EROCPoint Struct
The structure representing a point on the ROC (Receiver Operating Characteristic) curve.
Namespace: Euresys::Open_eVision::EasyDeepLearning
Properties
The True Positive Rate: it is the number of defective images classified as defective, normalized by the number of defective images.
The TPR can be NaN (Not A Number) if the metrics were computed using only good images.
The TPR can be NaN (Not A Number) if the metrics were computed using only good images.
The True Positive count: it is the number of defective images classified as defective.
The Positive count: it is the number of defective images.
The False Positive Rate: it is the number of good image classified as defective, normalized by the number of good images.
The False Positive count: it is the number of good image classified as defective.
The Negative count: it is the number of good images.
The threshold associated with the true and false positive rates (see EUnsupervisedSegmenter::ClassificationThreshold).
Methods
Loads the ROC point. The given ESerializer must have been created for reading.
Saves the ROC point. The given ESerializer must have been created for writing.
EROCPoint Struct
The structure representing a point on the ROC (Receiver Operating Characteristic) curve.
Namespace: Euresys.Open_eVision.EasyDeepLearning
Properties
The False Positive count: it is the number of good image classified as defective.
The False Positive Rate: it is the number of good image classified as defective, normalized by the number of good images.
The Negative count: it is the number of good images.
The Positive count: it is the number of defective images.
The threshold associated with the true and false positive rates (see EUnsupervisedSegmenter::ClassificationThreshold).
The True Positive count: it is the number of defective images classified as defective.
The True Positive Rate: it is the number of defective images classified as defective, normalized by the number of defective images.
The TPR can be NaN (Not A Number) if the metrics were computed using only good images.
The TPR can be NaN (Not A Number) if the metrics were computed using only good images.
Methods
Loads the ROC point. The given ESerializer must have been created for reading.
Saves the ROC point. The given ESerializer must have been created for writing.