Execution settings for a Deep Learning tool. More...

#include <eVision/Easy/EasyDeepLearning/EDeepLearningExecutionSettings.h>

Collaboration diagram for eVision::EasyDeepLearning::EDeepLearningExecutionSettings:

Public Member Functions
	EDeepLearningExecutionSettings ()
	Constructs a EDeepLearningExecutionSettings.
	EDeepLearningExecutionSettings (const eVision::EasyDeepLearning::EDeepLearningExecutionSettings &other)
	Copy constructor.
virtual	~EDeepLearningExecutionSettings () throw ()
eVision::EasyDeepLearning::EDeepLearningExecutionSettings &	operator= (const eVision::EasyDeepLearning::EDeepLearningExecutionSettings &other)
	Assignment operator.
bool	operator== (const eVision::EasyDeepLearning::EDeepLearningExecutionSettings &other) const
	Comparison operator.
bool	operator!= (const eVision::EasyDeepLearning::EDeepLearningExecutionSettings &other) const
	Inequality operator.
void	CopyTo (eVision::EasyDeepLearning::EDeepLearningExecutionSettings &other) const
	Copy the object to another one.
virtual void	Load (const std::string &filePath)
	Loads the EDeepLearningExecutionSettings. The given ESerializer must have been created for reading.
virtual void	Load (eVision::ESerializer *serializer)
	Loads the EDeepLearningExecutionSettings. The given ESerializer must have been created for reading.
virtual void	Save (const std::string &filePath)
	Saves the EDeepLearningExecutionSettings. The given ESerializer must have been created for writing.
virtual void	Save (eVision::ESerializer *serializer)
	Saves the EDeepLearningExecutionSettings. The given ESerializer must have been created for writing.
void	SetEngine (const std::string &engine)
	Engine with which to execute or train the neural network.
std::string	GetEngine () const
	Engine with which to execute or train the neural network.
eVision::EasyDeepLearning::EDeepLearningInferencePrecision	GetInferencePrecision () const
	Inference precision.
void	SetInferencePrecision (eVision::EasyDeepLearning::EDeepLearningInferencePrecision prec)
	Inference precision.
int	GetNumAvailableDevices () const
	Available devices for the current EDeepLearningExecutionSettings::SetEngine.
std::string	GetAvailableDeviceName (int i) const
	Name of the i-th device of the current engine.
eVision::EasyDeepLearning::EDeepLearningDevice	GetAvailableDevice (int i) const
	Gets the i-th EDeepLearningDevice of the current engine.
std::vector< eVision::EasyDeepLearning::EDeepLearningDevice >	GetAvailableDevices () const
	Get all available device for the current engine.
int	GetNumDevices () const
	Number of devices configured in this execution context.
void	SetDevice (const eVision::EasyDeepLearning::EDeepLearningDevice &device)
	Sets the device with which to run or train the model.
eVision::EasyDeepLearning::EDeepLearningDevice	GetDevice (int i) const
	Gets an active device. By default, it returns the first active device.
eVision::EasyDeepLearning::EDeepLearningDevice	GetDevice () const
	Gets an active device. By default, it returns the first active device.
void	SetDeviceByName (const std::string &name)
	Sets the device with which to run the model using its name.
void	SetDeviceById (int id)
	Sets the device with which to run the model using its index in the list returned by EDeepLearningExecutionSettings::GetAvailableDevices.
std::vector< eVision::EasyDeepLearning::EDeepLearningDevice >	GetDevices () const
	Devices with which to run or train the model.
void	SetDevices (const std::vector< eVision::EasyDeepLearning::EDeepLearningDevice > &devices)
	Devices with which to run or train the model.
void	SetBatchSize (int32_t batchSize)
	Batch size. The batch size is the number of images that are processed together during training and batch inference.
int32_t	GetBatchSize () const
	Batch size. The batch size is the number of images that are processed together during training and batch inference.
bool	GetOptimizeBatchSize () const
	Indicates whether to optimize the batch size (see EDeepLearningExecutionSettings::SetBatchSize) to maximize the training and inference speed according to the engine, device and the available memory.
void	SetOptimizeBatchSize (bool optimize)
	Indicates whether to optimize the batch size (see EDeepLearningExecutionSettings::SetBatchSize) to maximize the training and inference speed according to the engine, device and the available memory.
	EDeepLearningExecutionSettings (CppWrapperInternal::InternalConstructor)

Static Public Member Functions
static int	GetNumAvailableEngines ()
	Number of available engines.
static std::string	GetAvailableEngineName (int id)
	Gets the name of the engine given its id.
static std::vector< std::string >	GetAvailableEngines ()
	Available engines.
static std::vector< eVision::EasyDeepLearning::EDeepLearningDevice >	GetAvailableDevicesForEngine (const std::string &engine)
	Available devices for the specified engine.

Public Attributes
CppWrapperInternal::WrappedClass	wrappedClass_

Detailed Description

Execution settings for a Deep Learning tool.

License(s): BasicTypes

Constructor & Destructor Documentation

◆ EDeepLearningExecutionSettings() [1/3]

eVision::EasyDeepLearning::EDeepLearningExecutionSettings::EDeepLearningExecutionSettings ( )

Constructs a EDeepLearningExecutionSettings.

◆ EDeepLearningExecutionSettings() [2/3]

eVision::EasyDeepLearning::EDeepLearningExecutionSettings::EDeepLearningExecutionSettings ( const eVision::EasyDeepLearning::EDeepLearningExecutionSettings & other )

Copy constructor.

Parameters

other The other EDeepLearningExecutionSettings that we will copy into this one.

◆ ~EDeepLearningExecutionSettings()

eVision::EasyDeepLearning::EDeepLearningExecutionSettings::~EDeepLearningExecutionSettings	(		)
throw	(	)

virtual

◆ EDeepLearningExecutionSettings() [3/3]

eVision::EasyDeepLearning::EDeepLearningExecutionSettings::EDeepLearningExecutionSettings ( CppWrapperInternal::InternalConstructor )

Member Function Documentation

◆ CopyTo()

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::CopyTo ( eVision::EasyDeepLearning::EDeepLearningExecutionSettings & other ) const

Copy the object to another one.

Parameters

other The other EDeepLearningExecutionSettings that we will copy this one into.

◆ GetAvailableDevice()

eVision::EasyDeepLearning::EDeepLearningDevice eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetAvailableDevice ( int i ) const

Gets the i-th EDeepLearningDevice of the current engine.

Parameters

i	Index of the device between 0 and EDeepLearningExecutionSettings::GetNumAvailableDevices - 1.

◆ GetAvailableDeviceName()

std::string eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetAvailableDeviceName ( int i ) const

Name of the i-th device of the current engine.

Parameters

i	Index of the device between 0 and EDeepLearningExecutionSettings::GetNumAvailableDevices - 1.

◆ GetAvailableDevices()

std::vector< eVision::EasyDeepLearning::EDeepLearningDevice > eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetAvailableDevices ( ) const

Get all available device for the current engine.

◆ GetAvailableDevicesForEngine()

std::vector< eVision::EasyDeepLearning::EDeepLearningDevice > eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetAvailableDevicesForEngine ( const std::string & engine )

static

Available devices for the specified engine.

Parameters

engine Engine for which to get the devices

◆ GetAvailableEngineName()

std::string eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetAvailableEngineName ( int id )

static

Gets the name of the engine given its id.

Parameters

id	Index of the available engine between 0 and EDeepLearningExecutionSettings::GetNumAvailableEngines - 1.

◆ GetAvailableEngines()

std::vector< std::string > eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetAvailableEngines ( )

static

Available engines.

◆ GetBatchSize()

int32_t eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetBatchSize ( ) const

Batch size. The batch size is the number of images that are processed together during training and batch inference.

When using multi-GPUs processing, the batch size is the number of images that each GPU will process at once.

A large batch size will increase the processing speed on GPU but also the memory requirements.

The batch size must be bigger or equal to 1 and it is commonly chosen to be a power of 2.

If EDeepLearningExecutionSettings::GetOptimizeBatchSize is 'true', then the value of this property will not be taken into account because it will be optimized automatically for training or inference according to the situation.

◆ GetDevice() [1/2]

eVision::EasyDeepLearning::EDeepLearningDevice eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetDevice ( ) const

Gets an active device. By default, it returns the first active device.

◆ GetDevice() [2/2]

eVision::EasyDeepLearning::EDeepLearningDevice eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetDevice ( int i ) const

Gets an active device. By default, it returns the first active device.

Parameters

i	Index of the active devices between 0 and EDeepLearningExecutionSettings::GetNumDevices.

◆ GetDevices()

std::vector< eVision::EasyDeepLearning::EDeepLearningDevice > eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetDevices ( ) const

Devices with which to run or train the model.

Using multiple GPUs is only supported by the default engine.

If the specified devices don't support the current EDeepLearningExecutionSettings::GetInferencePrecision, it will be set to EDeepLearningDevice::GetDefaultPrecision.

◆ GetEngine()

std::string eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetEngine ( ) const

Engine with which to execute or train the neural network.

◆ GetInferencePrecision()

eVision::EasyDeepLearning::EDeepLearningInferencePrecision eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetInferencePrecision ( ) const

Inference precision.

Use EDeepLearningDevice::IsPrecisionSupported to check whether a device support the given precision.

◆ GetNumAvailableDevices()

int eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetNumAvailableDevices ( ) const

Available devices for the current EDeepLearningExecutionSettings::SetEngine.

◆ GetNumAvailableEngines()

int eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetNumAvailableEngines ( )

static

Number of available engines.

◆ GetNumDevices()

int eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetNumDevices ( ) const

Number of devices configured in this execution context.

◆ GetOptimizeBatchSize()

bool eVision::EasyDeepLearning::EDeepLearningExecutionSettings::GetOptimizeBatchSize ( ) const

Indicates whether to optimize the batch size (see EDeepLearningExecutionSettings::SetBatchSize) to maximize the training and inference speed according to the engine, device and the available memory.

Default value is true.

◆ Load() [1/2]

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::Load ( const std::string & filePath )

virtual

Loads the EDeepLearningExecutionSettings. The given ESerializer must have been created for reading.

Parameters

filePath File path.

Loading a EDeepLearningExecutionSettings can trigger exceptions if the engine and/or device is not available on the machine.

◆ Load() [2/2]

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::Load ( eVision::ESerializer * serializer )

virtual

Loads the EDeepLearningExecutionSettings. The given ESerializer must have been created for reading.

Parameters

serializer Pointer to the ESerializer created for reading.

Loading a EDeepLearningExecutionSettings can trigger exceptions if the engine and/or device is not available on the machine.

◆ operator!=()

bool eVision::EasyDeepLearning::EDeepLearningExecutionSettings::operator!= ( const eVision::EasyDeepLearning::EDeepLearningExecutionSettings & other ) const

Inequality operator.

Parameters

other Other execution settings

◆ operator=()

eVision::EasyDeepLearning::EDeepLearningExecutionSettings & eVision::EasyDeepLearning::EDeepLearningExecutionSettings::operator= ( const eVision::EasyDeepLearning::EDeepLearningExecutionSettings & other )

Assignment operator.

Parameters

other The other EDeepLearningExecutionSettings that we will copy into this one.

◆ operator==()

bool eVision::EasyDeepLearning::EDeepLearningExecutionSettings::operator== ( const eVision::EasyDeepLearning::EDeepLearningExecutionSettings & other ) const

Comparison operator.

Parameters

other Other execution settings

◆ Save() [1/2]

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::Save ( const std::string & filePath )

virtual

Saves the EDeepLearningExecutionSettings. The given ESerializer must have been created for writing.

Parameters

filePath File path.

◆ Save() [2/2]

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::Save ( eVision::ESerializer * serializer )

virtual

Saves the EDeepLearningExecutionSettings. The given ESerializer must have been created for writing.

Parameters

serializer Pointer to the ESerializer created for writing.

◆ SetBatchSize()

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::SetBatchSize ( int32_t batchSize )

Batch size. The batch size is the number of images that are processed together during training and batch inference.

When using multi-GPUs processing, the batch size is the number of images that each GPU will process at once.

A large batch size will increase the processing speed on GPU but also the memory requirements.

The batch size must be bigger or equal to 1 and it is commonly chosen to be a power of 2.

Parameters

batchSize Size of the batch

If EDeepLearningExecutionSettings::GetOptimizeBatchSize is 'true', then the value of this property will not be taken into account because it will be optimized automatically for training or inference according to the situation.

◆ SetDevice()

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::SetDevice ( const eVision::EasyDeepLearning::EDeepLearningDevice & device )

Sets the device with which to run or train the model.

Parameters

device Device

For CPU device, the number of thread is initialized from Easy::SetMaxNumberOfProcessingThreads.

If the specified device does support the current EDeepLearningExecutionSettings::GetInferencePrecision, it will be set to EDeepLearningDevice::GetDefaultPrecision.

◆ SetDeviceById()

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::SetDeviceById ( int id )

Sets the device with which to run the model using its index in the list returned by EDeepLearningExecutionSettings::GetAvailableDevices.

◆ SetDeviceByName()

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::SetDeviceByName ( const std::string & name )

Sets the device with which to run the model using its name.

◆ SetDevices()

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::SetDevices ( const std::vector< eVision::EasyDeepLearning::EDeepLearningDevice > & devices )

Devices with which to run or train the model.

Using multiple GPUs is only supported by the default engine.

Parameters

devices Device

If the specified devices don't support the current EDeepLearningExecutionSettings::GetInferencePrecision, it will be set to EDeepLearningDevice::GetDefaultPrecision.

◆ SetEngine()

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::SetEngine ( const std::string & engine )

Engine with which to execute or train the neural network.

◆ SetInferencePrecision()

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::SetInferencePrecision ( eVision::EasyDeepLearning::EDeepLearningInferencePrecision prec )

Inference precision.

Use EDeepLearningDevice::IsPrecisionSupported to check whether a device support the given precision.

◆ SetOptimizeBatchSize()

void eVision::EasyDeepLearning::EDeepLearningExecutionSettings::SetOptimizeBatchSize ( bool optimize )

Indicates whether to optimize the batch size (see EDeepLearningExecutionSettings::SetBatchSize) to maximize the training and inference speed according to the engine, device and the available memory.

Default value is true.

Member Data Documentation

◆ wrappedClass_

CppWrapperInternal::WrappedClass eVision::EasyDeepLearning::EDeepLearningExecutionSettings::wrappedClass_

Public Member Functions

Static Public Member Functions

Public Attributes

Detailed Description

Constructor & Destructor Documentation

◆ EDeepLearningExecutionSettings() [1/3]

◆ EDeepLearningExecutionSettings() [2/3]

◆ ~EDeepLearningExecutionSettings()

◆ EDeepLearningExecutionSettings() [3/3]

Member Function Documentation

◆ CopyTo()

◆ GetAvailableDevice()

◆ GetAvailableDeviceName()

◆ GetAvailableDevices()

◆ GetAvailableDevicesForEngine()

◆ GetAvailableEngineName()

◆ GetAvailableEngines()

◆ GetBatchSize()

◆ GetDevice() [1/2]

◆ GetDevice() [2/2]

◆ GetDevices()

◆ GetEngine()

◆ GetInferencePrecision()

◆ GetNumAvailableDevices()

◆ GetNumAvailableEngines()

◆ GetNumDevices()

◆ GetOptimizeBatchSize()

◆ Load() [1/2]

◆ Load() [2/2]

◆ operator!=()

◆ operator=()

◆ operator==()

◆ Save() [1/2]

◆ Save() [2/2]

◆ SetBatchSize()

◆ SetDevice()

◆ SetDeviceById()

◆ SetDeviceByName()

◆ SetDevices()

◆ SetEngine()

◆ SetInferencePrecision()

◆ SetOptimizeBatchSize()

Member Data Documentation

◆ wrappedClass_