org.deeplearning4j.nn.conf.graph

Class UnstackVertex

java.lang.Object

org.deeplearning4j.nn.conf.graph.GraphVertex

org.deeplearning4j.nn.conf.graph.UnstackVertex

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable

public class UnstackVertex
extends GraphVertex

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.

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected int	from
protected int	stackSize

Constructor Summary

Constructors

Constructor and Description
UnstackVertex(int from, int stackSize)

Method Summary

Modifier and Type	Method and Description
UnstackVertex	clone()
boolean	equals(java.lang.Object o)
InputType	getOutputType(int layerIndex, InputType... vertexInputs) Determine the type of output for this GraphVertex, given the specified inputs.
int	hashCode()
GraphVertex	instantiate(ComputationGraph graph, java.lang.String name, int idx, org.nd4j.linalg.api.ndarray.INDArray paramsView, boolean initializeParams) Create a GraphVertex instance, for the given computation graph, given the configuration instance.
int	numParams(boolean backprop)

Methods inherited from class java.lang.Object

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

Field Detail

from

protected int from

stackSize

protected int stackSize

Constructor Detail

UnstackVertex

public UnstackVertex(int from,
                     int stackSize)

Parameters:

from - The first column index of the stacked inputs.

stackSize - The total number of stacked inputs. An interval is automatically calculated according to the size of the first dimension.

Method Detail

instantiate

public GraphVertex instantiate(ComputationGraph graph,
                               java.lang.String name,
                               int idx,
                               org.nd4j.linalg.api.ndarray.INDArray paramsView,
                               boolean initializeParams)

Description copied from class: GraphVertex

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

Specified by:

instantiate in class GraphVertex

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

Returns:

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

clone

public UnstackVertex clone()

Specified by:

clone in class GraphVertex

equals

public boolean equals(java.lang.Object o)

Specified by:

equals in class GraphVertex

numParams

public int numParams(boolean backprop)

Specified by:

numParams in class GraphVertex

hashCode

public int hashCode()

Specified by:

hashCode in class GraphVertex

getOutputType

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

Description copied from class: GraphVertex

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

Specified by:

getOutputType in class GraphVertex

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