Package org.deeplearning4j.nn.conf.layers

Class FeedForwardLayer.Builder<T extends FeedForwardLayer.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>

Direct Known Subclasses:

BaseOutputLayer.Builder, BasePretrainNetwork.Builder, BaseRecurrentLayer.Builder, BatchNormalization.Builder, ConvolutionLayer.BaseConvBuilder, DenseLayer.Builder, DropoutLayer.Builder, ElementWiseMultiplicationLayer.Builder, EmbeddingLayer.Builder, EmbeddingSequenceLayer.Builder, PReLULayer.Builder, RepeatVector.Builder

Enclosing class:

FeedForwardLayer

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

Field Summary

Fields

Modifier and Type	Field	Description
protected long	nIn	Number of inputs for the layer (usually the size of the last layer).
protected long	nOut	Number of inputs for the layer (usually the size of the last layer).

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	Description
Builder()

Method Summary

Modifier and Type	Method	Description
T	nIn(int nIn)	Number of inputs for the layer (usually the size of the last layer).
T	nIn(long nIn)	Number of inputs for the layer (usually the size of the last layer).
T	nOut(int nOut)	Number of outputs - used to set the layer size (number of units/nodes for the current layer).
T	nOut(long nOut)	Number of outputs - used to set the layer size (number of units/nodes for the current layer).
T	units(int units)	Set the number of units / layer size for this layer. This is equivalent to nOut(int)

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

nIn

protected long nIn

Number of inputs for the layer (usually the size of the last layer).
Note that for Convolutional layers, this is the input channels, otherwise is the previous layer size.

nOut

protected long nOut

Number of inputs for the layer (usually the size of the last layer).
Note that for Convolutional layers, this is the input channels, otherwise is the previous layer size.

Constructor Detail

Builder

public Builder()

Method Detail

nIn

public T nIn(int nIn)

Number of inputs for the layer (usually the size of the last layer).
Note that for Convolutional layers, this is the input channels, otherwise is the previous layer size.

Parameters:

nIn - Number of inputs for the layer

nIn

public T nIn(long nIn)

Number of inputs for the layer (usually the size of the last layer).
Note that for Convolutional layers, this is the input channels, otherwise is the previous layer size.

Parameters:

nIn - Number of inputs for the layer

nOut

public T nOut(int nOut)

Number of outputs - used to set the layer size (number of units/nodes for the current layer). Note that this is equivalent to units(int)

Parameters:

nOut - Number of outputs / layer size

nOut

public T nOut(long nOut)

Number of outputs - used to set the layer size (number of units/nodes for the current layer). Note that this is equivalent to units(int)

Parameters:

nOut - Number of outputs / layer size

units

public T units(int units)

Set the number of units / layer size for this layer.
This is equivalent to nOut(int)

Parameters:

units - Size of the layer (number of units) / nOut

See Also:

nOut(int)