org.tensorflow.op.nn

Class FusedBatchNorm<T extends Number,U extends Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.nn.FusedBatchNorm<T,U>

Type Parameters:

T - data type for y() output

U - data type for batchMean() output

All Implemented Interfaces:

Op

@Operator(group="nn")
public final class FusedBatchNorm<T extends Number,U extends Number>
extends PrimitiveOp

Batch normalization.

Note that the size of 4D Tensors are defined by either "NHWC" or "NCHW". The size of 1D Tensors matches the dimension C of the 4D Tensors.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	FusedBatchNorm.Options Optional attributes for FusedBatchNorm

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
Output<U>	batchMean() A 1D Tensor for the computed batch mean, to be used by TensorFlow to compute the running mean.
Output<U>	batchVariance() A 1D Tensor for the computed batch variance, to be used by TensorFlow to compute the running variance.
static <T extends Number,U extends Number> FusedBatchNorm<T,U>	create(Scope scope, Operand<T> x, Operand<U> scale, Operand<U> offset, Operand<U> mean, Operand<U> variance, FusedBatchNorm.Options... options) Factory method to create a class wrapping a new FusedBatchNorm operation.
static FusedBatchNorm.Options	dataFormat(String dataFormat)
static FusedBatchNorm.Options	epsilon(Float epsilon)
static FusedBatchNorm.Options	isTraining(Boolean isTraining)
Output<U>	reserveSpace1() A 1D Tensor for the computed batch mean, to be reused in the gradient computation.
Output<U>	reserveSpace2() A 1D Tensor for the computed batch variance (inverted variance in the cuDNN case), to be reused in the gradient computation.
Output<T>	y() A 4D Tensor for output data.

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, op, toString

Methods inherited from class java.lang.Object

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

Method Detail

create

public static <T extends Number,U extends Number> FusedBatchNorm<T,U> create(Scope scope,
                                                                             Operand<T> x,
                                                                             Operand<U> scale,
                                                                             Operand<U> offset,
                                                                             Operand<U> mean,
                                                                             Operand<U> variance,
                                                                             FusedBatchNorm.Options... options)

Factory method to create a class wrapping a new FusedBatchNorm operation.

Parameters:

scope - current scope

x - A 4D Tensor for input data.

scale - A 1D Tensor for scaling factor, to scale the normalized x.

offset - A 1D Tensor for offset, to shift to the normalized x.

mean - A 1D Tensor for population mean. Used for inference only; must be empty for training.

variance - A 1D Tensor for population variance. Used for inference only; must be empty for training.

options - carries optional attributes values

Returns:

a new instance of FusedBatchNorm

epsilon

public static FusedBatchNorm.Options epsilon(Float epsilon)

Parameters:

epsilon - A small float number added to the variance of x.

dataFormat

public static FusedBatchNorm.Options dataFormat(String dataFormat)

Parameters:

dataFormat - The data format for x and y. Either "NHWC" (default) or "NCHW".

isTraining

public static FusedBatchNorm.Options isTraining(Boolean isTraining)

Parameters:

isTraining - A bool value to indicate the operation is for training (default) or inference.

y

public Output<T> y()

A 4D Tensor for output data.

batchMean

public Output<U> batchMean()

A 1D Tensor for the computed batch mean, to be used by TensorFlow to compute the running mean.

batchVariance

public Output<U> batchVariance()

A 1D Tensor for the computed batch variance, to be used by TensorFlow to compute the running variance.

reserveSpace1

public Output<U> reserveSpace1()

A 1D Tensor for the computed batch mean, to be reused in the gradient computation.

reserveSpace2

public Output<U> reserveSpace2()

A 1D Tensor for the computed batch variance (inverted variance in the cuDNN case), to be reused in the gradient computation.