org.deeplearning4j.nn.conf.layers

Class BaseRecurrentLayer.Builder<T extends BaseRecurrentLayer.Builder<T>>

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer.Builder<T>

org.deeplearning4j.nn.conf.layers.BaseLayer.Builder<T>

org.deeplearning4j.nn.conf.layers.FeedForwardLayer.Builder<T>

org.deeplearning4j.nn.conf.layers.BaseRecurrentLayer.Builder<T>

Direct Known Subclasses:

AbstractLSTM.Builder, GravesBidirectionalLSTM.Builder, SimpleRnn.Builder

Enclosing class:

BaseRecurrentLayer

public abstract static class BaseRecurrentLayer.Builder<T extends BaseRecurrentLayer.Builder<T>>
extends FeedForwardLayer.Builder<T>

Field Summary

Fields

Modifier and Type	Field and Description
protected List<LayerConstraint>	inputWeightConstraints Set constraints to be applied to the RNN input weight parameters of this layer.
protected List<LayerConstraint>	recurrentConstraints Set constraints to be applied to the RNN recurrent weight parameters of this layer.
protected RNNFormat	rnnDataFormat Set the format of data expected by the RNN.
protected IWeightInit	weightInitFnRecurrent Set the weight initialization for the recurrent weights.

Fields inherited from class org.deeplearning4j.nn.conf.layers.FeedForwardLayer.Builder

nIn, nOut

Fields inherited from class org.deeplearning4j.nn.conf.layers.BaseLayer.Builder

activationFn, biasInit, biasUpdater, gainInit, gradientNormalization, gradientNormalizationThreshold, iupdater, regularization, regularizationBias, weightInitFn, weightNoise

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

allParamConstraints, biasConstraints, iDropout, layerName, weightConstraints

Constructor Summary

Constructors

Constructor and Description
Builder()

Method Summary

Modifier and Type	Method and Description
T	constrainInputWeights(LayerConstraint... constraints) Set constraints to be applied to the RNN input weight parameters of this layer.
T	constrainRecurrent(LayerConstraint... constraints) Set constraints to be applied to the RNN recurrent weight parameters of this layer.
T	dataFormat(RNNFormat rnnDataFormat)
T	weightInitRecurrent(Distribution dist) Set the weight initialization for the recurrent weights, based on the specified distribution.
T	weightInitRecurrent(IWeightInit weightInit) Set the weight initialization for the recurrent weights.
T	weightInitRecurrent(WeightInit weightInit) Set the weight initialization for the recurrent weights.

Methods inherited from class org.deeplearning4j.nn.conf.layers.FeedForwardLayer.Builder

nIn, nIn, nOut, nOut, units

Methods inherited from class org.deeplearning4j.nn.conf.layers.BaseLayer.Builder

activation, activation, biasInit, biasUpdater, dist, gainInit, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, regularization, regularizationBias, updater, updater, weightDecay, weightDecay, weightDecayBias, weightDecayBias, weightInit, weightInit, weightInit, weightNoise

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

build, constrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, name

Methods inherited from class java.lang.Object

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

Field Detail

rnnDataFormat

protected RNNFormat rnnDataFormat

Set the format of data expected by the RNN. NCW = [miniBatchSize, size, timeSeriesLength], NWC = [miniBatchSize, timeSeriesLength, size]. Defaults to NCW.

recurrentConstraints

protected List<LayerConstraint> recurrentConstraints

Set constraints to be applied to the RNN recurrent weight parameters of this layer. Default: no constraints.
Constraints can be used to enforce certain conditions (non-negativity of parameters, max-norm regularization, etc). These constraints are applied at each iteration, after the parameters have been updated.

inputWeightConstraints

protected List<LayerConstraint> inputWeightConstraints

Set constraints to be applied to the RNN input weight parameters of this layer. Default: no constraints.
Constraints can be used to enforce certain conditions (non-negativity of parameters, max-norm regularization, etc). These constraints are applied at each iteration, after the parameters have been updated.

weightInitFnRecurrent

protected IWeightInit weightInitFnRecurrent

Set the weight initialization for the recurrent weights. Not that if this is not set explicitly, the same weight initialization as the layer input weights is also used for the recurrent weights.

Constructor Detail

Builder

public Builder()

Method Detail

constrainRecurrent

public T constrainRecurrent(LayerConstraint... constraints)

Set constraints to be applied to the RNN recurrent weight parameters of this layer. Default: no constraints.
Constraints can be used to enforce certain conditions (non-negativity of parameters, max-norm regularization, etc). These constraints are applied at each iteration, after the parameters have been updated.

Parameters:

constraints - Constraints to apply to the recurrent weight parameters of this layer

constrainInputWeights

public T constrainInputWeights(LayerConstraint... constraints)

Set constraints to be applied to the RNN input weight parameters of this layer. Default: no constraints.
Constraints can be used to enforce certain conditions (non-negativity of parameters, max-norm regularization, etc). These constraints are applied at each iteration, after the parameters have been updated.

Parameters:

constraints - Constraints to apply to the input weight parameters of this layer

weightInitRecurrent

public T weightInitRecurrent(IWeightInit weightInit)

Set the weight initialization for the recurrent weights. Not that if this is not set explicitly, the same weight initialization as the layer input weights is also used for the recurrent weights.

Parameters:

weightInit - Weight initialization for the recurrent weights only.

weightInitRecurrent

public T weightInitRecurrent(WeightInit weightInit)

Set the weight initialization for the recurrent weights. Not that if this is not set explicitly, the same weight initialization as the layer input weights is also used for the recurrent weights.

Parameters:

weightInit - Weight initialization for the recurrent weights only.

weightInitRecurrent

public T weightInitRecurrent(Distribution dist)

Set the weight initialization for the recurrent weights, based on the specified distribution. Not that if this is not set explicitly, the same weight initialization as the layer input weights is also used for the recurrent weights.

Parameters:

dist - Distribution to use for initializing the recurrent weights

dataFormat

public T dataFormat(RNNFormat rnnDataFormat)