Package org.tensorflow.op.quantization

Class RequantizationRange

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.quantization.RequantizationRange

All Implemented Interfaces:

Op

@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.

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method	Description
static <T> RequantizationRange	create(Scope scope, Operand<T> input, Operand<java.lang.Float> inputMin, Operand<java.lang.Float> inputMax)	Factory method to create a class to wrap a new RequantizationRange operation to the graph.
Output<java.lang.Float>	outputMax()	the computed max output.
Output<java.lang.Float>	outputMin()	The computed min output.

Methods inherited from class java.lang.Object

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

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Method Detail

create

public static <T> RequantizationRange create(Scope scope,
                                             Operand<T> input,
                                             Operand<java.lang.Float> inputMin,
                                             Operand<java.lang.Float> inputMax)

Factory method to create a class to wrap a new RequantizationRange operation to the graph.

Parameters:

scope - current graph scope

input -

inputMin - The float value that the minimum quantized input value represents.

inputMax - The float value that the maximum quantized input value represents.

Returns:

a new instance of RequantizationRange

outputMin

public Output<java.lang.Float> outputMin()

The computed min output.

outputMax

public Output<java.lang.Float> outputMax()

the computed max output.