ONE - On-device Neural Engine
Loading...
Searching...
No Matches
mir::AffineQuantization Class Reference

#include <Quantization.h>

Public Member Functions

 AffineQuantization ()=default
 
 AffineQuantization (float scale, int zero_point)
 
float getScale () const
 
int getZeroPoint () const
 
bool empty () const
 

Detailed Description

Definition at line 23 of file Quantization.h.

Constructor & Destructor Documentation

◆ AffineQuantization() [1/2]

mir::AffineQuantization::AffineQuantization ( )
default

◆ AffineQuantization() [2/2]

mir::AffineQuantization::AffineQuantization ( float  scale,
int  zero_point 
)
inline

Definition at line 28 of file Quantization.h.

29 : _scale(scale), _zero_point(zero_point), _empty(false)
30 {
31 }

Member Function Documentation

◆ empty()

bool mir::AffineQuantization::empty ( ) const
inline

Definition at line 37 of file Quantization.h.

37{ return _empty; }

Referenced by mir::TensorType::isQuantized().

◆ getScale()

float mir::AffineQuantization::getScale ( ) const
inline

Definition at line 33 of file Quantization.h.

33{ return _scale; }

Referenced by mir_interpreter::Dequantize().

◆ getZeroPoint()

int mir::AffineQuantization::getZeroPoint ( ) const
inline

Definition at line 35 of file Quantization.h.

35{ return _zero_point; }

Referenced by mir_interpreter::Dequantize().


The documentation for this class was generated from the following file: