@Operator(group="quantization") public final class RequantizationRange extends PrimitiveOp
Given a quantized tensor described by `(input, input_min, input_max)`, outputs a range that covers the actual values present in that tensor. This op is typically used to produce the `requested_output_min` and `requested_output_max` for `Requantize`.
operation
Modifier and Type | Method and Description |
---|---|
static <T> RequantizationRange |
create(Scope scope,
Operand<T> input,
Operand<Float> inputMin,
Operand<Float> inputMax)
Factory method to create a class wrapping a new RequantizationRange operation.
|
Output<Float> |
outputMax()
the computed max output.
|
Output<Float> |
outputMin()
The computed min output.
|
equals, hashCode, op, toString
public static <T> RequantizationRange create(Scope scope, Operand<T> input, Operand<Float> inputMin, Operand<Float> inputMax)
scope
- current scopeinput
- inputMin
- The float value that the minimum quantized input value represents.inputMax
- The float value that the maximum quantized input value represents.Copyright © 2022. All rights reserved.