eVision::EasyDeepLearning::EDeepOCRToolMetrics Class Reference

Metrics for EDeepOCRTool. More...

#include <eVision/EasyDeepLearning/EasyDeepOCR/EDeepOCRToolMetrics.h>

Collaboration diagram for eVision::EasyDeepLearning::EDeepOCRToolMetrics:

Public Member Functions
	EDeepOCRToolMetrics ()
	Constructs a EDeepOCRToolMetrics.
	EDeepOCRToolMetrics (const eVision::EasyDeepLearning::EDeepOCRToolMetrics &other)
	Copy constructor of a EDeepOCRToolMetrics object.
virtual	~EDeepOCRToolMetrics () throw ()
eVision::EasyDeepLearning::EDeepOCRToolMetrics &	operator= (const eVision::EasyDeepLearning::EDeepOCRToolMetrics &other)
	Assignment operator.
eVision::EasyDeepLearning::EDeepOCRModel	GetModel () const
	The type of model for this result.
void	AddResult (const eVision::EasyDeepLearning::EDeepOCRToolResult &result)
	Add a result to the metrics.
void	RemoveResult (const eVision::EasyDeepLearning::EDeepOCRToolResult &result)
	Removes a result from the metrics.
void	AddResult (float loss)
	Adds a loss result to the metrics.
void	RemoveResult (float loss)
	Removes a loss result from the metrics.
float	GetError () const
	Error computed during training.
bool	IsValid () const
	Whether the metrics contains data or not.
float	GetLocationFScore () const
	F Score of the location (harmonic mean of the precision and recall).
float	GetLocationRecall () const
	Recall of the location (proportion of ground truth text that are correctly detected).
float	GetLocationPrecision () const
	Precision of the location (proportion of detected texts that are correctly detected).
const eVision::EasyDeepLearning::EClassificationMetrics &	GetOrientationMetrics () const
	Get the metrics for the orientation.
float	GetRecognitionImageAccuracy () const
	Get the image-wise accuracy (mean per-image accuracy).
float	GetRecognitionWordAccuracy () const
	Get the word-wise accuracy (share of words that were correctly read in all images). Biased towards images containing a large number of words.
float	GetLocationThreshold () const
	Location threshold for which to compute the metrics.
void	SetLocationThreshold (float val)
	Location threshold for which to compute the metrics.
float	ComputeLocationThresholdMaximizingRecall () const
	Computes the location threshold that will maximize the EDeepOCRToolMetrics::GetLocationRecall.
float	ComputeLocationThresholdMaximizingFScore () const
	Computes the location threshold that will maximize the EDeepOCRToolMetrics::GetLocationFScore.
float	ComputeLocationThresholdMaximizingPrecision () const
	Computes the location threshold that will maximize the EDeepOCRToolMetrics::GetLocationPrecision.
void	Load (const std::string &path)
	Loads the EDeepOCRToolMetrics. The given ESerializer must have been created for reading.
void	Load (eVision::ESerializer *serializer)
	Loads the EDeepOCRToolMetrics. The given ESerializer must have been created for reading.
void	Save (const std::string &path)
	Saves the EDeepOCRToolMetrics. The given ESerializer must have been created for writing.
void	Save (eVision::ESerializer *serializer)
	Saves the EDeepOCRToolMetrics. The given ESerializer must have been created for writing.
	EDeepOCRToolMetrics (CppWrapperInternal::InternalConstructor)

Public Attributes
CppWrapperInternal::WrappedClass	wrappedClass_

Detailed Description

Metrics for EDeepOCRTool.

License(s): EasyDeepOCR

Constructor & Destructor Documentation

EDeepOCRToolMetrics() [1/3]

eVision::EasyDeepLearning::EDeepOCRToolMetrics::EDeepOCRToolMetrics

(

)

Constructs a EDeepOCRToolMetrics.

EDeepOCRToolMetrics() [2/3]

eVision::EasyDeepLearning::EDeepOCRToolMetrics::EDeepOCRToolMetrics

(

const eVision::EasyDeepLearning::EDeepOCRToolMetrics &

other

)

Copy constructor of a EDeepOCRToolMetrics object.

Parameters

other

Reference to the EDeepOCRToolMetrics object that should be copied

~EDeepOCRToolMetrics()

eVision::EasyDeepLearning::EDeepOCRToolMetrics::~EDeepOCRToolMetrics ( ) throw (  )

virtual

EDeepOCRToolMetrics() [3/3]

eVision::EasyDeepLearning::EDeepOCRToolMetrics::EDeepOCRToolMetrics

(

CppWrapperInternal::InternalConstructor

)

Member Function Documentation

AddResult() [1/2]

void eVision::EasyDeepLearning::EDeepOCRToolMetrics::AddResult

(

const eVision::EasyDeepLearning::EDeepOCRToolResult &

result

)

Add a result to the metrics.

Parameters

result

Result to add to the metrics.

AddResult() [2/2]

void eVision::EasyDeepLearning::EDeepOCRToolMetrics::AddResult

(

float

loss

)

Adds a loss result to the metrics.

Parameters

loss	Loss to add to the metrics.

ComputeLocationThresholdMaximizingFScore()

float eVision::EasyDeepLearning::EDeepOCRToolMetrics::ComputeLocationThresholdMaximizingFScore

(

)

const

Computes the location threshold that will maximize the EDeepOCRToolMetrics::GetLocationFScore.

ComputeLocationThresholdMaximizingPrecision()

float eVision::EasyDeepLearning::EDeepOCRToolMetrics::ComputeLocationThresholdMaximizingPrecision

(

)

const

Computes the location threshold that will maximize the EDeepOCRToolMetrics::GetLocationPrecision.

ComputeLocationThresholdMaximizingRecall()

float eVision::EasyDeepLearning::EDeepOCRToolMetrics::ComputeLocationThresholdMaximizingRecall

(

)

const

Computes the location threshold that will maximize the EDeepOCRToolMetrics::GetLocationRecall.

GetError()

float eVision::EasyDeepLearning::EDeepOCRToolMetrics::GetError

(

)

const

Error computed during training.

GetLocationFScore()

float eVision::EasyDeepLearning::EDeepOCRToolMetrics::GetLocationFScore

(

)

const

F Score of the location (harmonic mean of the precision and recall).

GetLocationPrecision()

float eVision::EasyDeepLearning::EDeepOCRToolMetrics::GetLocationPrecision

(

)

const

Precision of the location (proportion of detected texts that are correctly detected).

GetLocationRecall()

float eVision::EasyDeepLearning::EDeepOCRToolMetrics::GetLocationRecall

(

)

const

Recall of the location (proportion of ground truth text that are correctly detected).

GetLocationThreshold()

float eVision::EasyDeepLearning::EDeepOCRToolMetrics::GetLocationThreshold

(

)

const

Location threshold for which to compute the metrics.

GetModel()

eVision::EasyDeepLearning::EDeepOCRModel eVision::EasyDeepLearning::EDeepOCRToolMetrics::GetModel

(

)

const

The type of model for this result.

GetOrientationMetrics()

const eVision::EasyDeepLearning::EClassificationMetrics & eVision::EasyDeepLearning::EDeepOCRToolMetrics::GetOrientationMetrics

(

)

const

Get the metrics for the orientation.

GetRecognitionImageAccuracy()

float eVision::EasyDeepLearning::EDeepOCRToolMetrics::GetRecognitionImageAccuracy

(

)

const

Get the image-wise accuracy (mean per-image accuracy).

GetRecognitionWordAccuracy()

float eVision::EasyDeepLearning::EDeepOCRToolMetrics::GetRecognitionWordAccuracy

(

)

const

Get the word-wise accuracy (share of words that were correctly read in all images). Biased towards images containing a large number of words.

IsValid()

bool eVision::EasyDeepLearning::EDeepOCRToolMetrics::IsValid

(

)

const

Whether the metrics contains data or not.

Load() [1/2]

void eVision::EasyDeepLearning::EDeepOCRToolMetrics::Load

(

const std::string &

path

)

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

Parameters

path	The file path.

Load() [2/2]

void eVision::EasyDeepLearning::EDeepOCRToolMetrics::Load

(

eVision::ESerializer *

serializer

)

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

Parameters

serializer

The serializer.

operator=()

eVision::EasyDeepLearning::EDeepOCRToolMetrics & eVision::EasyDeepLearning::EDeepOCRToolMetrics::operator=

(

const eVision::EasyDeepLearning::EDeepOCRToolMetrics &

other

)

Assignment operator.

Parameters

other

Reference to the EDeepOCRToolMetrics object that should be copied

RemoveResult() [1/2]

void eVision::EasyDeepLearning::EDeepOCRToolMetrics::RemoveResult

(

const eVision::EasyDeepLearning::EDeepOCRToolResult &

result

)

Removes a result from the metrics.

Parameters

result

Result to remove from the metrics.

RemoveResult() [2/2]

void eVision::EasyDeepLearning::EDeepOCRToolMetrics::RemoveResult

(

float

loss

)

Removes a loss result from the metrics.

Parameters

loss	Loss result to remove from the metrics.

Save() [1/2]

void eVision::EasyDeepLearning::EDeepOCRToolMetrics::Save

(

const std::string &

path

)

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

Parameters

path	The file path.

Save() [2/2]

void eVision::EasyDeepLearning::EDeepOCRToolMetrics::Save

(

eVision::ESerializer *

serializer

)

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

Parameters

serializer

The serializer.

SetLocationThreshold()

void eVision::EasyDeepLearning::EDeepOCRToolMetrics::SetLocationThreshold

(

float

val

)

Location threshold for which to compute the metrics.

Member Data Documentation

wrappedClass_

CppWrapperInternal::WrappedClass eVision::EasyDeepLearning::EDeepOCRToolMetrics::wrappedClass_