Class BatchNormWithGlobalNormalizationGrad.Inputs<T extends TType>

java.lang.Object

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

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

Enclosing class:

BatchNormWithGlobalNormalizationGrad<T extends TType>

public static class BatchNormWithGlobalNormalizationGrad.Inputs<T extends TType>
extends RawOpInputs<BatchNormWithGlobalNormalizationGrad<T>>

Field Summary

Fields

Modifier and Type	Field	Description
final Operand<T>	backprop	4D backprop Tensor.
final Operand<T>	gamma	A 1D gamma Tensor with size matching the last dimension of t.
final Operand<T>	m	A 1D mean Tensor with size matching the last dimension of t.
final boolean	scaleAfterNormalization	A bool indicating whether the resulted tensor needs to be multiplied with gamma.
final Operand<T>	t	A 4D input Tensor.
final DataType	T	The T attribute
final Operand<T>	v	A 1D variance Tensor with size matching the last dimension of t.
final float	varianceEpsilon	A small float number to avoid dividing by 0.

Constructor Summary

Constructors

Constructor	Description
Inputs(GraphOperation op)

Method Summary

Methods inherited from class RawOpInputs

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

Methods inherited from class Object

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

Field Details

t

public final Operand<T extends TType> t

A 4D input Tensor.

m

public final Operand<T extends TType> m

A 1D mean Tensor with size matching the last dimension of t. This is the first output from tf.nn.moments, or a saved moving average thereof.

v

public final Operand<T extends TType> v

A 1D variance Tensor with size matching the last dimension of t. This is the second output from tf.nn.moments, or a saved moving average thereof.

gamma

public final Operand<T extends TType> gamma

A 1D gamma Tensor with size matching the last dimension of t. If "scale_after_normalization" is true, this Tensor will be multiplied with the normalized Tensor.

backprop

public final Operand<T extends TType> backprop

4D backprop Tensor.

T

public final DataType T

The T attribute

varianceEpsilon

public final float varianceEpsilon

A small float number to avoid dividing by 0.

scaleAfterNormalization

public final boolean scaleAfterNormalization

A bool indicating whether the resulted tensor needs to be multiplied with gamma.

Constructor Details

Inputs

public Inputs(GraphOperation op)