QuantizedInstanceNorm

public final class QuantizedInstanceNorm

Quantized Instance normalization.

Nested Classes

class

QuantizedInstanceNorm.Options

Optional attributes for QuantizedInstanceNorm

Constants

String

OP_NAME

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

Public Methods

static <T extends TType> QuantizedInstanceNorm<T>	create(Scope scope, Operand<T> x, Operand<TFloat32> xMin, Operand<TFloat32> xMax, Options... options) Factory method to create a class wrapping a new QuantizedInstanceNorm operation.
static QuantizedInstanceNorm.Options	givenYMax(Float givenYMax)
static QuantizedInstanceNorm.Options	givenYMin(Float givenYMin)
static QuantizedInstanceNorm.Options	minSeparation(Float minSeparation)
static QuantizedInstanceNorm.Options	outputRangeGiven(Boolean outputRangeGiven)
static QuantizedInstanceNorm.Options	varianceEpsilon(Float varianceEpsilon)
Output<T>	y() A 4D Tensor.
Output<TFloat32>	yMax() The value represented by the highest quantized output.
Output<TFloat32>	yMin() The value represented by the lowest quantized output.

Inherited Methods

From class org.tensorflow.op.RawOp

final boolean	equals(Object obj)
final int	hashCode()
Operation	op() Return this unit of computation as a single Operation.
final String	toString()

From class java.lang.Object

boolean	equals(Object arg0)
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

From interface org.tensorflow.op.Op

abstract ExecutionEnvironment	env() Return the execution environment this op was created in.
abstract Operation	op() Return this unit of computation as a single Operation.

Constants

public static final String OP_NAME

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

Constant Value: "QuantizedInstanceNorm"

Public Methods

public static QuantizedInstanceNorm<T> create (Scope scope, Operand<T> x, Operand<TFloat32> xMin, Operand<TFloat32> xMax, Options... options)

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

Parameters

scope	current scope
x	A 4D input Tensor.
xMin	The value represented by the lowest quantized input.
xMax	The value represented by the highest quantized input.
options	carries optional attributes values

Returns

• a new instance of QuantizedInstanceNorm

public static QuantizedInstanceNorm.Options givenYMax (Float givenYMax)

Parameters

givenYMax	Output in `y_max` if `output_range_given` is True.

public static QuantizedInstanceNorm.Options givenYMin (Float givenYMin)

Parameters

givenYMin	Output in `y_min` if `output_range_given` is True.

public static QuantizedInstanceNorm.Options minSeparation (Float minSeparation)

Parameters

minSeparation	Minimum value of `y_max - y_min`

public static QuantizedInstanceNorm.Options outputRangeGiven (Boolean outputRangeGiven)

Parameters

outputRangeGiven	If True, `given_y_min` and `given_y_min` and `given_y_max` are used as the output range. Otherwise, the implementation computes the output range.

public static QuantizedInstanceNorm.Options varianceEpsilon (Float varianceEpsilon)

Parameters

varianceEpsilon	A small float number to avoid dividing by 0.

public Output<T> y ()

A 4D Tensor.

public Output<TFloat32> yMax ()

The value represented by the highest quantized output.

public Output<TFloat32> yMin ()

The value represented by the lowest quantized output.