precision-recall curve for faster rcnn
9 ビュー (過去 30 日間)
古いコメントを表示
hi
i want to find precision-recall curve of my tranied faster rcnn detector.i tried thi code
testData = transform(testData,@(data)preprocessData(data,inputSize));
detectionResults = detect(detector,testData,'MinibatchSize',4);
classID = 1;
metrics = evaluateObjectDetection(detectionResults,testData);
precision = metrics.ClassMetrics.Precision{classID};
recall = metrics.ClassMetrics.Recall{classID};
figure
plot(recall,precision)
xlabel('Recall')
ylabel('Precision')
grid on
title(sprintf('Average Precision = %.2f', metrics.ClassMetrics.mAP(classID)))
but it shows error on evaluateObjectDetection that this is not in matlab second is that it show error that dot errorr is not worked in this( metrics.ClassMetrics.Precision{classID};)
so is there any other way to find precission-recall for multiple classes
0 件のコメント
採用された回答
Walter Roberson
2023 年 11 月 28 日
https://www.mathworks.com/help/vision/ref/evaluateobjectdetection.html was introduced in R2023b, but you have R2023a.
There are no functions available in R2023a that return metrics.
0 件のコメント
その他の回答 (0 件)
参考
カテゴリ
Help Center および File Exchange で Image and Video Ground Truth Labeling についてさらに検索
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!