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.
eVision.EasyDeepLearning.EDeepOCRModel	Model (self)
	The type of model for this result.
float	Error (self)
	Error computed during training.
float	LocationFScore (self)
	F Score of the location (harmonic mean of the precision and recall).
float	LocationRecall (self)
	Recall of the location (proportion of ground truth text that are correctly detected).
float	LocationPrecision (self)
	Precision of the location (proportion of detected texts that are correctly detected).
eVision.EasyDeepLearning.EClassificationMetrics	OrientationMetrics (self)
	Get the metrics for the orientation.
float	RecognitionImageAccuracy (self)
	Get the image-wise accuracy (mean per-image accuracy).
float	RecognitionWordAccuracy (self)
	Get the word-wise accuracy (share of words that were correctly read in all images).
float	LocationThreshold (self)
	Location threshold for which to compute the metrics.
	LocationThreshold (self, float value)
	Location threshold for which to compute the metrics.

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

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.

Error()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics.Error

(

self

)

Error computed during training.

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.

LocationFScore()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationFScore

(

self

)

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

LocationPrecision()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationPrecision

(

self

)

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

LocationRecall()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationRecall

(

self

)

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

LocationThreshold() [1/2]

float eVision.EasyDeepLearning.EDeepOCRToolMetrics.LocationThreshold

(

self

)

Location threshold for which to compute the metrics.

LocationThreshold() [2/2]

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

Location threshold for which to compute the metrics.

Model()

eVision.EasyDeepLearning.EDeepOCRModel eVision.EasyDeepLearning.EDeepOCRToolMetrics.Model

(

self

)

The type of model for this result.

OrientationMetrics()

eVision.EasyDeepLearning.EClassificationMetrics eVision.EasyDeepLearning.EDeepOCRToolMetrics.OrientationMetrics

(

self

)

Get the metrics for the orientation.

RecognitionImageAccuracy()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics.RecognitionImageAccuracy

(

self

)

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

RecognitionWordAccuracy()

float eVision.EasyDeepLearning.EDeepOCRToolMetrics.RecognitionWordAccuracy

(

self

)

Get the word-wise accuracy (share of words that were correctly read in all images).

Biased towards images containing a large number of words.

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.