T
- data type for y()
output@Operator(group="nn") public final class QuantizedInstanceNorm<T> extends PrimitiveOp
Modifier and Type | Class and Description |
---|---|
static class |
QuantizedInstanceNorm.Options
Optional attributes for
QuantizedInstanceNorm |
operation
Modifier and Type | Method and Description |
---|---|
static <T> QuantizedInstanceNorm<T> |
create(Scope scope,
Operand<T> x,
Operand<Float> xMin,
Operand<Float> xMax,
QuantizedInstanceNorm.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<Float> |
yMax()
The value represented by the highest quantized output.
|
Output<Float> |
yMin()
The value represented by the lowest quantized output.
|
equals, hashCode, op, toString
public static <T> QuantizedInstanceNorm<T> create(Scope scope, Operand<T> x, Operand<Float> xMin, Operand<Float> xMax, QuantizedInstanceNorm.Options... options)
scope
- current scopex
- 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 valuespublic static QuantizedInstanceNorm.Options outputRangeGiven(Boolean outputRangeGiven)
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 givenYMin(Float givenYMin)
givenYMin
- Output in `y_min` if `output_range_given` is True.public static QuantizedInstanceNorm.Options givenYMax(Float givenYMax)
givenYMax
- Output in `y_max` if `output_range_given` is True.public static QuantizedInstanceNorm.Options varianceEpsilon(Float varianceEpsilon)
varianceEpsilon
- A small float number to avoid dividing by 0.public static QuantizedInstanceNorm.Options minSeparation(Float minSeparation)
minSeparation
- Minimum value of `y_max - y_min`Copyright © 2022. All rights reserved.