ArmNN
 24.02
SelectiveQuantizer< T, DoQuantize > Struct Template Reference

#include <QuantizeHelper.hpp>

Static Public Member Functions

static T Quantize (float value, float scale, int32_t offset)
 
static float Dequantize (T value, float scale, int32_t offset)
 

Detailed Description

template<typename T, bool DoQuantize = true>
struct armnnUtils::SelectiveQuantizer< T, DoQuantize >

Definition at line 23 of file QuantizeHelper.hpp.

Member Function Documentation

◆ Dequantize()

static float Dequantize ( value,
float  scale,
int32_t  offset 
)
inlinestatic

Definition at line 30 of file QuantizeHelper.hpp.

31  {
32  return armnn::Dequantize(value, scale, offset);
33  }

References armnn::Dequantize().

◆ Quantize()

static T Quantize ( float  value,
float  scale,
int32_t  offset 
)
inlinestatic

Definition at line 25 of file QuantizeHelper.hpp.

26  {
27  return armnn::Quantize<T>(value, scale, offset);
28  }

The documentation for this struct was generated from the following file:
armnn::Dequantize
float Dequantize(QuantizedType value, float scale, int32_t offset)
Dequantize an 8-bit data type into a floating point data type.
Definition: TypesUtils.cpp:52