RequantizationRange

public final class RequantizationRange

Computes a range that covers the actual values present in a quantized tensor.

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`.

Constants

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

Public Methods

static RequantizationRange
create ( Scope scope, Operand <? extends TType > input, Operand < TFloat32 > inputMin, Operand < TFloat32 > inputMax)
Factory method to create a class wrapping a new RequantizationRange operation.
Output < TFloat32 >
outputMax ()
the computed max output.
Output < TFloat32 >
outputMin ()
The computed min output.

Inherited Methods

Constants

public static final String OP_NAME

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

Constant Value: "RequantizationRange"

Public Methods

public static RequantizationRange create ( Scope scope, Operand <? extends TType > input, Operand < TFloat32 > inputMin, Operand < TFloat32 > inputMax)

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

Parameters
scope current scope
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

public Output < TFloat32 > outputMax ()

the computed max output.

public Output < TFloat32 > outputMin ()

The computed min output.