org.deeplearning4j.nn.conf.graph

Class GraphVertex

java.lang.Object

org.deeplearning4j.nn.conf.graph.GraphVertex

All Implemented Interfaces:

Serializable, Cloneable

Direct Known Subclasses:

DuplicateToTimeSeriesVertex, ElementWiseVertex, FrozenVertex, L2NormalizeVertex, L2Vertex, LastTimeStepVertex, LayerVertex, MergeVertex, PoolHelperVertex, PreprocessorVertex, ReshapeVertex, ReverseTimeSeriesVertex, SameDiffVertex, ScaleVertex, ShiftVertex, StackVertex, SubsetVertex, UnstackVertex

public abstract class GraphVertex
extends Object
implements Cloneable, Serializable

A GraphVertex is a vertex in the computation graph type of neural network. It may contain Layer, or define some arbitrary forward/backward pass behaviour based on the inputs. GraphVertex instances may also have trainable parameters.

Author:

Alex Black

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
GraphVertex()

Method Summary

Modifier and Type	Method and Description
abstract GraphVertex	clone()
abstract boolean	equals(Object o)
abstract MemoryReport	getMemoryReport(InputType... inputTypes) This is a report of the estimated memory consumption for the given vertex
abstract InputType	getOutputType(int layerIndex, InputType... vertexInputs) Determine the type of output for this GraphVertex, given the specified inputs.
abstract int	hashCode()
abstract GraphVertex	instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype) Create a GraphVertex instance, for the given computation graph, given the configuration instance.
abstract int	maxVertexInputs()
abstract int	minVertexInputs()
abstract long	numParams(boolean backprop)
void	setDataType(org.nd4j.linalg.api.buffer.DataType dataType)

Methods inherited from class java.lang.Object

finalize, getClass, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

GraphVertex

public GraphVertex()

Method Detail

clone

public abstract GraphVertex clone()

Overrides:

clone in class Object

equals

public abstract boolean equals(Object o)

Overrides:

equals in class Object

hashCode

public abstract int hashCode()

Overrides:

hashCode in class Object

numParams

public abstract long numParams(boolean backprop)

minVertexInputs

public abstract int minVertexInputs()

Returns:

The Smallest valid number of inputs to this vertex

maxVertexInputs

public abstract int maxVertexInputs()

Returns:

The largest valid number of inputs to this vertex

instantiate

public abstract GraphVertex instantiate(ComputationGraph graph,
                                        String name,
                                        int idx,
                                        INDArray paramsView,
                                        boolean initializeParams,
                                        org.nd4j.linalg.api.buffer.DataType networkDatatype)

Create a GraphVertex instance, for the given computation graph, given the configuration instance.

Parameters:

graph - The computation graph that this GraphVertex is to be part of

name - The name of the GraphVertex object

idx - The index of the GraphVertex

paramsView - A view of the full parameters array

initializeParams - If true: initialize the parameters. If false: make no change to the values in the paramsView array

networkDatatype -

Returns:

The implementation GraphVertex object (i.e., implementation, no the configuration)

getOutputType

public abstract InputType getOutputType(int layerIndex,
                                        InputType... vertexInputs)
                                 throws InvalidInputTypeException

Determine the type of output for this GraphVertex, given the specified inputs. Given that a GraphVertex may do arbitrary processing or modifications of the inputs, the output types can be quite different to the input type(s).
This is generally used to determine when to add preprocessors, as well as the input sizes etc for layers

Parameters:

layerIndex - The index of the layer (if appropriate/necessary).

vertexInputs - The inputs to this vertex

Returns:

The type of output for this vertex

Throws:

InvalidInputTypeException - If the input type is invalid for this type of GraphVertex

getMemoryReport

public abstract MemoryReport getMemoryReport(InputType... inputTypes)

This is a report of the estimated memory consumption for the given vertex

Parameters:

inputTypes - Input types to the vertex. Memory consumption is often a function of the input type

Returns:

Memory report for the vertex

setDataType

public void setDataType(org.nd4j.linalg.api.buffer.DataType dataType)