ArmNN
 24.08
QSymmS8Encoder Class Reference

#include <BaseIterator.hpp>

Inheritance diagram for QSymmS8Encoder:
[legend]
Collaboration diagram for QSymmS8Encoder:
[legend]

Public Member Functions

 QSymmS8Encoder (int8_t *data, const float scale, const int32_t offset)
 
 QSymmS8Encoder (const float scale, const int32_t offset)
 
void Set (float right) override
 
float Get () const override
 
- Public Member Functions inherited from TypedIterator< int8_t, Encoder< float > >
 TypedIterator (int8_t *data=nullptr)
 
void Reset (void *data) override
 
TypedIteratoroperator++ () override
 
TypedIteratoroperator+= (const unsigned int increment) override
 
TypedIteratoroperator-= (const unsigned int increment) override
 
TypedIteratoroperator[] (const unsigned int index) override
 
- Public Member Functions inherited from Encoder< float >
 Encoder ()
 
virtual ~Encoder ()
 
virtual float Get () const=0
 
- Public Member Functions inherited from BaseIterator
 BaseIterator ()
 
virtual ~BaseIterator ()
 

Additional Inherited Members

- Protected Attributes inherited from TypedIterator< int8_t, Encoder< float > >
int8_t * m_Iterator
 
int8_t * m_Start
 

Detailed Description

Definition at line 534 of file BaseIterator.hpp.

Constructor & Destructor Documentation

◆ QSymmS8Encoder() [1/2]

QSymmS8Encoder ( int8_t *  data,
const float  scale,
const int32_t  offset 
)
inline

Definition at line 537 of file BaseIterator.hpp.

538  : TypedIterator(data), m_Scale(scale), m_Offset(offset) {}

◆ QSymmS8Encoder() [2/2]

QSymmS8Encoder ( const float  scale,
const int32_t  offset 
)
inline

Definition at line 540 of file BaseIterator.hpp.

541  : QSymmS8Encoder(nullptr, scale, offset) {}

Member Function Documentation

◆ Get()

float Get ( ) const
inlineoverride

Definition at line 548 of file BaseIterator.hpp.

549  {
550  return armnn::Dequantize(*m_Iterator, m_Scale, m_Offset);
551  }

References armnn::Dequantize(), and TypedIterator< int8_t, Encoder< float > >::m_Iterator.

◆ Set()

void Set ( float  right)
inlineoverridevirtual

Implements Encoder< float >.

Definition at line 543 of file BaseIterator.hpp.

544  {
545  *m_Iterator = armnn::Quantize<int8_t>(right, m_Scale, m_Offset);
546  }

References TypedIterator< int8_t, Encoder< float > >::m_Iterator.


The documentation for this class was generated from the following file:
armnn::TypedIterator< int8_t, Encoder< float > >::m_Iterator
int8_t * m_Iterator
Definition: BaseIterator.hpp:107
armnn::QSymmS8Encoder::QSymmS8Encoder
QSymmS8Encoder(int8_t *data, const float scale, const int32_t offset)
Definition: BaseIterator.hpp:537
armnn::TypedIterator< int8_t, Encoder< float > >::TypedIterator
TypedIterator(int8_t *data=nullptr)
Definition: BaseIterator.hpp:68
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:48