org.deeplearning4j.nn.graph.vertex.impl

Class LayerVertex

java.lang.Object

org.deeplearning4j.nn.graph.vertex.BaseGraphVertex

org.deeplearning4j.nn.graph.vertex.impl.LayerVertex

All Implemented Interfaces:

Serializable, Trainable, GraphVertex

public class LayerVertex
extends BaseGraphVertex

LayerVertex is a GraphVertex with a neural network Layer (and, optionally an InputPreProcessor) in it

Author:

Alex Black

See Also:

Serialized Form

Field Summary

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

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

Constructor Summary

Constructors

Constructor and Description
LayerVertex(ComputationGraph graph, String name, int vertexIndex, Layer layer, InputPreProcessor layerPreProcessor, boolean outputVertex, DataType dataType) Create a network input vertex:
LayerVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, Layer layer, InputPreProcessor layerPreProcessor, boolean outputVertex, DataType dataType)

Method Summary

Modifier and Type	Method and Description
void	applyPreprocessorAndSetInput(LayerWorkspaceMgr workspaceMgr)
boolean	canDoBackward() Whether the GraphVertex can do backward pass.
double	computeScore(double r, boolean training, LayerWorkspaceMgr workspaceMgr)
INDArray	computeScoreForExamples(double r, LayerWorkspaceMgr workspaceMgr)
Pair<Gradient,INDArray[]>	doBackward(boolean tbptt, LayerWorkspaceMgr workspaceMgr) Do backward pass
INDArray	doForward(boolean training, LayerWorkspaceMgr workspaceMgr) Do forward pass using the stored inputs
Pair<INDArray,MaskState>	feedForwardMaskArrays(INDArray[] maskArrays, MaskState currentMaskState, int minibatchSize)
TrainingConfig	getConfig()
INDArray	getGradientsViewArray()
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
INDArray	params()
Map<String,INDArray>	paramTable(boolean backpropOnly) Get the parameter table for the vertex
void	setBackpropGradientsViewArray(INDArray backpropGradientsViewArray) See Model.setBackpropGradientsViewArray(INDArray)
void	setInput(int inputNumber, INDArray input, LayerWorkspaceMgr workspaceMgr) Set the input activations.
void	setLayerAsFrozen() Only applies to layer vertices.
String	toString()

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

canDoForward, clear, clearVertex, getEpsilon, getInputVertices, getNumInputArrays, getNumOutputConnections, getOutputVertices, getVertexIndex, getVertexName, isInputVertex, numParams, setEpsilon, setInputVertices, setOutputVertices, updaterDivideByMinibatch

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

LayerVertex

public LayerVertex(ComputationGraph graph,
                   String name,
                   int vertexIndex,
                   Layer layer,
                   InputPreProcessor layerPreProcessor,
                   boolean outputVertex,
                   DataType dataType)

Create a network input vertex:

LayerVertex

public LayerVertex(ComputationGraph graph,
                   String name,
                   int vertexIndex,
                   VertexIndices[] inputVertices,
                   VertexIndices[] outputVertices,
                   Layer layer,
                   InputPreProcessor layerPreProcessor,
                   boolean outputVertex,
                   DataType dataType)

Method Detail

hasLayer

public boolean hasLayer()

Description copied from interface: GraphVertex

Whether the GraphVertex contains a Layer object or not

setLayerAsFrozen

public void setLayerAsFrozen()

Description copied from interface: GraphVertex

Only applies to layer vertices. Will throw exceptions on others. If applied to a layer vertex it will treat the parameters of the layer within it as constant. Activations through these will be calculated as they would as test time regardless of training mode

Specified by:

setLayerAsFrozen in interface GraphVertex

Overrides:

setLayerAsFrozen in class BaseGraphVertex

paramTable

public Map<String,INDArray> paramTable(boolean backpropOnly)

Description copied from interface: GraphVertex

Get the parameter table for the vertex

Specified by:

paramTable in interface Trainable

Specified by:

paramTable in interface GraphVertex

Overrides:

paramTable in class BaseGraphVertex

Parameters:

backpropOnly - If true: exclude unsupervised training parameters

Returns:

Parameter table

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 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

applyPreprocessorAndSetInput

public void applyPreprocessorAndSetInput(LayerWorkspaceMgr workspaceMgr)

doBackward

public Pair<Gradient,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

setInput

public void setInput(int inputNumber,
                     INDArray input,
                     LayerWorkspaceMgr workspaceMgr)

Description copied from interface: GraphVertex

Set the input activations.

Specified by:

setInput in interface GraphVertex

Overrides:

setInput in class BaseGraphVertex

Parameters:

inputNumber - Must be in range 0 to GraphVertex.getNumInputArrays()-1

input - The input array

setBackpropGradientsViewArray

public void setBackpropGradientsViewArray(INDArray backpropGradientsViewArray)

Description copied from interface: GraphVertex

See Model.setBackpropGradientsViewArray(INDArray)

feedForwardMaskArrays

public Pair<INDArray,MaskState> feedForwardMaskArrays(INDArray[] maskArrays,
                                                      MaskState currentMaskState,
                                                      int minibatchSize)

toString

public String toString()

Specified by:

toString in class BaseGraphVertex

canDoBackward

public boolean canDoBackward()

Description copied from interface: GraphVertex

Whether the GraphVertex can do backward pass. Typically, this is just whether all errors/epsilons are set

Specified by:

canDoBackward in interface GraphVertex

Overrides:

canDoBackward in class BaseGraphVertex

computeScore

public double computeScore(double r,
                           boolean training,
                           LayerWorkspaceMgr workspaceMgr)

computeScoreForExamples

public INDArray computeScoreForExamples(double r,
                                        LayerWorkspaceMgr workspaceMgr)

getConfig

public TrainingConfig getConfig()

Specified by:

getConfig in interface Trainable

Overrides:

getConfig in class BaseGraphVertex

Returns:

Training configuration

params

public INDArray params()

Specified by:

params in interface Trainable

Overrides:

params in class BaseGraphVertex

Returns:

1d parameter vector

getGradientsViewArray

public INDArray getGradientsViewArray()

Specified by:

getGradientsViewArray in interface Trainable

Overrides:

getGradientsViewArray in class BaseGraphVertex

Returns:

1D gradients view array