evaluateSemanticSegmentation
Evaluate semantic segmentation data set against ground truth
Syntax
Description
computes various metrics to evaluate the quality of the semantic segmentation results from confusion matrices,SSM
= evaluateSemanticSegmentation(imageSetConfusion
,classNames
)imageSetConfusion
, with segmentation classesclassNames
。
[
computes various metrics to evaluate the quality of the block-based semantic segmentation results from confusion matrices,SSM
,blockMetrics
] = evaluateSemanticSegmentation(BlocksetConfusion
,classNames
)BlocksetConfusion
with classesclassNames
。
[___] = evaluateSemanticSegmentation(___,
computes semantic segmentation metrics using one or more姓名,Value
)姓名,Value
pair arguments to control the evaluation.
Examples
Input Arguments
输出参数
Tips
A value of
NaN
in the dataset, class, or image metrics, indicates that one or more classes were missing during the computation of the metrics when using theevaluateSemanticSegmentation
function. In this case, the software was unable to accurately compute the metrics.可以通过查看丢失的课程来找到
ClassMetrics
属性,为每个类提供指标。要更准确地评估您的网络,请使用包括缺失类别的更多数据来增强地面真相。
References
[1] Csurka, G., D. Larlus, and F. Perronnin. "What is a good evaluation measure for semantic segmentation?"Proceedings of the British Machine Vision Conference, 2013, pp. 32.1–32.11.