Uses of Class
org.deeplearning4j.berkeley.Pair

Packages that use Pair

Package	Description
org.deeplearning4j.berkeley
org.deeplearning4j.datasets.iterator
org.deeplearning4j.eval
org.deeplearning4j.nn.api
org.deeplearning4j.nn.api.layers
org.deeplearning4j.nn.conf
org.deeplearning4j.nn.conf.preprocessor
org.deeplearning4j.nn.graph
org.deeplearning4j.nn.graph.vertex
org.deeplearning4j.nn.graph.vertex.impl
org.deeplearning4j.nn.graph.vertex.impl.rnn
org.deeplearning4j.nn.layers
org.deeplearning4j.nn.layers.convolution
org.deeplearning4j.nn.layers.convolution.subsampling
org.deeplearning4j.nn.layers.feedforward.autoencoder
org.deeplearning4j.nn.layers.feedforward.embedding
org.deeplearning4j.nn.layers.feedforward.rbm
org.deeplearning4j.nn.layers.normalization
org.deeplearning4j.nn.layers.pooling
org.deeplearning4j.nn.layers.recurrent
org.deeplearning4j.nn.layers.training
org.deeplearning4j.nn.layers.variational
org.deeplearning4j.nn.multilayer
org.deeplearning4j.optimize.api
org.deeplearning4j.optimize.listeners
org.deeplearning4j.optimize.solvers
org.deeplearning4j.util

Uses of Pair in org.deeplearning4j.berkeley

Methods in org.deeplearning4j.berkeley that return Pair

Modifier and Type	Method and Description
Pair<K,V>	CounterMap.argMax() Finds the key with maximum count.
static <S,T> Pair<S,T>	Pair.makePair(S first, T second)
static <S,T> Pair<S,T>	Pair.newPair(S first, T second)
Pair<S,F>	Pair.reverse()

Methods in org.deeplearning4j.berkeley that return types with arguments of type Pair

Modifier and Type	Method and Description
Iterator<Pair<K,V>>	CounterMap.getPairIterator()
static <S,T> Iterator<Pair<S,T>>	Iterators.zip(Iterator<S> s, Iterator<T> t)

Methods in org.deeplearning4j.berkeley with parameters of type Pair

Modifier and Type	Method and Description
int	Pair.LexicographicPairComparator.compare(Pair<F,S> pair1, Pair<F,S> pair2)
int	Pair.LexicographicPairComparator.compare(Pair<F,S> pair1, Pair<F,S> pair2)
int	Pair.DefaultLexicographicPairComparator.compare(Pair<F,S> o1, Pair<F,S> o2)
int	Pair.DefaultLexicographicPairComparator.compare(Pair<F,S> o1, Pair<F,S> o2)
int	Pair.FirstComparator.compare(Pair<S,T> p1, Pair<S,T> p2)
int	Pair.FirstComparator.compare(Pair<S,T> p1, Pair<S,T> p2)
int	Pair.ReverseFirstComparator.compare(Pair<S,T> p1, Pair<S,T> p2)
int	Pair.ReverseFirstComparator.compare(Pair<S,T> p1, Pair<S,T> p2)
int	Pair.SecondComparator.compare(Pair<S,T> p1, Pair<S,T> p2)
int	Pair.SecondComparator.compare(Pair<S,T> p1, Pair<S,T> p2)
int	Pair.ReverseSecondComparator.compare(Pair<S,T> p1, Pair<S,T> p2)
int	Pair.ReverseSecondComparator.compare(Pair<S,T> p1, Pair<S,T> p2)
int	Pair.compareTo(Pair<F,S> o) Compares this object with the specified object for order.

Uses of Pair in org.deeplearning4j.datasets.iterator

Constructor parameters in org.deeplearning4j.datasets.iterator with type arguments of type Pair

Constructor and Description
AbstractDataSetIterator(Iterable<Pair<T,T>> iterable, int batchSize)
DoublesDataSetIterator(Iterable<Pair<double[],double[]>> iterable, int batchSize)
FloatsDataSetIterator(Iterable<Pair<float[],float[]>> iterable, int batchSize)
INDArrayDataSetIterator(Iterable<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> iterable, int batchSize)

Uses of Pair in org.deeplearning4j.eval

Fields in org.deeplearning4j.eval with type parameters of type Pair

Modifier and Type	Field and Description
protected Map<Pair<Integer,Integer>,List<Object>>	Evaluation.confusionMatrixMetaData

Methods in org.deeplearning4j.eval that return Pair

Modifier and Type	Method and Description
static Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	EvaluationUtils.extractNonMaskedTimeSteps(org.nd4j.linalg.api.ndarray.INDArray labels, org.nd4j.linalg.api.ndarray.INDArray predicted, org.nd4j.linalg.api.ndarray.INDArray outputMask)

Uses of Pair in org.deeplearning4j.nn.api

Methods in org.deeplearning4j.nn.api that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	Layer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon) Calculate the gradient relative to the error in the next layer
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	Layer.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize) Feed forward the input mask array, setting in in the layer as appropriate.
Pair<Gradient,Double>	Model.gradientAndScore() Get the gradient and score

Uses of Pair in org.deeplearning4j.nn.api.layers

Methods in org.deeplearning4j.nn.api.layers that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	RecurrentLayer.tbpttBackpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon, int tbpttBackLength) Truncated BPTT equivalent of Layer.backpropGradient().

Uses of Pair in org.deeplearning4j.nn.conf

Methods in org.deeplearning4j.nn.conf that return Pair

Modifier and Type	Method and Description
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	InputPreProcessor.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)

Uses of Pair in org.deeplearning4j.nn.conf.preprocessor

Methods in org.deeplearning4j.nn.conf.preprocessor that return Pair

Modifier and Type	Method and Description
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	ComposableInputPreProcessor.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	BaseInputPreProcessor.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	FeedForwardToRnnPreProcessor.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	RnnToFeedForwardPreProcessor.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	CnnToFeedForwardPreProcessor.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	FeedForwardToCnnPreProcessor.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	RnnToCnnPreProcessor.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	CnnToRnnPreProcessor.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)

Uses of Pair in org.deeplearning4j.nn.graph

Methods in org.deeplearning4j.nn.graph that return Pair

Modifier and Type	Method and Description
Pair<Gradient,Double>	ComputationGraph.gradientAndScore()

Uses of Pair in org.deeplearning4j.nn.graph.vertex

Methods in org.deeplearning4j.nn.graph.vertex that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	GraphVertex.doBackward(boolean tbptt) Do backward pass
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	GraphVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)

Uses of Pair in org.deeplearning4j.nn.graph.vertex.impl

Methods in org.deeplearning4j.nn.graph.vertex.impl that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	ScaleVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	PreprocessorVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	PoolHelperVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	LayerVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	MergeVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	InputVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	L2NormalizeVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	SubsetVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	ShiftVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	ElementWiseVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	UnstackVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	StackVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	L2Vertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	ReshapeVertex.doBackward(boolean tbptt)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	ScaleVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	PreprocessorVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	PoolHelperVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	LayerVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	MergeVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	InputVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	L2NormalizeVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	SubsetVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	ShiftVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	ElementWiseVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	UnstackVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	StackVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	L2Vertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	ReshapeVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)

Uses of Pair in org.deeplearning4j.nn.graph.vertex.impl.rnn

Methods in org.deeplearning4j.nn.graph.vertex.impl.rnn that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	DuplicateToTimeSeriesVertex.doBackward(boolean tbptt)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	LastTimeStepVertex.doBackward(boolean tbptt)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	DuplicateToTimeSeriesVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	LastTimeStepVertex.feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)

Uses of Pair in org.deeplearning4j.nn.layers

Methods in org.deeplearning4j.nn.layers that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	BasePretrainNetwork.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	BaseOutputLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	FrozenLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	ActivationLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	DropoutLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	LossLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	BaseLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	FrozenLayer.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	AbstractLayer.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<Gradient,Double>	BaseOutputLayer.gradientAndScore()
Pair<Gradient,Double>	FrozenLayer.gradientAndScore()
Pair<Gradient,Double>	AbstractLayer.gradientAndScore()
Pair<Gradient,Double>	LossLayer.gradientAndScore()
abstract Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	BasePretrainNetwork.sampleHiddenGivenVisible(org.nd4j.linalg.api.ndarray.INDArray v) Sample the hidden distribution given the visible
abstract Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	BasePretrainNetwork.sampleVisibleGivenHidden(org.nd4j.linalg.api.ndarray.INDArray h) Sample the visible distribution given the hidden

Uses of Pair in org.deeplearning4j.nn.layers.convolution

Methods in org.deeplearning4j.nn.layers.convolution that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	ConvolutionLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	Convolution1DLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	ZeroPaddingLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	ConvolutionHelper.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray weights, org.nd4j.linalg.api.ndarray.INDArray delta, int[] kernel, int[] strides, int[] pad, org.nd4j.linalg.api.ndarray.INDArray biasGradView, org.nd4j.linalg.api.ndarray.INDArray weightGradView, org.nd4j.linalg.activations.IActivation afn, ConvolutionLayer.AlgoMode mode, ConvolutionLayer.BwdFilterAlgo bwdFilterAlgo, ConvolutionLayer.BwdDataAlgo bwdDataAlgo, ConvolutionMode convolutionMode)
protected Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	ConvolutionLayer.preOutput(boolean training, boolean forBackprop) PreOutput method that also returns the im2col2d array (if being called for backprop), as this can be re-used instead of being calculated again.
protected Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	ConvolutionLayer.preOutput4d(boolean training, boolean forBackprop) preOutput4d: Used so that ConvolutionLayer subclasses (such as Convolution1DLayer) can maintain their standard non-4d preOutput method, while overriding this to return 4d activations (for use in backprop) without modifying the public API
protected Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	Convolution1DLayer.preOutput4d(boolean training, boolean forBackprop)

Uses of Pair in org.deeplearning4j.nn.layers.convolution.subsampling

Methods in org.deeplearning4j.nn.layers.convolution.subsampling that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	SubsamplingLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	Subsampling1DLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	SubsamplingHelper.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray epsilon, int[] kernel, int[] strides, int[] pad, PoolingType poolingType, ConvolutionMode convolutionMode)

Uses of Pair in org.deeplearning4j.nn.layers.feedforward.autoencoder

Methods in org.deeplearning4j.nn.layers.feedforward.autoencoder that return Pair

Modifier and Type	Method and Description
Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	AutoEncoder.sampleHiddenGivenVisible(org.nd4j.linalg.api.ndarray.INDArray v)
Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	AutoEncoder.sampleVisibleGivenHidden(org.nd4j.linalg.api.ndarray.INDArray h)

Uses of Pair in org.deeplearning4j.nn.layers.feedforward.embedding

Methods in org.deeplearning4j.nn.layers.feedforward.embedding that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	EmbeddingLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)

Uses of Pair in org.deeplearning4j.nn.layers.feedforward.rbm

Methods in org.deeplearning4j.nn.layers.feedforward.rbm that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	RBM.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>,Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>>	RBM.gibbhVh(org.nd4j.linalg.api.ndarray.INDArray h) Gibbs sampling step: hidden ---> visible ---> hidden
Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	RBM.sampleHiddenGivenVisible(org.nd4j.linalg.api.ndarray.INDArray v) Binomial sampling of the hidden values given visible
Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	RBM.sampleVisibleGivenHidden(org.nd4j.linalg.api.ndarray.INDArray h) Guess the visible values given the hidden

Methods in org.deeplearning4j.nn.layers.feedforward.rbm that return types with arguments of type Pair

Modifier and Type	Method and Description
Pair<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>,Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>>	RBM.gibbhVh(org.nd4j.linalg.api.ndarray.INDArray h) Gibbs sampling step: hidden ---> visible ---> hidden
Pair<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>,Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>>	RBM.gibbhVh(org.nd4j.linalg.api.ndarray.INDArray h) Gibbs sampling step: hidden ---> visible ---> hidden

Uses of Pair in org.deeplearning4j.nn.layers.normalization

Methods in org.deeplearning4j.nn.layers.normalization that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	BatchNormalization.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	LocalResponseNormalization.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	LocalResponseNormalizationHelper.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray epsilon, double k, double n, double alpha, double beta)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	BatchNormalizationHelper.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray epsilon, int[] shape, org.nd4j.linalg.api.ndarray.INDArray gamma, org.nd4j.linalg.api.ndarray.INDArray dGammaView, org.nd4j.linalg.api.ndarray.INDArray dBetaView, double eps)

Uses of Pair in org.deeplearning4j.nn.layers.pooling

Methods in org.deeplearning4j.nn.layers.pooling that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	GlobalPoolingLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	GlobalPoolingLayer.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)

Uses of Pair in org.deeplearning4j.nn.layers.recurrent

Methods in org.deeplearning4j.nn.layers.recurrent that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	LSTM.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	RnnOutputLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	GravesBidirectionalLSTM.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	GravesLSTM.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	LSTMHelper.backpropGradient(NeuralNetConfiguration conf, org.nd4j.linalg.activations.IActivation gateActivationFn, org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray recurrentWeights, org.nd4j.linalg.api.ndarray.INDArray inputWeights, org.nd4j.linalg.api.ndarray.INDArray epsilon, boolean truncatedBPTT, int tbpttBackwardLength, FwdPassReturn fwdPass, boolean forwards, String inputWeightKey, String recurrentWeightKey, String biasWeightKey, Map<String,org.nd4j.linalg.api.ndarray.INDArray> gradientViews, org.nd4j.linalg.api.ndarray.INDArray maskArray, boolean hasPeepholeConnections)
static Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	LSTMHelpers.backpropGradientHelper(NeuralNetConfiguration conf, org.nd4j.linalg.activations.IActivation gateActivationFn, org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray recurrentWeights, org.nd4j.linalg.api.ndarray.INDArray inputWeights, org.nd4j.linalg.api.ndarray.INDArray epsilon, boolean truncatedBPTT, int tbpttBackwardLength, FwdPassReturn fwdPass, boolean forwards, String inputWeightKey, String recurrentWeightKey, String biasWeightKey, Map<String,org.nd4j.linalg.api.ndarray.INDArray> gradientViews, org.nd4j.linalg.api.ndarray.INDArray maskArray, boolean hasPeepholeConnections, LSTMHelper helper)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	LSTM.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	RnnOutputLayer.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	GravesBidirectionalLSTM.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	GravesLSTM.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	LSTM.tbpttBackpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon, int tbpttBackwardLength)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	GravesBidirectionalLSTM.tbpttBackpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon, int tbpttBackwardLength)
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	GravesLSTM.tbpttBackpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon, int tbpttBackwardLength)

Uses of Pair in org.deeplearning4j.nn.layers.training

Methods in org.deeplearning4j.nn.layers.training that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	CenterLossOutputLayer.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<Gradient,Double>	CenterLossOutputLayer.gradientAndScore()

Uses of Pair in org.deeplearning4j.nn.layers.variational

Methods in org.deeplearning4j.nn.layers.variational that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	VariationalAutoencoder.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	VariationalAutoencoder.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<Gradient,Double>	VariationalAutoencoder.gradientAndScore()

Uses of Pair in org.deeplearning4j.nn.multilayer

Methods in org.deeplearning4j.nn.multilayer that return Pair

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	MultiLayerNetwork.backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
protected Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	MultiLayerNetwork.calcBackpropGradients(org.nd4j.linalg.api.ndarray.INDArray epsilon, boolean withOutputLayer) Calculate gradients and errors.
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	MultiLayerNetwork.feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
Pair<Gradient,Double>	MultiLayerNetwork.gradientAndScore()

Uses of Pair in org.deeplearning4j.optimize.api

Methods in org.deeplearning4j.optimize.api that return Pair

Modifier and Type	Method and Description
Pair<Gradient,Double>	ConvexOptimizer.gradientAndScore() The gradient and score for this optimizer

Methods in org.deeplearning4j.optimize.api with parameters of type Pair

Modifier and Type	Method and Description
void	ConvexOptimizer.setupSearchState(Pair<Gradient,Double> pair) Based on the gradient and score setup a search state

Uses of Pair in org.deeplearning4j.optimize.listeners

Methods in org.deeplearning4j.optimize.listeners that return types with arguments of type Pair

Modifier and Type	Method and Description
List<Pair<Integer,Double>>	CollectScoresIterationListener.getScoreVsIter()

Uses of Pair in org.deeplearning4j.optimize.solvers

Methods in org.deeplearning4j.optimize.solvers that return Pair

Modifier and Type	Method and Description
Pair<Gradient,Double>	BaseOptimizer.gradientAndScore()

Methods in org.deeplearning4j.optimize.solvers with parameters of type Pair

Modifier and Type	Method and Description
void	LBFGS.setupSearchState(Pair<Gradient,Double> pair)
void	BaseOptimizer.setupSearchState(Pair<Gradient,Double> pair) Setup the initial search state

Uses of Pair in org.deeplearning4j.util

Methods in org.deeplearning4j.util that return Pair

Modifier and Type	Method and Description
Pair<Double,org.nd4j.linalg.api.ndarray.INDArray>	Viterbi.decode(org.nd4j.linalg.api.ndarray.INDArray labels) Decodes the given labels, assuming its a binary label matrix
Pair<Double,org.nd4j.linalg.api.ndarray.INDArray>	Viterbi.decode(org.nd4j.linalg.api.ndarray.INDArray labels, boolean binaryLabelMatrix) Decodes a series of labels
Pair<K,T>	MultiDimensionalMap.Entry.getKey() Returns the key corresponding to this entry.

Methods in org.deeplearning4j.util that return types with arguments of type Pair

Modifier and Type	Method and Description
Iterator<Pair<K,V>>	MultiDimensionalSet.iterator() Returns an iterator over the elements in this applyTransformToDestination.
Set<Pair<K,T>>	MultiDimensionalMap.keySet() Returns a Set view of the keys contained in this map.

Methods in org.deeplearning4j.util with parameters of type Pair

Modifier and Type	Method and Description
boolean	MultiDimensionalSet.add(Pair<K,V> kvPair) Adds the specified element to this applyTransformToDestination if it is not already present (optional operation).
V	MultiDimensionalMap.put(Pair<K,T> key, V value) Associates the specified value with the specified key in this map (optional operation).

Method parameters in org.deeplearning4j.util with type arguments of type Pair

Modifier and Type	Method and Description
boolean	MultiDimensionalSet.addAll(Collection<? extends Pair<K,V>> c) Adds all of the elements in the specified collection to this applyTransformToDestination if they're not already present (optional operation).
void	MultiDimensionalMap.putAll(Map<? extends Pair<K,T>,? extends V> m) Copies all of the mappings from the specified map to this map (optional operation).
static void	InputSplit.splitInputs(org.nd4j.linalg.api.ndarray.INDArray inputs, org.nd4j.linalg.api.ndarray.INDArray outcomes, List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> train, List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> test, double split)
static void	InputSplit.splitInputs(org.nd4j.linalg.api.ndarray.INDArray inputs, org.nd4j.linalg.api.ndarray.INDArray outcomes, List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> train, List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> test, double split)
static void	InputSplit.splitInputs(List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> pairs, List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> train, List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> test, double split)
static void	InputSplit.splitInputs(List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> pairs, List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> train, List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> test, double split)
static void	InputSplit.splitInputs(List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> pairs, List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> train, List<Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>> test, double split)

Constructor parameters in org.deeplearning4j.util with type arguments of type Pair

Constructor and Description
MultiDimensionalMap(Map<Pair<K,T>,V> backedMap)
MultiDimensionalSet(Set<Pair<K,V>> backedSet)