Class QuantizedBatchNormWithGlobalNormalization<U extends TNumber>

java.lang.Object

org.tensorflow.op.RawOp

org.tensorflow.op.nn.QuantizedBatchNormWithGlobalNormalization<U>

All Implemented Interfaces:

Op

@Operator(group="nn")
public final class QuantizedBatchNormWithGlobalNormalization<U extends TNumber>
extends RawOp

Quantized Batch normalization. This op is deprecated and will be removed in the future. Prefer tf.nn.batch_normalization.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	QuantizedBatchNormWithGlobalNormalization.Inputs<T extends TNumber>

Field Summary

Fields

Modifier and Type	Field	Description
static final String	OP_NAME	The name of this op, as known by TensorFlow core engine

Fields inherited from class RawOp

operation

Constructor Summary

Constructors

Constructor	Description
QuantizedBatchNormWithGlobalNormalization(Operation operation)

Method Summary

Modifier and Type	Method	Description
static <U extends TNumber, T extends TNumber> QuantizedBatchNormWithGlobalNormalization<U>	create(Scope scope, Operand<T> t, Operand<TFloat32> tMin, Operand<TFloat32> tMax, Operand<T> m, Operand<TFloat32> mMin, Operand<TFloat32> mMax, Operand<T> v, Operand<TFloat32> vMin, Operand<TFloat32> vMax, Operand<T> beta, Operand<TFloat32> betaMin, Operand<TFloat32> betaMax, Operand<T> gamma, Operand<TFloat32> gammaMin, Operand<TFloat32> gammaMax, Class<U> outType, Float varianceEpsilon, Boolean scaleAfterNormalization)	Factory method to create a class wrapping a new QuantizedBatchNormWithGlobalNormalization operation.
Output<U>	result()	Gets result.
Output<TFloat32>	resultMax()	Gets resultMax.
Output<TFloat32>	resultMin()	Gets resultMin.

Methods inherited from class RawOp

equals, hashCode, op, toString

Methods inherited from class Object

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

Methods inherited from interface Op

env

Field Details

OP_NAME

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

See Also:

• Constant Field Values

Constructor Details

QuantizedBatchNormWithGlobalNormalization

public QuantizedBatchNormWithGlobalNormalization(Operation operation)

Method Details

create

@Endpoint(describeByClass=true)
public static <U extends TNumber, T extends TNumber>
QuantizedBatchNormWithGlobalNormalization<U> create(Scope scope,
 Operand<T> t,
 Operand<TFloat32> tMin,
 Operand<TFloat32> tMax,
 Operand<T> m,
 Operand<TFloat32> mMin,
 Operand<TFloat32> mMax,
 Operand<T> v,
 Operand<TFloat32> vMin,
 Operand<TFloat32> vMax,
 Operand<T> beta,
 Operand<TFloat32> betaMin,
 Operand<TFloat32> betaMax,
 Operand<T> gamma,
 Operand<TFloat32> gammaMin,
 Operand<TFloat32> gammaMax,
 Class<U> outType,
 Float varianceEpsilon,
 Boolean scaleAfterNormalization)

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

Type Parameters:

U - data type for QuantizedBatchNormWithGlobalNormalization output and operands

T - data type for QuantizedBatchNormWithGlobalNormalization output and operands

Parameters:

scope - current scope

t - A 4D input Tensor.

tMin - The value represented by the lowest quantized input.

tMax - The value represented by the highest quantized input.

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.

mMin - The value represented by the lowest quantized mean.

mMax - The value represented by the highest quantized mean.

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.

vMin - The value represented by the lowest quantized variance.

vMax - The value represented by the highest quantized variance.

beta - A 1D beta Tensor with size matching the last dimension of t. An offset to be added to the normalized tensor.

betaMin - The value represented by the lowest quantized offset.

betaMax - The value represented by the highest quantized offset.

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.

gammaMin - The value represented by the lowest quantized gamma.

gammaMax - The value represented by the highest quantized gamma.

outType - The value of the outType attribute

varianceEpsilon - A small float number to avoid dividing by 0.

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

Returns:

a new instance of QuantizedBatchNormWithGlobalNormalization

result

public Output<U> result()

Gets result.

Returns:

result.

resultMin

public Output<TFloat32> resultMin()

Gets resultMin.

Returns:

resultMin.

resultMax

public Output<TFloat32> resultMax()

Gets resultMax.

Returns:

resultMax.