org.deeplearning4j.nn.graph.vertex.impl.rnn

Class ReverseTimeSeriesVertex

java.lang.Object

org.deeplearning4j.nn.graph.vertex.BaseGraphVertex

org.deeplearning4j.nn.graph.vertex.impl.rnn.ReverseTimeSeriesVertex

All Implemented Interfaces:

Serializable, GraphVertex

public class ReverseTimeSeriesVertex
extends BaseGraphVertex

ReverseTimeSeriesVertex is used in recurrent neural networks to revert the order of time series. As a result, the last time step is moved to the beginning of the time series and the first time step is moved to the end. This allows recurrent layers to backward process time series.

Masks: The input might be masked (to allow for varying time series lengths in one minibatch). In this case the present input (mask array = 1) will be reverted in place and the padding (mask array = 0) will be left untouched at the same place. For a time series of length n, this would normally mean, that the first n time steps are reverted and the following padding is left untouched, but more complex masks are supported (e.g. [1, 0, 1, 0, ...].

Author:

Klaus Broelemann (SCHUFA Holding AG)

See Also:

Serialized Form

Field Summary

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

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

Constructor Summary

Constructors

Constructor and Description
ReverseTimeSeriesVertex(ComputationGraph graph, String name, int vertexIndex, String inputName)

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.primitives.Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray[]>	doBackward(boolean tbptt, LayerWorkspaceMgr workspaceMgr) Do backward pass
org.nd4j.linalg.api.ndarray.INDArray	doForward(boolean training, LayerWorkspaceMgr workspaceMgr) Do forward pass using the stored inputs
org.nd4j.linalg.primitives.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)
String	toString()

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

canDoBackward, canDoForward, clear, clearVertex, 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, setOutputVertex

Constructor Detail

ReverseTimeSeriesVertex

public ReverseTimeSeriesVertex(ComputationGraph graph,
                               String name,
                               int vertexIndex,
                               String inputName)

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,
                                                      LayerWorkspaceMgr workspaceMgr)

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

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

toString

public String toString()

Specified by:

toString in class BaseGraphVertex