eVision::EasyDeepLearning::EDeepLearningBenchmark Class Reference

Deep Learning benchmark results. More...

#include <eVision/EasyDeepLearning/EDeepLearningBenchmark.h>

Collaboration diagram for eVision::EasyDeepLearning::EDeepLearningBenchmark:

Public Member Functions
	EDeepLearningBenchmark ()
	Constructors.
	EDeepLearningBenchmark (const eVision::EasyDeepLearning::EDeepLearningBenchmark &other)
	Constructors.
	EDeepLearningBenchmark (const eVision::EasyDeepLearning::EDeepLearningBenchmarkSettings &settings)
	Constructors.
virtual	~EDeepLearningBenchmark () throw ()
eVision::EasyDeepLearning::EDeepLearningBenchmark &	operator= (const eVision::EasyDeepLearning::EDeepLearningBenchmark &other)
	Assignment operator.
bool	IsValid () const
	Whether the benchmark is ready and valid.
eVision::EError	GetErrorCode () const
	Error code thrown when computing the benchmark.
std::string	GetErrorDescription () const
	Description of the error that occurred during the benchmark.
virtual void	Load (const std::string &filePath)
	Load a EDeepLearningBenchmark object. The given ESerializer must have been created for reading.
virtual void	Load (eVision::ESerializer *serializer)
	Load a EDeepLearningBenchmark object. The given ESerializer must have been created for reading.
virtual void	Save (const std::string &filePath)
	Save the EDeepLearningBenchmark object. The given ESerializer must have been created for writing.
virtual void	Save (eVision::ESerializer *serializer)
	Save the EDeepLearningBenchmark object. The given ESerializer must have been created for writing.
int	GetNumImagesByInference () const
	The number of images that were processed together in one inference call to exploit the specified batch size. For EasyClassify and EasyLocate, this is equal to the batch size. For EasySegment, it depends on the number of patches that are extracted from input images.
int	GetNumInferences () const
	Number of inference made in the benchmark. It is equal to EDeepLearningBenchmarkSettings::GetNumInferences.
std::vector< double >	GetTimePerInference () const
	Inference time (in nanoseconds) for all the inference calls (an inference processes EDeepLearningBenchmark::GetNumImagesByInference images together). A time of 0 means that the images for this inference call were dropped (not processed).
int	GetNumDroppedInference () const
	The number of dropped inference call. Dropped inference call happens when simulating a camera framerate and the processing speed isn't fast enough.
double	GetMinLatency () const
	Minimum latency (time between the acquisition of an image and the computation of its result).
double	GetMaxLatency () const
	Maximum latency (time between the acquisition of an image and the computation of its result).
double	GetMeanLatency () const
	Mean latency.
double	GetThroughput () const
	Number of images per second that were processed by the Deep Learning tool.
double	GetMinTimePerInference () const
	Minimum time for a single inference call (in seconds).
double	GetMaxTimePerInference () const
	Maximum time for a single inference call (in seconds).
double	GetMeanTimePerInference () const
	Mean time for a single inference call (in seconds).
double	GetStdTimePerInference () const
	Standard deviation of the inference time for a single inference call (in seconds).
double	GetMinTimePerImage () const
	Minimum time in seconds for an image (equal to EDeepLearningBenchmark::GetMinTimePerInference / EDeepLearningBenchmark::GetNumImagesByInference).
double	GetMaxTimePerImage () const
	Maximum time in seconds for an image (equal to EDeepLearningBenchmark::GetMaxTimePerInference / EDeepLearningBenchmark::GetNumImagesByInference).
double	GetMeanTimePerImage () const
	Mean time in seconds for an image (equal to EDeepLearningBenchmark::GetMeanTimePerInference / EDeepLearningBenchmark::GetNumImagesByInference).
double	GetStdTimePerImage () const
	Standard deviation of the time in seconds for an image (equal to EDeepLearningBenchmark::GetStdTimePerInference / EDeepLearningBenchmark::GetNumImagesByInference).
int	GetDatasetWidth () const
	Width of the dataset used to run the benchmark.
int	GetDatasetHeight () const
	Height of the dataset used to run the benchmark.
int	GetBenchmarkWidth () const
	Width of the images generated in the benchmark. It depends on EDeepLearningBenchmark::GetDatasetWidth and EDeepLearningBenchmarkSettings::GetInternalResizeDisabled).
int	GetBenchmarkHeight () const
	Height of the images generated in the benchmark. It depends on EDeepLearningBenchmark::GetDatasetHeight and EDeepLearningBenchmarkSettings::GetInternalResizeDisabled).
const eVision::EasyDeepLearning::EDeepLearningBenchmarkSettings &	GetBenchmarkSettings () const
	Settings of the benchmark.
eVision::EasyDeepLearning::EDeepLearningBenchmarkSettings &	GetBenchmarkSettings ()
	Settings of the benchmark.
	EDeepLearningBenchmark (CppWrapperInternal::InternalConstructor)

Public Attributes
CppWrapperInternal::WrappedClass	wrappedClass_

Detailed Description

Deep Learning benchmark results.

License(s): EasyClassify or EasySegment or EasyLocate

Constructor & Destructor Documentation

EDeepLearningBenchmark() [1/4]

eVision::EasyDeepLearning::EDeepLearningBenchmark::EDeepLearningBenchmark

(

)

Constructors.

EDeepLearningBenchmark() [2/4]

eVision::EasyDeepLearning::EDeepLearningBenchmark::EDeepLearningBenchmark

(

const eVision::EasyDeepLearning::EDeepLearningBenchmark &

other

)

Constructors.

Parameters

other

The other EDeepLearningBenchmark that we will copy into this one.

EDeepLearningBenchmark() [3/4]

eVision::EasyDeepLearning::EDeepLearningBenchmark::EDeepLearningBenchmark

(

const eVision::EasyDeepLearning::EDeepLearningBenchmarkSettings &

settings

)

Constructors.

Parameters

settings

The settings used to configure this EDeepLearningBenchmark.

~EDeepLearningBenchmark()

eVision::EasyDeepLearning::EDeepLearningBenchmark::~EDeepLearningBenchmark ( ) throw (  )

virtual

EDeepLearningBenchmark() [4/4]

eVision::EasyDeepLearning::EDeepLearningBenchmark::EDeepLearningBenchmark

(

CppWrapperInternal::InternalConstructor

)

Member Function Documentation

GetBenchmarkHeight()

int eVision::EasyDeepLearning::EDeepLearningBenchmark::GetBenchmarkHeight

(

)

const

Height of the images generated in the benchmark. It depends on EDeepLearningBenchmark::GetDatasetHeight and EDeepLearningBenchmarkSettings::GetInternalResizeDisabled).

GetBenchmarkSettings() [1/2]

eVision::EasyDeepLearning::EDeepLearningBenchmarkSettings & eVision::EasyDeepLearning::EDeepLearningBenchmark::GetBenchmarkSettings

(

)

Settings of the benchmark.

GetBenchmarkSettings() [2/2]

const eVision::EasyDeepLearning::EDeepLearningBenchmarkSettings & eVision::EasyDeepLearning::EDeepLearningBenchmark::GetBenchmarkSettings

(

)

const

Settings of the benchmark.

GetBenchmarkWidth()

int eVision::EasyDeepLearning::EDeepLearningBenchmark::GetBenchmarkWidth

(

)

const

Width of the images generated in the benchmark. It depends on EDeepLearningBenchmark::GetDatasetWidth and EDeepLearningBenchmarkSettings::GetInternalResizeDisabled).

GetDatasetHeight()

int eVision::EasyDeepLearning::EDeepLearningBenchmark::GetDatasetHeight

(

)

const

Height of the dataset used to run the benchmark.

GetDatasetWidth()

int eVision::EasyDeepLearning::EDeepLearningBenchmark::GetDatasetWidth

(

)

const

Width of the dataset used to run the benchmark.

GetErrorCode()

eVision::EError eVision::EasyDeepLearning::EDeepLearningBenchmark::GetErrorCode

(

)

const

Error code thrown when computing the benchmark.

GetErrorDescription()

std::string eVision::EasyDeepLearning::EDeepLearningBenchmark::GetErrorDescription

(

)

const

Description of the error that occurred during the benchmark.

GetMaxLatency()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetMaxLatency

(

)

const

Maximum latency (time between the acquisition of an image and the computation of its result).

GetMaxTimePerImage()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetMaxTimePerImage

(

)

const

Maximum time in seconds for an image (equal to EDeepLearningBenchmark::GetMaxTimePerInference / EDeepLearningBenchmark::GetNumImagesByInference).

GetMaxTimePerInference()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetMaxTimePerInference

(

)

const

Maximum time for a single inference call (in seconds).

GetMeanLatency()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetMeanLatency

(

)

const

Mean latency.

GetMeanTimePerImage()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetMeanTimePerImage

(

)

const

Mean time in seconds for an image (equal to EDeepLearningBenchmark::GetMeanTimePerInference / EDeepLearningBenchmark::GetNumImagesByInference).

GetMeanTimePerInference()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetMeanTimePerInference

(

)

const

Mean time for a single inference call (in seconds).

GetMinLatency()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetMinLatency

(

)

const

Minimum latency (time between the acquisition of an image and the computation of its result).

GetMinTimePerImage()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetMinTimePerImage

(

)

const

Minimum time in seconds for an image (equal to EDeepLearningBenchmark::GetMinTimePerInference / EDeepLearningBenchmark::GetNumImagesByInference).

GetMinTimePerInference()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetMinTimePerInference

(

)

const

Minimum time for a single inference call (in seconds).

GetNumDroppedInference()

int eVision::EasyDeepLearning::EDeepLearningBenchmark::GetNumDroppedInference

(

)

const

The number of dropped inference call. Dropped inference call happens when simulating a camera framerate and the processing speed isn't fast enough.

GetNumImagesByInference()

int eVision::EasyDeepLearning::EDeepLearningBenchmark::GetNumImagesByInference

(

)

const

The number of images that were processed together in one inference call to exploit the specified batch size. For EasyClassify and EasyLocate, this is equal to the batch size. For EasySegment, it depends on the number of patches that are extracted from input images.

GetNumInferences()

int eVision::EasyDeepLearning::EDeepLearningBenchmark::GetNumInferences

(

)

const

Number of inference made in the benchmark. It is equal to EDeepLearningBenchmarkSettings::GetNumInferences.

GetStdTimePerImage()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetStdTimePerImage

(

)

const

Standard deviation of the time in seconds for an image (equal to EDeepLearningBenchmark::GetStdTimePerInference / EDeepLearningBenchmark::GetNumImagesByInference).

GetStdTimePerInference()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetStdTimePerInference

(

)

const

Standard deviation of the inference time for a single inference call (in seconds).

GetThroughput()

double eVision::EasyDeepLearning::EDeepLearningBenchmark::GetThroughput

(

)

const

Number of images per second that were processed by the Deep Learning tool.

GetTimePerInference()

std::vector< double > eVision::EasyDeepLearning::EDeepLearningBenchmark::GetTimePerInference

(

)

const

Inference time (in nanoseconds) for all the inference calls (an inference processes EDeepLearningBenchmark::GetNumImagesByInference images together). A time of 0 means that the images for this inference call were dropped (not processed).

IsValid()

bool eVision::EasyDeepLearning::EDeepLearningBenchmark::IsValid

(

)

const

Whether the benchmark is ready and valid.

Load() [1/2]

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

virtual

Load a EDeepLearningBenchmark object. The given ESerializer must have been created for reading.

Parameters

filePath

File path.

Load() [2/2]

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

virtual

Load a EDeepLearningBenchmark object. The given ESerializer must have been created for reading.

Parameters

serializer

Pointer to the ESerializer created for reading.

operator=()

eVision::EasyDeepLearning::EDeepLearningBenchmark & eVision::EasyDeepLearning::EDeepLearningBenchmark::operator=

(

const eVision::EasyDeepLearning::EDeepLearningBenchmark &

other

)

Assignment operator.

Parameters

other

The other EDeepLearningBenchmark that we will copy into this one.

Save() [1/2]

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

virtual

Save the EDeepLearningBenchmark object. The given ESerializer must have been created for writing.

Parameters

filePath

File path.

Save() [2/2]

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

virtual

Save the EDeepLearningBenchmark object. The given ESerializer must have been created for writing.

Parameters

serializer

Pointer to the ESerializer created for writing.

Member Data Documentation

wrappedClass_

CppWrapperInternal::WrappedClass eVision::EasyDeepLearning::EDeepLearningBenchmark::wrappedClass_