OptimizerOptions Struct Reference

#include <INetwork.hpp>

Public Member Functions
	OptimizerOptions ()
	OptimizerOptions (bool reduceFp32ToFp16, bool debug, bool reduceFp32ToBf16, bool importEnabled, ModelOptions modelOptions={})
	OptimizerOptions (bool reduceFp32ToFp16, bool debug, bool reduceFp32ToBf16=false, ShapeInferenceMethod shapeInferenceMethod=armnn::ShapeInferenceMethod::ValidateOnly, bool importEnabled=false, ModelOptions modelOptions={})

Public Attributes
bool	m_ReduceFp32ToFp16
bool	m_Debug
bool	m_ReduceFp32ToBf16
ShapeInferenceMethod	m_shapeInferenceMethod
bool	m_ImportEnabled
ModelOptions	m_ModelOptions

Detailed Description

Definition at line 616 of file INetwork.hpp.

Constructor & Destructor Documentation

OptimizerOptions() [1/3]

OptimizerOptions ( )

inline

Definition at line 618 of file INetwork.hpp.

        : m_ReduceFp32ToFp16(false)
        , m_Debug(false)
        , m_ReduceFp32ToBf16(false)
        , m_shapeInferenceMethod(armnn::ShapeInferenceMethod::ValidateOnly)
        , m_ImportEnabled(false)
        , m_ModelOptions()
    {}

OptimizerOptions() [2/3]

OptimizerOptions ( bool  reduceFp32ToFp16, bool  debug, bool  reduceFp32ToBf16, bool  importEnabled, ModelOptions  modelOptions = {}  )

inline

Definition at line 627 of file INetwork.hpp.

References armnn::ValidateOnly.

                                    {})
        : m_ReduceFp32ToFp16(reduceFp32ToFp16)
        , m_Debug(debug)
        , m_ReduceFp32ToBf16(reduceFp32ToBf16)
        , m_shapeInferenceMethod(armnn::ShapeInferenceMethod::ValidateOnly)
        , m_ImportEnabled(importEnabled)
        , m_ModelOptions(modelOptions)
    {
        if (m_ReduceFp32ToFp16 && m_ReduceFp32ToBf16)
        {
            throw InvalidArgumentException("BFloat16 and Float16 optimization cannot be enabled at the same time.");
        }
    }

OptimizerOptions() [3/3]

OptimizerOptions ( bool  reduceFp32ToFp16, bool  debug, bool  reduceFp32ToBf16 = false, ShapeInferenceMethod  shapeInferenceMethod = armnn::ShapeInferenceMethod::ValidateOnly, bool  importEnabled = false, ModelOptions  modelOptions = {}  )

inline

Definition at line 642 of file INetwork.hpp.

                                                                             {})
        : m_ReduceFp32ToFp16(reduceFp32ToFp16)
        , m_Debug(debug)
        , m_ReduceFp32ToBf16(reduceFp32ToBf16)
        , m_shapeInferenceMethod(shapeInferenceMethod)
        , m_ImportEnabled(importEnabled)
        , m_ModelOptions(modelOptions)
    {
        if (m_ReduceFp32ToFp16 && m_ReduceFp32ToBf16)
        {
            throw InvalidArgumentException("BFloat16 and Float16 optimization cannot be enabled at the same time.");
        }
    }

Member Data Documentation

m_Debug

bool m_Debug

Definition at line 662 of file INetwork.hpp.

Referenced by BOOST_AUTO_TEST_CASE(), InferenceModel< IParser, TDataType >::InferenceModel(), and armnn::Optimize().

m_ImportEnabled

bool m_ImportEnabled

Definition at line 671 of file INetwork.hpp.

Referenced by BOOST_AUTO_TEST_CASE(), and armnn::Optimize().

m_ModelOptions

ModelOptions m_ModelOptions

Definition at line 674 of file INetwork.hpp.

Referenced by BOOST_AUTO_TEST_CASE(), InferenceModel< IParser, TDataType >::InferenceModel(), and armnn::Optimize().

m_ReduceFp32ToBf16

bool m_ReduceFp32ToBf16

Definition at line 665 of file INetwork.hpp.

Referenced by InferenceModel< IParser, TDataType >::InferenceModel(), and armnn::Optimize().

m_ReduceFp32ToFp16

bool m_ReduceFp32ToFp16

Definition at line 659 of file INetwork.hpp.

Referenced by BOOST_AUTO_TEST_CASE(), InferenceModel< IParser, TDataType >::InferenceModel(), and armnn::Optimize().

m_shapeInferenceMethod

ShapeInferenceMethod m_shapeInferenceMethod

Definition at line 668 of file INetwork.hpp.

---

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

• include/armnn/INetwork.hpp