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

Inheritance diagram for eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics:

[legend]

Collaboration diagram for eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics:

[legend]

Public Member Functions
	EUnsupervisedSegmenterMetrics ()
	Constructs an EUnsupervisedSegmenterMetrics object.
	EUnsupervisedSegmenterMetrics (eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics other)
	Copy constructor of an EUnsupervisedSegmenterMetrics object.
bool	IsTotallyUnsupervised ()
	Whether this metrics has results from only good images (true) or from both good and defective images (false).
bool	IsValid ()
	Indicates whether the object contains at least one result.
override void	Load (string path)
	Loads an unsupervised segmentation metric. The given ESerializer must have been created for reading.
override void	Load (eVision.ESerializer serializer)
	Loads an unsupervised segmentation metric. The given ESerializer must have been created for reading.
override void	Save (string path)
	Saves an unsupervised segmentation metric. The given ESerializer must have been created for writing.
override void	Save (eVision.ESerializer serializer)
	Saves an unsupervised segmentation metric. The given ESerializer must have been created for writing.
void	AddResult (eVision.EasyDeepLearning.EUnsupervisedSegmenterResult result, bool isGoodImage)
	Adds the given result with the corresponding ground truth label to the metrics.
void	AddErrorResult (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.
void	RemoveResult (eVision.EasyDeepLearning.EUnsupervisedSegmenterResult result, bool isGoodImage)
	Removes the given result with the corresponding ground truth label to the metrics.
void	RemoveErrorResult (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.
void	AddMetrics (eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics other)
	Adds the other metrics to the current metrics of this object.
new float	GetBestWeightedAccuracy (float goodWeight, float badWeight)
	Best achievable weighted accuracy.
float	GetBestWeightedAccuracy (eVision.EasyDeepLearning.EDataset dataset)
	Best achievable weighted accuracy.
new float	GetBestWeightedAccuracyClassificationThreshold (float goodWeight, float badWeight)
	Classification threshold giving the best achievable weighted accuracy (see EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracy).
float	GetBestWeightedAccuracyClassificationThreshold (eVision.EasyDeepLearning.EDataset dataset)
	Classification threshold giving the best achievable weighted accuracy (see EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracy).
Public Member Functions inherited from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics
	EDeepLearningDefectDetectionMetrics ()
	Constructs an empty EDeepLearningDefectDetectionMetrics object.
	EDeepLearningDefectDetectionMetrics (eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics other)
	Copy constructor.
bool	IsDefectDetectionMetricsValid ()
	Whether the defect detection metrics are valid or not. Defect detection metrics are completely valid when the metrics has results for at least one good and one defective images. Some metrics might be valid with only defective or good results.
float	GetAccuracy (int index)
	The accuracy of the segmenter.
float	GetAccuracy ()
	The accuracy of the segmenter.
float	GetBestWeightedAccuracy (float goodWeight, float badWeight)
	Best achievable weighted accuracy.
float	GetBestWeightedAccuracyClassificationThreshold (float goodWeight, float badWeight)
	Classification threshold giving the best achievable weighted accuracy (see EDeepLearningDefectDetectionMetrics.GetBestWeightedAccuracy).
uint	GetConfusion (eVision.EasyDeepLearning.EConfusionMatrixElement element, int index)
	Confusion value of one label with another.
uint	GetConfusion (eVision.EasyDeepLearning.EConfusionMatrixElement element)
	Confusion value of one label with another.
float	GetRecall (int index)
	Recall for the current threshold.
float	GetRecall ()
	Recall for the current threshold.
float	GetPrecision (int index)
	Precision for the current threshold.
float	GetPrecision ()
	Precision for the current threshold.
float	GetFScore (int index)
	The F1-Score for the current threshold.
float	GetFScore ()
	The F1-Score for the current threshold.
eVision.EasyDeepLearning.EROCPoint	GetPrecisionRecallCurvePoint (int index)
	Get a point on the precision/recall curve.
eVision.EasyDeepLearning.EROCPoint	GetPrecisionRecallCurvePoint ()
	Get a point on the precision/recall curve.
eVision.EasyDeepLearning.EROCPoint	GetROCPoint (int index)
	ROC (Receiver Operating Characteristic) point.
eVision.EasyDeepLearning.EROCPoint	GetROCPoint ()
	ROC (Receiver Operating Characteristic) point.

Properties
float	Error `[get]`
	The error of the segmenter.
float	AverageScoreOnGoodImages `[get]`
	Gets the average score of good images.
float	AverageScoreOnDefectiveImages `[get]`
	Gets the average score of defective images.
Properties inherited from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics
int	NumDefectiveSample `[get]`
	Number of defective sample added to the metric.
int	NumGoodSample `[get]`
	Number of good sample added to the metric.
float	BestAccuracy `[get]`
	Best achievable accuracy.
float	BestBalancedAccuracy `[get]`
	Best achievable balanced accuracy.
float	BestAccuracyClassificationThreshold `[get]`
	Classification threshold giving the best achievable accuracy (see EDeepLearningDefectDetectionMetrics.BestAccuracy).
float	BestBalancedAccuracyClassificationThreshold `[get]`
	Classification threshold giving the best achievable balanced accuracy (see EDeepLearningDefectDetectionMetrics.BestBalancedAccuracy).
float	AreaUnderROCCurve `[get]`
	The area under ROC curve (AUC) of the classifier (see EDeepLearningDefectDetectionMetrics.GetROCPoint). It's value is between 0 and 1.
float	AveragePrecision `[get]`
	Average precision.
float	BestFScore `[get]`
	Best F1-Score.
float	BestFScoreThreshold `[get]`
	Classification threshold that yields the best F1-Score.
int	PrecisionRecallCurveIndex `[get]`
	Index in the precision/recall curve for the current EDeepLearningDefectDetectionMetrics.ClassificationThreshold.
int	NumPrecisionRecallCurvePoint `[get]`
	Number of point in the precision/recall curve.
int	NumberOfClassifiers `[get]`
	Number of different possible classifiers.
float	ClassificationThreshold `[get, set]`
	Classification threshold.

Detailed Description

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

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

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, EUnsupervisedSegmenterMetrics.IsTotallyUnsupervised is false.

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

License(s): BasicTypes

Constructor & Destructor Documentation

◆ EUnsupervisedSegmenterMetrics() [1/2]

eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.EUnsupervisedSegmenterMetrics ( )

Constructs an EUnsupervisedSegmenterMetrics object.

◆ EUnsupervisedSegmenterMetrics() [2/2]

eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.EUnsupervisedSegmenterMetrics ( eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics other )

Copy constructor of an EUnsupervisedSegmenterMetrics object.

Parameters

other Reference to the EUnsupervisedSegmenterMetrics object that should be copied

Member Function Documentation

◆ AddErrorResult()

void eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AddErrorResult ( 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 EUnsupervisedSegmenterResult object.

◆ AddMetrics()

void eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AddMetrics ( eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics other )

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

Parameters

other Unsupervised segmenter metrics

◆ AddResult()

void eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AddResult	(	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 EUnsupervisedSegmenterResult object.
isGoodImage	True if the ground truth of this result is good, else false.

◆ GetBestWeightedAccuracy() [1/2]

float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracy ( 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 EROCPoint.

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

Parameters

dataset Dataset to get the label weight from.

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.

◆ GetBestWeightedAccuracy() [2/2]

new float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.GetBestWeightedAccuracy	(	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 EROCPoint.

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

Parameters

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

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.

◆ GetBestWeightedAccuracyClassificationThreshold() [1/2]

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

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

Parameters

dataset Dataset to get the label weight from.

◆ GetBestWeightedAccuracyClassificationThreshold() [2/2]

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

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

Parameters

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

◆ IsTotallyUnsupervised()

bool eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.IsTotallyUnsupervised ( )

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

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

◆ IsValid()

bool eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.IsValid ( )

Indicates whether the object contains at least one result.

◆ Load() [1/2]

override void eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.Load ( eVision.ESerializer serializer )

virtual

Loads an unsupervised segmentation metric. The given ESerializer must have been created for reading.

Parameters

serializer The serializer.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

◆ Load() [2/2]

override void eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.Load ( string path )

virtual

Loads an unsupervised segmentation metric. The given ESerializer must have been created for reading.

Parameters

path	The file path.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

◆ RemoveErrorResult()

void eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.RemoveErrorResult ( 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 EUnsupervisedSegmenterResult object.

◆ RemoveResult()

void eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.RemoveResult	(	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 EUnsupervisedSegmenterResult object.
isGoodImage	True if the ground truth of this result is good, else false.

◆ Save() [1/2]

override void eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.Save ( eVision.ESerializer serializer )

virtual

Saves an unsupervised segmentation metric. The given ESerializer must have been created for writing.

Parameters

serializer The serializer.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

◆ Save() [2/2]

override void eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.Save ( string path )

virtual

Saves an unsupervised segmentation metric. The given ESerializer must have been created for writing.

Parameters

path	The file path.

Reimplemented from eVision.EasyDeepLearning.EDeepLearningDefectDetectionMetrics.

Property Documentation

◆ AverageScoreOnDefectiveImages

float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AverageScoreOnDefectiveImages

get

Gets the average score of defective images.

◆ AverageScoreOnGoodImages

float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.AverageScoreOnGoodImages

get

Gets the average score of good images.

◆ Error

float eVision.EasyDeepLearning.EUnsupervisedSegmenterMetrics.Error

get

The error of the segmenter.

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

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

Public Member Functions

Properties

Detailed Description

Constructor & Destructor Documentation

◆ EUnsupervisedSegmenterMetrics() [1/2]

◆ EUnsupervisedSegmenterMetrics() [2/2]

Member Function Documentation

◆ AddErrorResult()

◆ AddMetrics()

◆ AddResult()

◆ 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]

Property Documentation

◆ AverageScoreOnDefectiveImages

◆ AverageScoreOnGoodImages

◆ Error