org.deeplearning4j.nn.graph.vertex.impl

Class UnstackVertex

java.lang.Object

org.deeplearning4j.nn.graph.vertex.BaseGraphVertex

org.deeplearning4j.nn.graph.vertex.impl.UnstackVertex

All Implemented Interfaces:

java.io.Serializable, GraphVertex

public class UnstackVertex
extends BaseGraphVertex

UnstackVertex allows for unstacking of inputs so that they may be forwarded through a network. This is useful for cases such as Triplet Embedding, where embeddings can be separated and run through subsequent layers. Works similarly to SubsetVertex, except on dimension 0 of the input. stackSize is explicitly defined by the user to properly calculate an step.

See Also:

Serialized Form

Field Summary

Fields inherited from class org.deeplearning4j.nn.graph.vertex.BaseGraphVertex

epsilon, graph, inputs, inputVertices, outputVertices, vertexIndex, vertexName

Constructor Summary

Constructors

Constructor and Description
UnstackVertex(ComputationGraph graph, java.lang.String name, int vertexIndex, int from, int stackSize)
UnstackVertex(ComputationGraph graph, java.lang.String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, int from, int stackSize)

Method Summary

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	doBackward(boolean tbptt) Do backward pass
org.nd4j.linalg.api.ndarray.INDArray	doForward(boolean training) Do forward pass using the stored inputs
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
Layer	getLayer() Get the Layer (if any).
boolean	hasLayer() Whether the GraphVertex contains a Layer object or not
boolean	isOutputVertex() Whether the GraphVertex is an output vertex
void	setBackpropGradientsViewArray(org.nd4j.linalg.api.ndarray.INDArray backpropGradientsViewArray) See Model.setBackpropGradientsViewArray(INDArray)
java.lang.String	toString()

Methods inherited from class org.deeplearning4j.nn.graph.vertex.BaseGraphVertex

canDoBackward, canDoForward, clear, getEpsilon, getInputVertices, getNumInputArrays, getNumOutputConnections, getOutputVertices, getVertexIndex, getVertexName, isInputVertex, setEpsilon, setInput, setInputVertices, setLayerAsFrozen, setOutputVertices

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.deeplearning4j.nn.graph.vertex.GraphVertex

getInputs, setInputs

Constructor Detail

UnstackVertex

public UnstackVertex(ComputationGraph graph,
                     java.lang.String name,
                     int vertexIndex,
                     int from,
                     int stackSize)

UnstackVertex

public UnstackVertex(ComputationGraph graph,
                     java.lang.String name,
                     int vertexIndex,
                     VertexIndices[] inputVertices,
                     VertexIndices[] outputVertices,
                     int from,
                     int stackSize)

Method Detail

hasLayer

public boolean hasLayer()

Description copied from interface: GraphVertex

Whether the GraphVertex contains a Layer object or not

isOutputVertex

public boolean isOutputVertex()

Description copied from interface: GraphVertex

Whether the GraphVertex is an output vertex

getLayer

public Layer getLayer()

Description copied from interface: GraphVertex

Get the Layer (if any). Returns null if GraphVertex.hasLayer() == false

doForward

public org.nd4j.linalg.api.ndarray.INDArray doForward(boolean training)

Description copied from interface: GraphVertex

Do forward pass using the stored inputs

Parameters:

training - if true: forward pass at training time. If false: forward pass at test time

Returns:

The output (for example, activations) of the GraphVertex

doBackward

public Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]> doBackward(boolean tbptt)

Description copied from interface: GraphVertex

Do backward pass

Parameters:

tbptt - If true: do backprop using truncated BPTT

Returns:

The gradients (may be null), and the errors/epsilons for all inputs to this GraphVertex

setBackpropGradientsViewArray

public void setBackpropGradientsViewArray(org.nd4j.linalg.api.ndarray.INDArray backpropGradientsViewArray)

Description copied from interface: GraphVertex

See Model.setBackpropGradientsViewArray(INDArray)

feedForwardMaskArrays

public Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState> feedForwardMaskArrays(org.nd4j.linalg.api.ndarray.INDArray[] maskArrays,
                                                                                  MaskState currentMaskState,
                                                                                  int minibatchSize)

toString

public java.lang.String toString()

Specified by:

toString in class BaseGraphVertex