

Memory report for the layer

paramReshapeOrder

public char paramReshapeOrder(String param)

Returns the memory layout ('c' or 'f' order - i.e., row/column major) of the parameters. In most cases, this can/should be left

Parameters:

param - Name of the parameter

Returns:

Memory layout ('c' or 'f') of the parameter

initWeights

protected void initWeights(int fanIn,
                           int fanOut,
                           WeightInit weightInit,
                           INDArray array)

applyGlobalConfig

public void applyGlobalConfig(NeuralNetConfiguration.Builder b)

onesMaskForInput

public INDArray onesMaskForInput(INDArray input)

This method generates an "all ones" mask array for use in the SameDiff model when none is provided.

Parameters:

input - Input to the layer

Returns:

A mask array - should be same datatype as the input (usually)