Class FractionalAvgPoolGrad.Inputs<T extends TNumber>

java.lang.Object

org.tensorflow.op.RawOpInputs<FractionalAvgPoolGrad<T>>

org.tensorflow.op.nn.FractionalAvgPoolGrad.Inputs<T>

Enclosing class:

FractionalAvgPoolGrad<T extends TNumber>

public static class FractionalAvgPoolGrad.Inputs<T extends TNumber>
extends RawOpInputs<FractionalAvgPoolGrad<T>>

Field Summary

Fields

Modifier and Type	Field	Description
final Operand<TInt64>	colPoolingSequence	column pooling sequence, form pooling region with row_pooling sequence.
final Operand<TInt64>	origInputTensorShape	Original input tensor shape for fractional_avg_pool
final Operand<T>	outBackprop	4-D with shape [batch, height, width, channels].
final boolean	overlapping	When set to True, it means when pooling, the values at the boundary of adjacent pooling cells are used by both cells.
final Operand<TInt64>	rowPoolingSequence	row pooling sequence, form pooling region with col_pooling_sequence.
final DataType	T	The T attribute

Constructor Summary

Constructors

Constructor	Description
Inputs(GraphOperation op)

Method Summary

Methods inherited from class RawOpInputs

attributeMetadata, attributeNames, attributes, attributeValue, attributeValues, equals, getOutputs, hashCode, toString

Modifier and Type	Method	Description
AttributeMetadata	attributeMetadata(String name)	Get the metadata for an attribute
Set<String>	attributeNames()	Get the names of this op's attributes
OperationAttributeInspector	attributes()	Get an inspector for the operation's attributes.
AttrValue	attributeValue(String name)	Get the value of an attribute as an AttrValue proto.
Map<String, AttrValue>	attributeValues()	Get all attribute value protos
final boolean	equals(Object obj)
FractionalAvgPoolGrad<T>	getOutputs()	The outputs of this operation.
final int	hashCode()
final String	toString()

Methods inherited from class Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Field Details

origInputTensorShape

public final Operand<TInt64> origInputTensorShape

Original input tensor shape for fractional_avg_pool

outBackprop

public final Operand<T extends TNumber> outBackprop

4-D with shape [batch, height, width, channels]. Gradients w.r.t. the output of fractional_avg_pool.

rowPoolingSequence

public final Operand<TInt64> rowPoolingSequence

row pooling sequence, form pooling region with col_pooling_sequence.

colPoolingSequence

public final Operand<TInt64> colPoolingSequence

column pooling sequence, form pooling region with row_pooling sequence.

overlapping

public final boolean overlapping

When set to True, it means when pooling, the values at the boundary of adjacent pooling cells are used by both cells. For example:

index 0 1 2 3 4

value 20 5 16 3 7

If the pooling sequence is [0, 2, 4], then 16, at index 2 will be used twice. The result would be [41/3, 26/3] for fractional avg pooling.

T

public final DataType T

The T attribute

Constructor Details

Inputs

public Inputs(GraphOperation op)