Class RnnLossLayer.Builder
- 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.BaseOutputLayer.Builder<RnnLossLayer.Builder>
-
- org.deeplearning4j.nn.conf.layers.RnnLossLayer.Builder
-
- Enclosing class:
- RnnLossLayer
public static class RnnLossLayer.Builder extends BaseOutputLayer.Builder<RnnLossLayer.Builder>
-
-
Field Summary
-
Fields inherited from class org.deeplearning4j.nn.conf.layers.BaseOutputLayer.Builder
lossFn
-
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 Description Builder()
Builder(ILossFunction lossFunction)
Builder(LossFunctions.LossFunction lossFunction)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description RnnLossLayer
build()
RnnLossLayer.Builder
dataFormat(RNNFormat rnnDataFormat)
RnnLossLayer.Builder
nIn(int nIn)
Number of inputs for the layer (usually the size of the last layer).RnnLossLayer.Builder
nOut(int nOut)
Number of outputs - used to set the layer size (number of units/nodes for the current layer).void
setNIn(long nIn)
void
setNOut(long nOut)
-
Methods inherited from class org.deeplearning4j.nn.conf.layers.BaseOutputLayer.Builder
hasBias, lossFunction, lossFunction
-
Methods inherited from class org.deeplearning4j.nn.conf.layers.FeedForwardLayer.Builder
nIn, 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
constrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, name
-
-
-
-
Constructor Detail
-
Builder
public Builder()
-
Builder
public Builder(LossFunctions.LossFunction lossFunction)
- Parameters:
lossFunction
- Loss function for the loss layer
-
Builder
public Builder(ILossFunction lossFunction)
- Parameters:
lossFunction
- Loss function for the loss layer
-
-
Method Detail
-
nIn
public RnnLossLayer.Builder nIn(int nIn)
Description copied from class:FeedForwardLayer.Builder
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.- Overrides:
nIn
in classFeedForwardLayer.Builder<RnnLossLayer.Builder>
- Parameters:
nIn
- Number of inputs for the layer
-
nOut
public RnnLossLayer.Builder nOut(int nOut)
Description copied from class:FeedForwardLayer.Builder
Number of outputs - used to set the layer size (number of units/nodes for the current layer). Note that this is equivalent toFeedForwardLayer.Builder.units(int)
- Overrides:
nOut
in classFeedForwardLayer.Builder<RnnLossLayer.Builder>
- Parameters:
nOut
- Number of outputs / layer size
-
setNIn
public void setNIn(long nIn)
-
setNOut
public void setNOut(long nOut)
-
dataFormat
public RnnLossLayer.Builder dataFormat(RNNFormat rnnDataFormat)
- Parameters:
rnnDataFormat
- Data format expected by the layer. NCW = [miniBatchSize, size, timeSeriesLength], NWC = [miniBatchSize, timeSeriesLength, size]. Defaults to NCW.
-
build
public RnnLossLayer build()
- Specified by:
build
in classLayer.Builder<RnnLossLayer.Builder>
-
-