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
All Methods Instance Methods Concrete Methods 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 tonOut(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
-
-
-
-
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.
-
-
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 tounits(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 tounits(int)
- Parameters:
nOut
- Number of outputs / layer size
-
-