eVision.EasyDeepLearning.EDeepLearningExecutionSettings Class Reference

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

Public Member Functions
None	__init__ (self)
	Constructs a eVision.EasyDeepLearning.EDeepLearningExecutionSettings.
None	__init__ (self, eVision.EasyDeepLearning.EDeepLearningExecutionSettings other)
	Copy constructor.
None	CopyTo (self, eVision.EasyDeepLearning.EDeepLearningExecutionSettings other)
	Copy the object to another one.
None	Load (self, str filePath)
	Loads the eVision.EasyDeepLearning.EDeepLearningExecutionSettings.
None	Load (self, eVision.ESerializer|None serializer)
	Loads the eVision.EasyDeepLearning.EDeepLearningExecutionSettings.
None	Save (self, str filePath)
	Saves the eVision.EasyDeepLearning.EDeepLearningExecutionSettings.
None	Save (self, eVision.ESerializer|None serializer)
	Saves the eVision.EasyDeepLearning.EDeepLearningExecutionSettings.
str	GetAvailableDeviceName (self, int i)
	Name of the i-th device of the current engine.
eVision.EasyDeepLearning.EDeepLearningDevice	GetAvailableDevice (self, int i)
	Gets the i-th eVision.EasyDeepLearning.EDeepLearningDevice of the current engine.
None	SetDevice (self, eVision.EasyDeepLearning.EDeepLearningDevice device)
	Sets the device with which to run or train the model.
eVision.EasyDeepLearning.EDeepLearningDevice	GetDevice (self, int i)
	Gets an active device.
eVision.EasyDeepLearning.EDeepLearningDevice	GetDevice (self)
	Gets an active device.

Static Public Member Functions
int	GetNumAvailableEngines ()
	Number of available engines.
str	GetAvailableEngineName (int id)
	Gets the name of the engine given its id.
list[str]	GetAvailableEngines ()
	Available engines.
list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice]	GetAvailableDevicesForEngine (str engine)
	Available devices for the specified engine.

Protected Member Functions
str	_Engine__getter (self)
	\cond
	_Engine__setter (self, str value)
	Engine with which to execute or train the neural network.
eVision.EasyDeepLearning.EDeepLearningInferencePrecision	_InferencePrecision__getter (self)
	\cond
	_InferencePrecision__setter (self, eVision.EasyDeepLearning.EDeepLearningInferencePrecision value)
	Inference precision.
int	_NumAvailableDevices__getter (self)
	\cond
list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice]	_AvailableDevices__getter (self)
	\cond
int	_NumDevices__getter (self)
	\cond
	_DeviceByName__setter (self, str value)
	\cond
	_DeviceById__setter (self, int value)
	\cond
list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice]	_Devices__getter (self)
	\cond
	_Devices__setter (self, list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice] value)
	Devices with which to run or train the model.
int	_BatchSize__getter (self)
	\cond
	_BatchSize__setter (self, int value)
	Batch size.
bool	_OptimizeBatchSize__getter (self)
	\cond
	_OptimizeBatchSize__setter (self, bool value)
	Indicates whether to optimize the batch size (see eVision.EasyDeepLearning.EDeepLearningExecutionSettings.BatchSize) to maximize the training and inference speed according to the engine, device and the available memory.

Properties
	Engine = property(_Engine__getter, _Engine__setter)
	\endcond
	InferencePrecision = property(_InferencePrecision__getter, _InferencePrecision__setter)
	\endcond
	NumAvailableDevices = property(_NumAvailableDevices__getter, None)
	\endcond
	AvailableDevices = property(_AvailableDevices__getter, None)
	\endcond
	NumDevices = property(_NumDevices__getter, None)
	\endcond
	DeviceByName = property(None, _DeviceByName__setter)
	\endcond
	DeviceById = property(None, _DeviceById__setter)
	\endcond
	Devices = property(_Devices__getter, _Devices__setter)
	\endcond
	BatchSize = property(_BatchSize__getter, _BatchSize__setter)
	\endcond
	OptimizeBatchSize = property(_OptimizeBatchSize__getter, _OptimizeBatchSize__setter)
	\endcond

Detailed Description

Execution settings for a Deep Learning tool.

Remarks:

License(s): BasicTypes

Constructor & Destructor Documentation

__init__() [1/2]

None eVision.EasyDeepLearning.EDeepLearningExecutionSettings.__init__

(

self

)

Constructs a eVision.EasyDeepLearning.EDeepLearningExecutionSettings.

__init__() [2/2]

None eVision.EasyDeepLearning.EDeepLearningExecutionSettings.__init__	(		self,
		eVision.EasyDeepLearning.EDeepLearningExecutionSettings	other )

Copy constructor.

Parameters

other

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

Member Function Documentation

_AvailableDevices__getter()

list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice] eVision.EasyDeepLearning.EDeepLearningExecutionSettings._AvailableDevices__getter ( self )

protected

\cond

Get all available device for the current engine.

_BatchSize__getter()

int eVision.EasyDeepLearning.EDeepLearningExecutionSettings._BatchSize__getter ( self )

protected

\cond

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.

Remarks:

If eVision.EasyDeepLearning.EDeepLearningExecutionSettings.OptimizeBatchSize 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.

_BatchSize__setter()

eVision.EasyDeepLearning.EDeepLearningExecutionSettings._BatchSize__setter ( self, int value )

protected

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.

Remarks:

If eVision.EasyDeepLearning.EDeepLearningExecutionSettings.OptimizeBatchSize 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.

_DeviceById__setter()

eVision.EasyDeepLearning.EDeepLearningExecutionSettings._DeviceById__setter ( self, int value )

protected

\cond

Sets the device with which to run the model using its index in the list returned by eVision.EasyDeepLearning.EDeepLearningExecutionSettings.AvailableDevices.

_DeviceByName__setter()

eVision.EasyDeepLearning.EDeepLearningExecutionSettings._DeviceByName__setter ( self, str value )

protected

\cond

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

_Devices__getter()

list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice] eVision.EasyDeepLearning.EDeepLearningExecutionSettings._Devices__getter ( self )

protected

\cond

Devices with which to run or train the model.

Using multiple GPUs is only supported by the default engine.

Remarks:

If the specified devices don't support the current eVision.EasyDeepLearning.EDeepLearningExecutionSettings.InferencePrecision, it will be set to eVision.EasyDeepLearning.EDeepLearningDevice.DefaultPrecision.

_Devices__setter()

eVision.EasyDeepLearning.EDeepLearningExecutionSettings._Devices__setter ( self, list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice] value )

protected

Devices with which to run or train the model.

Using multiple GPUs is only supported by the default engine.

Remarks:

If the specified devices don't support the current eVision.EasyDeepLearning.EDeepLearningExecutionSettings.InferencePrecision, it will be set to eVision.EasyDeepLearning.EDeepLearningDevice.DefaultPrecision.

_Engine__getter()

str eVision.EasyDeepLearning.EDeepLearningExecutionSettings._Engine__getter ( self )

protected

\cond

Engine with which to execute or train the neural network.

_Engine__setter()

eVision.EasyDeepLearning.EDeepLearningExecutionSettings._Engine__setter ( self, str value )

protected

Engine with which to execute or train the neural network.

_InferencePrecision__getter()

eVision.EasyDeepLearning.EDeepLearningInferencePrecision eVision.EasyDeepLearning.EDeepLearningExecutionSettings._InferencePrecision__getter ( self )

protected

\cond

Inference precision.

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

_InferencePrecision__setter()

eVision.EasyDeepLearning.EDeepLearningExecutionSettings._InferencePrecision__setter ( self, eVision.EasyDeepLearning.EDeepLearningInferencePrecision value )

protected

Inference precision.

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

_NumAvailableDevices__getter()

int eVision.EasyDeepLearning.EDeepLearningExecutionSettings._NumAvailableDevices__getter ( self )

protected

\cond

Available devices for the current eVision.EasyDeepLearning.EDeepLearningExecutionSettings.Engine.

_NumDevices__getter()

int eVision.EasyDeepLearning.EDeepLearningExecutionSettings._NumDevices__getter ( self )

protected

\cond

Number of devices configured in this execution context.

_OptimizeBatchSize__getter()

bool eVision.EasyDeepLearning.EDeepLearningExecutionSettings._OptimizeBatchSize__getter ( self )

protected

\cond

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

Default value is true.

_OptimizeBatchSize__setter()

eVision.EasyDeepLearning.EDeepLearningExecutionSettings._OptimizeBatchSize__setter ( self, bool value )

protected

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

Default value is true.

CopyTo()

None eVision.EasyDeepLearning.EDeepLearningExecutionSettings.CopyTo	(		self,
		eVision.EasyDeepLearning.EDeepLearningExecutionSettings	other )

Copy the object to another one.

Parameters

other

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

GetAvailableDevice()

eVision.EasyDeepLearning.EDeepLearningDevice eVision.EasyDeepLearning.EDeepLearningExecutionSettings.GetAvailableDevice	(		self,
		int	i )

Gets the i-th eVision.EasyDeepLearning.EDeepLearningDevice of the current engine.

Parameters

i	Index of the device between 0 and eVision.EasyDeepLearning.EDeepLearningExecutionSettings.NumAvailableDevices - 1.

GetAvailableDeviceName()

str eVision.EasyDeepLearning.EDeepLearningExecutionSettings.GetAvailableDeviceName	(		self,
		int	i )

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

Parameters

i	Index of the device between 0 and eVision.EasyDeepLearning.EDeepLearningExecutionSettings.NumAvailableDevices - 1.

GetAvailableDevicesForEngine()

list[eVision._eVision.EasyDeepLearning.EDeepLearningDevice] eVision.EasyDeepLearning.EDeepLearningExecutionSettings.GetAvailableDevicesForEngine ( str engine )

static

Available devices for the specified engine.

Parameters

engine

Engine for which to get the devices

GetAvailableEngineName()

str 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 eVision.EasyDeepLearning.EDeepLearningExecutionSettings.GetNumAvailableEngines - 1.

GetAvailableEngines()

list[str] eVision.EasyDeepLearning.EDeepLearningExecutionSettings.GetAvailableEngines ( )

static

Available engines.

GetDevice() [1/2]

eVision.EasyDeepLearning.EDeepLearningDevice eVision.EasyDeepLearning.EDeepLearningExecutionSettings.GetDevice

(

self

)

Gets an active device.

By default, it returns the first active device.

GetDevice() [2/2]

eVision.EasyDeepLearning.EDeepLearningDevice eVision.EasyDeepLearning.EDeepLearningExecutionSettings.GetDevice	(		self,
		int	i )

Gets an active device.

By default, it returns the first active device.

Parameters

i	Index of the active devices between 0 and eVision.EasyDeepLearning.EDeepLearningExecutionSettings.NumDevices.

GetNumAvailableEngines()

int eVision.EasyDeepLearning.EDeepLearningExecutionSettings.GetNumAvailableEngines ( )

static

Number of available engines.

Load() [1/2]

None eVision.EasyDeepLearning.EDeepLearningExecutionSettings.Load	(		self,
		eVision.ESerializer | None	serializer )

Loads the eVision.EasyDeepLearning.EDeepLearningExecutionSettings.

The given eVision.ESerializer must have been created for reading.

Remarks:

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

Parameters

serializer

Pointer to the eVision.ESerializer created for reading.

Load() [2/2]

None eVision.EasyDeepLearning.EDeepLearningExecutionSettings.Load	(		self,
		str	filePath )

Loads the eVision.EasyDeepLearning.EDeepLearningExecutionSettings.

The given eVision.ESerializer must have been created for reading.

Remarks:

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

Parameters

filePath

File path.

Save() [1/2]

None eVision.EasyDeepLearning.EDeepLearningExecutionSettings.Save	(		self,
		eVision.ESerializer | None	serializer )

Saves the eVision.EasyDeepLearning.EDeepLearningExecutionSettings.

The given eVision.ESerializer must have been created for writing.

Parameters

serializer

Pointer to the eVision.ESerializer created for writing.

Save() [2/2]

None eVision.EasyDeepLearning.EDeepLearningExecutionSettings.Save	(		self,
		str	filePath )

Saves the eVision.EasyDeepLearning.EDeepLearningExecutionSettings.

The given eVision.ESerializer must have been created for writing.

Parameters

filePath

File path.

SetDevice()

None eVision.EasyDeepLearning.EDeepLearningExecutionSettings.SetDevice	(		self,
		eVision.EasyDeepLearning.EDeepLearningDevice	device )

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

Remarks:

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

If the specified device does support the current eVision.EasyDeepLearning.EDeepLearningExecutionSettings.InferencePrecision, it will be set to eVision.EasyDeepLearning.EDeepLearningDevice.DefaultPrecision.

Parameters

device

Device

Property Documentation

AvailableDevices

eVision.EasyDeepLearning.EDeepLearningExecutionSettings.AvailableDevices = property(_AvailableDevices__getter, None)

static

\endcond

Get all available device for the current engine.

BatchSize

eVision.EasyDeepLearning.EDeepLearningExecutionSettings.BatchSize = property(_BatchSize__getter, _BatchSize__setter)

static

\endcond

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.

Remarks:

If eVision.EasyDeepLearning.EDeepLearningExecutionSettings.OptimizeBatchSize 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.

DeviceById

eVision.EasyDeepLearning.EDeepLearningExecutionSettings.DeviceById = property(None, _DeviceById__setter)

static

\endcond

Sets the device with which to run the model using its index in the list returned by eVision.EasyDeepLearning.EDeepLearningExecutionSettings.AvailableDevices.

DeviceByName

eVision.EasyDeepLearning.EDeepLearningExecutionSettings.DeviceByName = property(None, _DeviceByName__setter)

static

\endcond

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

Devices

eVision.EasyDeepLearning.EDeepLearningExecutionSettings.Devices = property(_Devices__getter, _Devices__setter)

static

\endcond

Devices with which to run or train the model.

Using multiple GPUs is only supported by the default engine.

Remarks:

If the specified devices don't support the current eVision.EasyDeepLearning.EDeepLearningExecutionSettings.InferencePrecision, it will be set to eVision.EasyDeepLearning.EDeepLearningDevice.DefaultPrecision.

Engine

eVision.EasyDeepLearning.EDeepLearningExecutionSettings.Engine = property(_Engine__getter, _Engine__setter)

static

\endcond

Engine with which to execute or train the neural network.

InferencePrecision

eVision.EasyDeepLearning.EDeepLearningExecutionSettings.InferencePrecision = property(_InferencePrecision__getter, _InferencePrecision__setter)

static

\endcond

Inference precision.

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

NumAvailableDevices

eVision.EasyDeepLearning.EDeepLearningExecutionSettings.NumAvailableDevices = property(_NumAvailableDevices__getter, None)

static

\endcond

Available devices for the current eVision.EasyDeepLearning.EDeepLearningExecutionSettings.Engine.

NumDevices

eVision.EasyDeepLearning.EDeepLearningExecutionSettings.NumDevices = property(_NumDevices__getter, None)

static

\endcond

Number of devices configured in this execution context.

OptimizeBatchSize

eVision.EasyDeepLearning.EDeepLearningExecutionSettings.OptimizeBatchSize = property(_OptimizeBatchSize__getter, _OptimizeBatchSize__setter)

static

\endcond

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

Default value is true.