Deep Learning benchmark results. More...

Inheritance diagram for eVision.EasyDeepLearning.EDeepLearningBenchmark:

Collaboration diagram for eVision.EasyDeepLearning.EDeepLearningBenchmark:

Public Member Functions
	EDeepLearningBenchmark ()
	Constructors.
	EDeepLearningBenchmark (eVision.EasyDeepLearning.EDeepLearningBenchmark other)
	Constructors.
	EDeepLearningBenchmark (eVision.EasyDeepLearning.EDeepLearningBenchmarkSettings settings)
	Constructors.
bool	IsValid ()
	Whether the benchmark is ready and valid.
virtual void	Load (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 (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.

Properties
eVision.EError	ErrorCode `[get]`
	Error code thrown when computing the benchmark.
string	ErrorDescription `[get]`
	Description of the error that occurred during the benchmark.
int	NumImagesByInference `[get]`
	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	NumInferences `[get]`
	Number of inference made in the benchmark. It is equal to EDeepLearningBenchmarkSettings.NumInferences.
double[]	TimePerInference `[get]`
	Inference time (in nanoseconds) for all the inference calls (an inference processes EDeepLearningBenchmark.NumImagesByInference images together). A time of 0 means that the images for this inference call were dropped (not processed).
int	NumDroppedInference `[get]`
	The number of dropped inference call. Dropped inference call happens when simulating a camera framerate and the processing speed isn't fast enough.
double	MinLatency `[get]`
	Minimum latency (time between the acquisition of an image and the computation of its result).
double	MaxLatency `[get]`
	Maximum latency (time between the acquisition of an image and the computation of its result).
double	MeanLatency `[get]`
	Mean latency.
double	Throughput `[get]`
	Number of images per second that were processed by the Deep Learning tool.
double	MinTimePerInference `[get]`
	Minimum time for a single inference call (in seconds).
double	MaxTimePerInference `[get]`
	Maximum time for a single inference call (in seconds).
double	MeanTimePerInference `[get]`
	Mean time for a single inference call (in seconds).
double	StdTimePerInference `[get]`
	Standard deviation of the inference time for a single inference call (in seconds).
double	MinTimePerImage `[get]`
	Minimum time in seconds for an image (equal to EDeepLearningBenchmark.MinTimePerInference / EDeepLearningBenchmark.NumImagesByInference).
double	MaxTimePerImage `[get]`
	Maximum time in seconds for an image (equal to EDeepLearningBenchmark.MaxTimePerInference / EDeepLearningBenchmark.NumImagesByInference).
double	MeanTimePerImage `[get]`
	Mean time in seconds for an image (equal to EDeepLearningBenchmark.MeanTimePerInference / EDeepLearningBenchmark.NumImagesByInference).
double	StdTimePerImage `[get]`
	Standard deviation of the time in seconds for an image (equal to EDeepLearningBenchmark.StdTimePerInference / EDeepLearningBenchmark.NumImagesByInference).
int	DatasetWidth `[get]`
	Width of the dataset used to run the benchmark.
int	DatasetHeight `[get]`
	Height of the dataset used to run the benchmark.
int	BenchmarkWidth `[get]`
	Width of the images generated in the benchmark. It depends on EDeepLearningBenchmark.DatasetWidth and EDeepLearningBenchmarkSettings.InternalResizeDisabled).
int	BenchmarkHeight `[get]`
	Height of the images generated in the benchmark. It depends on EDeepLearningBenchmark.DatasetHeight and EDeepLearningBenchmarkSettings.InternalResizeDisabled).
eVision.EasyDeepLearning.EDeepLearningBenchmarkSettings	BenchmarkSettings `[get]`
	Settings of the benchmark.

Detailed Description

Deep Learning benchmark results.

License(s): EasyClassify or EasySegment or EasyLocate

Constructor & Destructor Documentation

◆ EDeepLearningBenchmark() [1/3]

eVision.EasyDeepLearning.EDeepLearningBenchmark.EDeepLearningBenchmark ( )

Constructors.

◆ EDeepLearningBenchmark() [2/3]

eVision.EasyDeepLearning.EDeepLearningBenchmark.EDeepLearningBenchmark ( eVision.EasyDeepLearning.EDeepLearningBenchmark other )

Constructors.

Parameters

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

◆ EDeepLearningBenchmark() [3/3]

eVision.EasyDeepLearning.EDeepLearningBenchmark.EDeepLearningBenchmark ( eVision.EasyDeepLearning.EDeepLearningBenchmarkSettings settings )

Constructors.

Parameters

settings The settings used to configure this EDeepLearningBenchmark.

Member Function Documentation

◆ IsValid()

bool eVision.EasyDeepLearning.EDeepLearningBenchmark.IsValid ( )

Whether the benchmark is ready and valid.

◆ Load() [1/2]

virtual 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.

◆ Load() [2/2]

virtual void eVision.EasyDeepLearning.EDeepLearningBenchmark.Load ( string filePath )

virtual

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

Parameters

filePath File path.

◆ Save() [1/2]

virtual 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.

◆ Save() [2/2]

virtual void eVision.EasyDeepLearning.EDeepLearningBenchmark.Save ( string filePath )

virtual

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

Parameters

filePath File path.

Property Documentation

◆ BenchmarkHeight

int eVision.EasyDeepLearning.EDeepLearningBenchmark.BenchmarkHeight

get

Height of the images generated in the benchmark. It depends on EDeepLearningBenchmark.DatasetHeight and EDeepLearningBenchmarkSettings.InternalResizeDisabled).

◆ BenchmarkSettings

eVision.EasyDeepLearning.EDeepLearningBenchmarkSettings eVision.EasyDeepLearning.EDeepLearningBenchmark.BenchmarkSettings

get

Settings of the benchmark.

◆ BenchmarkWidth

int eVision.EasyDeepLearning.EDeepLearningBenchmark.BenchmarkWidth

get

Width of the images generated in the benchmark. It depends on EDeepLearningBenchmark.DatasetWidth and EDeepLearningBenchmarkSettings.InternalResizeDisabled).

◆ DatasetHeight

int eVision.EasyDeepLearning.EDeepLearningBenchmark.DatasetHeight

get

Height of the dataset used to run the benchmark.

◆ DatasetWidth

int eVision.EasyDeepLearning.EDeepLearningBenchmark.DatasetWidth

get

Width of the dataset used to run the benchmark.

◆ ErrorCode

eVision.EError eVision.EasyDeepLearning.EDeepLearningBenchmark.ErrorCode

get

Error code thrown when computing the benchmark.

◆ ErrorDescription

string eVision.EasyDeepLearning.EDeepLearningBenchmark.ErrorDescription

get

Description of the error that occurred during the benchmark.

◆ MaxLatency

double eVision.EasyDeepLearning.EDeepLearningBenchmark.MaxLatency

get

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

◆ MaxTimePerImage

double eVision.EasyDeepLearning.EDeepLearningBenchmark.MaxTimePerImage

get

Maximum time in seconds for an image (equal to EDeepLearningBenchmark.MaxTimePerInference / EDeepLearningBenchmark.NumImagesByInference).

◆ MaxTimePerInference

double eVision.EasyDeepLearning.EDeepLearningBenchmark.MaxTimePerInference

get

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

◆ MeanLatency

double eVision.EasyDeepLearning.EDeepLearningBenchmark.MeanLatency

get

Mean latency.

◆ MeanTimePerImage

double eVision.EasyDeepLearning.EDeepLearningBenchmark.MeanTimePerImage

get

Mean time in seconds for an image (equal to EDeepLearningBenchmark.MeanTimePerInference / EDeepLearningBenchmark.NumImagesByInference).

◆ MeanTimePerInference

double eVision.EasyDeepLearning.EDeepLearningBenchmark.MeanTimePerInference

get

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

◆ MinLatency

double eVision.EasyDeepLearning.EDeepLearningBenchmark.MinLatency

get

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

◆ MinTimePerImage

double eVision.EasyDeepLearning.EDeepLearningBenchmark.MinTimePerImage

get

Minimum time in seconds for an image (equal to EDeepLearningBenchmark.MinTimePerInference / EDeepLearningBenchmark.NumImagesByInference).

◆ MinTimePerInference

double eVision.EasyDeepLearning.EDeepLearningBenchmark.MinTimePerInference

get

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

◆ NumDroppedInference

int eVision.EasyDeepLearning.EDeepLearningBenchmark.NumDroppedInference

get

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

◆ NumImagesByInference

int eVision.EasyDeepLearning.EDeepLearningBenchmark.NumImagesByInference

get

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.

◆ NumInferences

int eVision.EasyDeepLearning.EDeepLearningBenchmark.NumInferences

get

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

◆ StdTimePerImage

double eVision.EasyDeepLearning.EDeepLearningBenchmark.StdTimePerImage

get

Standard deviation of the time in seconds for an image (equal to EDeepLearningBenchmark.StdTimePerInference / EDeepLearningBenchmark.NumImagesByInference).

◆ StdTimePerInference

double eVision.EasyDeepLearning.EDeepLearningBenchmark.StdTimePerInference

get

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

◆ Throughput

double eVision.EasyDeepLearning.EDeepLearningBenchmark.Throughput

get

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

◆ TimePerInference

double [] eVision.EasyDeepLearning.EDeepLearningBenchmark.TimePerInference

get

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

Public Member Functions

Properties

Detailed Description

Constructor & Destructor Documentation

◆ EDeepLearningBenchmark() [1/3]

◆ EDeepLearningBenchmark() [2/3]

◆ EDeepLearningBenchmark() [3/3]

Member Function Documentation

◆ IsValid()

◆ Load() [1/2]

◆ Load() [2/2]

◆ Save() [1/2]

◆ Save() [2/2]

Property Documentation

◆ BenchmarkHeight

◆ BenchmarkSettings

◆ BenchmarkWidth

◆ DatasetHeight

◆ DatasetWidth

◆ ErrorCode

◆ ErrorDescription

◆ MaxLatency

◆ MaxTimePerImage

◆ MaxTimePerInference

◆ MeanLatency

◆ MeanTimePerImage

◆ MeanTimePerInference

◆ MinLatency

◆ MinTimePerImage

◆ MinTimePerInference

◆ NumDroppedInference

◆ NumImagesByInference

◆ NumInferences

◆ StdTimePerImage

◆ StdTimePerInference

◆ Throughput

◆ TimePerInference