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

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.