Collection of metrics used to evaluate the state of an eVision.EasyDeepLearning.EUnsupervisedSegmenter. More...

Inheritance diagram for eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics:

Collaboration diagram for eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics:

Public Member Functions
None	__init__ (self)
	Constructs an eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics object.
None	__init__ (self, eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics other)
	Copy constructor of an eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics object.
bool	IsTotallyUnsupervised (self)
	Whether this metrics has results from only good images (true) or from both good and defective images (false).
bool	IsValid (self)
	Indicates whether the object contains at least one result.
None	Load (self, str path)
	Loads an unsupervised segmentation metric.
None	Load (self, eVision.ESerializer\|None serializer)
	Loads an unsupervised segmentation metric.
None	Save (self, str path)
	Saves an unsupervised segmentation metric.
None	Save (self, eVision.ESerializer\|None serializer)
	Saves an unsupervised segmentation metric.
None	AddResult (self, eVision.EasyDeepLearning.EUnsupervisedSegmenterResult result, bool isGoodImage)
	Adds the given result with the corresponding ground truth label to the metrics.
None	AddErrorResult (self, eVision.EasyDeepLearning.EUnsupervisedSegmenterResult result)
	Adds the given result to the metric for error computation.
None	RemoveResult (self, eVision.EasyDeepLearning.EUnsupervisedSegmenterResult result, bool isGoodImage)
	Removes the given result with the corresponding ground truth label to the metrics.
None	RemoveErrorResult (self, eVision.EasyDeepLearning.EUnsupervisedSegmenterResult result)
	Removes the given result from the metric for error computation.
None	AddMetrics (self, eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics other)
	Adds the other metrics to the current metrics of this object.
float	GetBestWeightedAccuracy (self, float goodWeight, float badWeight)
	Best achievable weighted accuracy.
float	GetBestWeightedAccuracy (self, eVision.EasyDeepLearning.EDataset dataset)
	Best achievable weighted accuracy.
float	GetBestWeightedAccuracyClassificationThreshold (self, float goodWeight, float badWeight)
	Classification threshold giving the best achievable weighted accuracy (see eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracy).
float	GetBestWeightedAccuracyClassificationThreshold (self, eVision.EasyDeepLearning.EDataset dataset)
	Classification threshold giving the best achievable weighted accuracy (see eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracy).
float	Error (self)
	The error of the segmenter.
float	AverageScoreOnGoodImages (self)
	Gets the average score of good images.
float	AverageScoreOnDefectiveImages (self)
	Gets the average score of defective images.
Public Member Functions inherited from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics
None	__init__ (self)
	Constructs an empty eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics object.
None	__init__ (self, eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics other)
	Copy constructor.
bool	IsDefectDetectionMetricsValid (self)
	Whether the defect detection metrics are valid or not.
float	GetAccuracy (self, int index)
	The accuracy of the segmenter.
float	GetAccuracy (self)
	The accuracy of the segmenter.
int	GetConfusion (self, eVision.EasyDeepLearning.EConfusionMatrixElement element, int index)
	Confusion value of one label with another.
int	GetConfusion (self, eVision.EasyDeepLearning.EConfusionMatrixElement element)
	Confusion value of one label with another.
float	GetRecall (self, int index)
	Recall for the current threshold.
float	GetRecall (self)
	Recall for the current threshold.
float	GetPrecision (self, int index)
	Precision for the current threshold.
float	GetPrecision (self)
	Precision for the current threshold.
float	GetFScore (self, int index)
	The F1-Score for the current threshold.
float	GetFScore (self)
	The F1-Score for the current threshold.
eVision.EasyDeepLearning.EROCPoint	GetPrecisionRecallCurvePoint (self, int index)
	Get a point on the precision/recall curve.
eVision.EasyDeepLearning.EROCPoint	GetPrecisionRecallCurvePoint (self)
	Get a point on the precision/recall curve.
eVision.EasyDeepLearning.EROCPoint	GetROCPoint (self, int index)
	ROC (Receiver Operating Characteristic) point.
eVision.EasyDeepLearning.EROCPoint	GetROCPoint (self)
	ROC (Receiver Operating Characteristic) point.
int	NumDefectiveSample (self)
	Number of defective sample added to the metric.
int	NumGoodSample (self)
	Number of good sample added to the metric.
float	BestAccuracy (self)
	Best achievable accuracy.
float	BestBalancedAccuracy (self)
	Best achievable balanced accuracy.
float	BestAccuracyClassificationThreshold (self)
	Classification threshold giving the best achievable accuracy (see eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.BestAccuracy).
float	BestBalancedAccuracyClassificationThreshold (self)
	Classification threshold giving the best achievable balanced accuracy (see eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.BestBalancedAccuracy).
float	AreaUnderROCCurve (self)
	The area under ROC curve (AUC) of the classifier (see eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.GetROCPoint).
float	AveragePrecision (self)
	Average precision.
float	BestFScore (self)
	Best F1-Score.
float	BestFScoreThreshold (self)
	Classification threshold that yields the best F1-Score.
int	PrecisionRecallCurveIndex (self)
	Index in the precision/recall curve for the current eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.ClassificationThreshold.
int	NumPrecisionRecallCurvePoint (self)
	Number of point in the precision/recall curve.
int	NumberOfClassifiers (self)
	Number of different possible classifiers.
float	ClassificationThreshold (self)
	Classification threshold.
	ClassificationThreshold (self, float value)
	Classification threshold.

Detailed Description

Collection of metrics used to evaluate the state of an eVision.EasyDeepLearning.EUnsupervisedSegmenter.

A metric is a value summarizing the quality of a collection of unsupervised segmentation results (see eVision.EasyDeepLearning.EUnsupervisedSegmenterResult) with respect to their ground truth. New results can be added to the object individually with eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AddResult or collectively with eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AddMetrics.

eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics contains two types of metrics: unsupervised metrics that are computed only on good images and supervised/defect detection metrics that are computed on both good and bad images. The defect detection metrics are accessible only when results for bad images were added to the object. When supervised metrics are accessible, eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.IsTotallyUnsupervised is false.

There is only one unsupervised metric: the error (see eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.Error). See eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics for a description of the defect detection metrics.

Remarks:

License(s): BasicTypes

Constructor & Destructor Documentation

◆ init() [1/2]

None eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.__init__ ( self )

Constructs an eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics object.

◆ init() [2/2]

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

Copy constructor of an eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics object.

Parameters

other Reference to the eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics object that should be copied

Member Function Documentation

◆ AddErrorResult()

None eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AddErrorResult	(		self,
		eVision.EasyDeepLearning.EUnsupervisedSegmenterResult	result )

Adds the given result to the metric for error computation.

The result must be computed from a good image that was corrupted during training.

Parameters

result A reference to an eVision.EasyDeepLearning.EUnsupervisedSegmenterResult object.

◆ AddMetrics()

None eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AddMetrics	(		self,
		eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics	other )

Adds the other metrics to the current metrics of this object.

Parameters

other Unsupervised segmenter metrics

◆ AddResult()

None eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AddResult	(		self,
		eVision.EasyDeepLearning.EUnsupervisedSegmenterResult	result,
		bool	isGoodImage )

Adds the given result with the corresponding ground truth label to the metrics.

Parameters

result	A reference to an eVision.EasyDeepLearning.EUnsupervisedSegmenterResult object.
isGoodImage	True if the ground truth of this result is good, else false.

◆ AverageScoreOnDefectiveImages()

float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AverageScoreOnDefectiveImages ( self )

Gets the average score of defective images.

◆ AverageScoreOnGoodImages()

float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AverageScoreOnGoodImages ( self )

Gets the average score of good images.

◆ Error()

float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.Error ( self )

The error of the segmenter.

This metric is only available in the metrics computed during a training which are accessible through eVision.EasyDeepLearning.EUnsupervisedSegmenter.GetValidationMetrics.

The error, which is also called the loss, is the quantity that is minimized during the training of the deep neural network.

◆ GetBestWeightedAccuracy() [1/2]

float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracy	(		self,
		eVision.EasyDeepLearning.EDataset	dataset )

Best achievable weighted accuracy.

The weighted accuracy is the weighted average of the true positive rate and the true negative rate (which is equal to 1 minus the false positive rate). See eVision.EasyDeepLearning.EROCPoint.

The classification threshold corresponding to this accuracy is given by eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracyClassificationThreshold.

Remarks:

When using a dataset as the source for the label weights, the good weight is the weight of the "good" label and the bad weight is the sum of the weights of all the other labels.

Parameters

dataset Dataset to get the label weight from.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

◆ GetBestWeightedAccuracy() [2/2]

float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracy	(		self,
		float	goodWeight,
		float	badWeight )

Best achievable weighted accuracy.

The weighted accuracy is the weighted average of the true positive rate and the true negative rate (which is equal to 1 minus the false positive rate). See eVision.EasyDeepLearning.EROCPoint.

The classification threshold corresponding to this accuracy is given by eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracyClassificationThreshold.

Remarks:

When using a dataset as the source for the label weights, the good weight is the weight of the "good" label and the bad weight is the sum of the weights of all the other labels.

Parameters

goodWeight	weight of the good label.
badWeight	weight of the bad label.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

◆ GetBestWeightedAccuracyClassificationThreshold() [1/2]

float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracyClassificationThreshold	(		self,
		eVision.EasyDeepLearning.EDataset	dataset )

Classification threshold giving the best achievable weighted accuracy (see eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracy).

Parameters

dataset Dataset to get the label weight from.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

◆ GetBestWeightedAccuracyClassificationThreshold() [2/2]

float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracyClassificationThreshold	(		self,
		float	goodWeight,
		float	badWeight )

Classification threshold giving the best achievable weighted accuracy (see eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracy).

Parameters

goodWeight	Weight for the good label
badWeight	Weight for the bad label

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

◆ IsTotallyUnsupervised()

bool eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.IsTotallyUnsupervised ( self )

Whether this metrics has results from only good images (true) or from both good and defective images (false).

Some metrics are accessible only if eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.IsTotallyUnsupervised is false.

◆ IsValid()

bool eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.IsValid ( self )

Indicates whether the object contains at least one result.

◆ Load() [1/2]

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

Loads an unsupervised segmentation metric.

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

Parameters

serializer The serializer.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

◆ Load() [2/2]

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

Loads an unsupervised segmentation metric.

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

Parameters

path	The file path.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

◆ RemoveErrorResult()

None eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.RemoveErrorResult	(		self,
		eVision.EasyDeepLearning.EUnsupervisedSegmenterResult	result )

Removes the given result from the metric for error computation.

The result must be computed from a good image that was corrupted during training.

Parameters

result A reference to an eVision.EasyDeepLearning.EUnsupervisedSegmenterResult object.

◆ RemoveResult()

None eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.RemoveResult	(		self,
		eVision.EasyDeepLearning.EUnsupervisedSegmenterResult	result,
		bool	isGoodImage )

Removes the given result with the corresponding ground truth label to the metrics.

Parameters

result	A reference to an eVision.EasyDeepLearning.EUnsupervisedSegmenterResult object.
isGoodImage	True if the ground truth of this result is good, else false.

◆ Save() [1/2]

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

Saves an unsupervised segmentation metric.

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

Parameters

serializer The serializer.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

◆ Save() [2/2]

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

Saves an unsupervised segmentation metric.

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

Parameters

path	The file path.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ __init__() [1/2]

◆ __init__() [2/2]

Member Function Documentation

◆ AddErrorResult()

◆ AddMetrics()

◆ AddResult()

◆ AverageScoreOnDefectiveImages()

◆ AverageScoreOnGoodImages()

◆ Error()

◆ GetBestWeightedAccuracy() [1/2]

◆ GetBestWeightedAccuracy() [2/2]

◆ GetBestWeightedAccuracyClassificationThreshold() [1/2]

◆ GetBestWeightedAccuracyClassificationThreshold() [2/2]

◆ IsTotallyUnsupervised()

◆ IsValid()

◆ Load() [1/2]

◆ Load() [2/2]

◆ RemoveErrorResult()

◆ RemoveResult()

◆ Save() [1/2]

◆ Save() [2/2]

◆ init() [1/2]

◆ init() [2/2]