eVision.EasyDeepLearning.EDeepOCRToolMetrics Class Reference

Metrics for eVision.EasyDeepLearning.EDeepOCRTool. More...

Public Member Functions
None	__init__ (self)
	Constructs a eVision.EasyDeepLearning.EDeepOCRToolMetrics.
None	__init__ (self, eVision.EasyDeepLearning.EDeepOCRToolMetrics other)
	Copy constructor of a eVision.EasyDeepLearning.EDeepOCRToolMetrics object.
None	AddResult (self, eVision.EasyDeepLearning.EDeepOCRToolResult result)
	Add a result to the metrics.
None	AddResult (self, float loss)
	Adds a loss result to the metrics.
None	RemoveResult (self, eVision.EasyDeepLearning.EDeepOCRToolResult result)
	Removes a result from the metrics.
None	RemoveResult (self, float loss)
	Removes a loss result from the metrics.
bool	IsValid (self)
	Whether the metrics contains data or not.
float	ComputeLocationThresholdMaximizingRecall (self)
	Computes the location threshold that will maximize the eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationRecall.
float	ComputeLocationThresholdMaximizingFScore (self)
	Computes the location threshold that will maximize the eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationFScore.
float	ComputeLocationThresholdMaximizingPrecision (self)
	Computes the location threshold that will maximize the eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationPrecision.
None	Load (self, str path)
	Loads the eVision.EasyDeepLearning.EDeepOCRToolMetrics.
None	Load (self, eVision.ESerializer|None serializer)
	Loads the eVision.EasyDeepLearning.EDeepOCRToolMetrics.
None	Save (self, str path)
	Saves the eVision.EasyDeepLearning.EDeepOCRToolMetrics.
None	Save (self, eVision.ESerializer|None serializer)
	Saves the eVision.EasyDeepLearning.EDeepOCRToolMetrics.

Protected Member Functions
eVision.EasyDeepLearning.EDeepOCRModel	_Model__getter (self)
	\cond
float	_Error__getter (self)
	\cond
float	_LocationFScore__getter (self)
	\cond
float	_LocationRecall__getter (self)
	\cond
float	_LocationPrecision__getter (self)
	\cond
eVision.EasyDeepLearning.EClassificationMetrics	_OrientationMetrics__getter (self)
	\cond
float	_RecognitionImageAccuracy__getter (self)
	\cond
float	_RecognitionWordAccuracy__getter (self)
	\cond
float	_LocationThreshold__getter (self)
	\cond
	_LocationThreshold__setter (self, float value)
	Location threshold for which to compute the metrics.

Properties
	Model = property(_Model__getter, None)
	\endcond
	Error = property(_Error__getter, None)
	\endcond
	LocationFScore = property(_LocationFScore__getter, None)
	\endcond
	LocationRecall = property(_LocationRecall__getter, None)
	\endcond
	LocationPrecision = property(_LocationPrecision__getter, None)
	\endcond
	OrientationMetrics = property(_OrientationMetrics__getter, None)
	\endcond
	RecognitionImageAccuracy = property(_RecognitionImageAccuracy__getter, None)
	\endcond
	RecognitionWordAccuracy = property(_RecognitionWordAccuracy__getter, None)
	\endcond
	LocationThreshold = property(_LocationThreshold__getter, _LocationThreshold__setter)
	\endcond

Detailed Description

Metrics for eVision.EasyDeepLearning.EDeepOCRTool.

Remarks:

License(s): EasyDeepOCR

Constructor & Destructor Documentation

__init__() [1/2]

None eVision.EasyDeepLearning.EDeepOCRToolMetrics.__init__

(

self

)

Constructs a eVision.EasyDeepLearning.EDeepOCRToolMetrics.

__init__() [2/2]

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

Copy constructor of a eVision.EasyDeepLearning.EDeepOCRToolMetrics object.

Parameters

other

Reference to the eVision.EasyDeepLearning.EDeepOCRToolMetrics object that should be copied

Member Function Documentation

_Error__getter()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics._Error__getter ( self )

protected

\cond

Error computed during training.

_LocationFScore__getter()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics._LocationFScore__getter ( self )

protected

\cond

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

_LocationPrecision__getter()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics._LocationPrecision__getter ( self )

protected

\cond

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

_LocationRecall__getter()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics._LocationRecall__getter ( self )

protected

\cond

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

_LocationThreshold__getter()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics._LocationThreshold__getter ( self )

protected

\cond

Location threshold for which to compute the metrics.

_LocationThreshold__setter()

eVision.EasyDeepLearning.EDeepOCRToolMetrics._LocationThreshold__setter ( self, float value )

protected

Location threshold for which to compute the metrics.

_Model__getter()

eVision.EasyDeepLearning.EDeepOCRModel eVision.EasyDeepLearning.EDeepOCRToolMetrics._Model__getter ( self )

protected

\cond

The type of model for this result.

_OrientationMetrics__getter()

eVision.EasyDeepLearning.EClassificationMetrics eVision.EasyDeepLearning.EDeepOCRToolMetrics._OrientationMetrics__getter ( self )

protected

\cond

Get the metrics for the orientation.

_RecognitionImageAccuracy__getter()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics._RecognitionImageAccuracy__getter ( self )

protected

\cond

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

_RecognitionWordAccuracy__getter()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics._RecognitionWordAccuracy__getter ( self )

protected

\cond

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

AddResult() [1/2]

None eVision.EasyDeepLearning.EDeepOCRToolMetrics.AddResult	(		self,
		eVision.EasyDeepLearning.EDeepOCRToolResult	result )

Add a result to the metrics.

Parameters

result

Result to add to the metrics.

AddResult() [2/2]

None eVision.EasyDeepLearning.EDeepOCRToolMetrics.AddResult	(		self,
		float	loss )

Adds a loss result to the metrics.

Parameters

loss	Loss to add to the metrics.

ComputeLocationThresholdMaximizingFScore()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics.ComputeLocationThresholdMaximizingFScore

(

self

)

Computes the location threshold that will maximize the eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationFScore.

ComputeLocationThresholdMaximizingPrecision()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics.ComputeLocationThresholdMaximizingPrecision

(

self

)

Computes the location threshold that will maximize the eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationPrecision.

ComputeLocationThresholdMaximizingRecall()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics.ComputeLocationThresholdMaximizingRecall

(

self

)

Computes the location threshold that will maximize the eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationRecall.

IsValid()

bool eVision.EasyDeepLearning.EDeepOCRToolMetrics.IsValid

(

self

)

Whether the metrics contains data or not.

Load() [1/2]

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

Loads the eVision.EasyDeepLearning.EDeepOCRToolMetrics.

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

Parameters

serializer

The serializer.

Load() [2/2]

None eVision.EasyDeepLearning.EDeepOCRToolMetrics.Load	(		self,
		str	path )

Loads the eVision.EasyDeepLearning.EDeepOCRToolMetrics.

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

Parameters

path	The file path.

RemoveResult() [1/2]

None eVision.EasyDeepLearning.EDeepOCRToolMetrics.RemoveResult	(		self,
		eVision.EasyDeepLearning.EDeepOCRToolResult	result )

Removes a result from the metrics.

Parameters

result

Result to remove from the metrics.

RemoveResult() [2/2]

None eVision.EasyDeepLearning.EDeepOCRToolMetrics.RemoveResult	(		self,
		float	loss )

Removes a loss result from the metrics.

Parameters

loss	Loss result to remove from the metrics.

Save() [1/2]

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

Saves the eVision.EasyDeepLearning.EDeepOCRToolMetrics.

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

Parameters

serializer

The serializer.

Save() [2/2]

None eVision.EasyDeepLearning.EDeepOCRToolMetrics.Save	(		self,
		str	path )

Saves the eVision.EasyDeepLearning.EDeepOCRToolMetrics.

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

Parameters

path	The file path.

Property Documentation

Error

eVision.EasyDeepLearning.EDeepOCRToolMetrics.Error = property(_Error__getter, None)

static

\endcond

Error computed during training.

LocationFScore

eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationFScore = property(_LocationFScore__getter, None)

static

\endcond

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

LocationPrecision

eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationPrecision = property(_LocationPrecision__getter, None)

static

\endcond

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

LocationRecall

eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationRecall = property(_LocationRecall__getter, None)

static

\endcond

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

LocationThreshold

eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationThreshold = property(_LocationThreshold__getter, _LocationThreshold__setter)

static

\endcond

Location threshold for which to compute the metrics.

Model

eVision.EasyDeepLearning.EDeepOCRToolMetrics.Model = property(_Model__getter, None)

static

\endcond

The type of model for this result.

OrientationMetrics

eVision.EasyDeepLearning.EDeepOCRToolMetrics.OrientationMetrics = property(_OrientationMetrics__getter, None)

static

\endcond

Get the metrics for the orientation.

RecognitionImageAccuracy

eVision.EasyDeepLearning.EDeepOCRToolMetrics.RecognitionImageAccuracy = property(_RecognitionImageAccuracy__getter, None)

static

\endcond

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

RecognitionWordAccuracy

eVision.EasyDeepLearning.EDeepOCRToolMetrics.RecognitionWordAccuracy = property(_RecognitionWordAccuracy__getter, None)

static

\endcond

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