GlobalAccuracy- 正确分类像素与总像素的比率，无论类别如何。

卑鄙的准确性- 每个类中正确分类的像素与总像素的比率，在所有类上平均。值等于ClassMetrics.Accuracy。

MeanIoU— Average intersection over union (IoU) of all classes. The value is equal to the mean ofClassMetrics.IoU。

WeightedIoU- 所有课程的平均值，由类中的像素数量加权。

MeanBFScore- 所有图像的平均边界F1（BF）得分。值等于ImageMetrics。BFScore。创建一个指标，当您创建一个指标semanticSegmentationMetricsobject by using a confusion matrix as the input toevaluateSemanticSegmentation。

准确性— Ratio of correctly classified pixels in each class to the total number of pixels belonging to that class according to the ground truth. Accuracy can be expressed as:

TP：真正的阳性和FN是虚假负面的数量。

iou— Ratio of correctly classified pixels to the total number of pixels that are assigned that class by the ground truth and the predictor. IoU can be expressed as:

该图像描述了真实的阳性（TP），误报（FP）和假阴性（FN）。

MeanBFScore- 每个班级的边界F1得分，平均在所有图像上。创建一个指标，当您创建一个指标semanticSegmentationMetricsobject by using a confusion matrix as the input toevaluateSemanticSegmentation。

GlobalAccuracy- 正确分类像素与总像素的比率，无论类别如何。

卑鄙的准确性— Ratio of correctly classified pixels to total pixels, averaged over all classes in the image.

MeanIoU— Average IoU of all classes in the image.

WeightedIoU— Average IoU of all classes in the image, weighted by the number of pixels in each class.

MeanBFScore— Average BF score of each class in the image. This metric is not available when you create asemanticSegmentationMetricsobject by using a confusion matrix as the input toevaluateSemanticSegmentation。