org.deeplearning4j.nn.conf.layers.samediff

Class SameDiffLayer

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

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

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

All Implemented Interfaces:

Serializable, Cloneable, TrainingConfig

Direct Known Subclasses:

LocallyConnected1D, LocallyConnected2D, SameDiffLambdaLayer

public abstract class SameDiffLayer
extends AbstractSameDiffLayer

A base layer used for implementing Deeplearning4j layers using SameDiff. These layers are not scoring/output layers: that is, they should be used as the intermediate layer in a network only.
To implement an output layer, extend SameDiffOutputLayer instead.
Note also that if multiple inputs are required, it is possible to implement a vertex instead: SameDiffVertex

To implement a Deeplearning layer using SameDiff, extend this class.
There are 4 required methods:
- defineLayer: Defines the forward pass for the layer
- defineParameters: Define the layer's parameters in a way suitable for DL4J
- initializeParameters: if required, set the initial parameter values for the layer
- getOutputType: determine the type of output/activations for the layer (without actually executing the layer's forward pass)

Furthermore, there are 3 optional methods:
- setNIn(InputType inputType, boolean override): if implemented, set the number of inputs to the layer during network initialization
- getPreProcessorForInputType: return the preprocessor that should be added (if any), for the given input type
- applyGlobalConfigToLayer: apply any global configuration options (weight init, activation functions etc) to the layer's configuration.

Author:

Alex Black

See Also:

Serialized Form

Nested Class Summary

Nested Classes

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

Field Summary

Fields

Modifier and Type	Field and Description
protected WeightInit	weightInit

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

biasUpdater, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, updater

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

constraints, iDropout, layerName

Constructor Summary

Constructors

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

Method Summary

Modifier and Type	Method and Description
abstract SDVariable	defineLayer(SameDiff sameDiff, SDVariable layerInput, Map<String,SDVariable> paramTable) Define the layer
Layer	instantiate(NeuralNetConfiguration conf, Collection<TrainingListener> trainingListeners, int layerIndex, INDArray layerParamsView, boolean initializeParams)

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

applyGlobalConfig, applyGlobalConfigToLayer, defineParameters, getL1ByParam, getL2ByParam, getLayerParams, getMemoryReport, getPreProcessorForInputType, getUpdaterByParam, initializeParameters, initializer, initWeights, isPretrain, isPretrainParam, paramReshapeOrder, setNIn

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

clone, getOutputType, initializeConstraints, resetLayerDefaultConfig, setPretrain

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

weightInit

protected WeightInit weightInit

Constructor Detail

SameDiffLayer

protected SameDiffLayer(SameDiffLayer.Builder builder)

SameDiffLayer

protected SameDiffLayer()

Method Detail

defineLayer

public abstract SDVariable defineLayer(SameDiff sameDiff,
                                       SDVariable layerInput,
                                       Map<String,SDVariable> paramTable)

Define the layer

Parameters:

sameDiff - SameDiff instance

layerInput - Input to the layer

paramTable - Parameter table - keys as defined by AbstractSameDiffLayer.defineParameters(SDLayerParams)

Returns:

The final layer variable corresponding to the activations/output from the forward pass

instantiate

public Layer instantiate(NeuralNetConfiguration conf,
                         Collection<TrainingListener> trainingListeners,
                         int layerIndex,
                         INDArray layerParamsView,
                         boolean initializeParams)

Specified by:

instantiate in class AbstractSameDiffLayer