How to improve my graph?

3 次查看（过去 30 天）

Adrian Kleffler 2023-5-22

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1970274-how-to-improve-my-graph

评论： Ranjeet 2023-6-1

Hello guys, I made an object detector YOLOv4 and after runnin this code:

[ap,recall,precision] = evaluateDetectionPrecision(detectionResults,testData);
recallv = cell2mat(recall);
precisionv = cell2mat(precision);
[r,index] = sort(recallv);
p = precisionv(index);
figure
plot(r,p)
xlabel("Recall")
ylabel("Precision")
grid on
title(sprintf("Average Precision = %.2f",mean(ap)))

My graph looks like this :

But in Matlab example their graph looks like this :

I have 5 classes in my object detector...

What can be wrong ? Thanks for help

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Ranjeet 2023-6-1

Hi Adrian,

Testing the following script in R2022b, I do not face any issues.

https://www.mathworks.com/help/vision/ug/object-detection-using-yolov4-deep-learning.html

However, I wanted to ask "Why are you using cell2mat with recall and precision? They are already be a returned as a vector and not cell. Is the operation not throwing any error?"

Also, providing the script that is being used for training might help.

请先登录，再进行评论。

请先登录，再回答此问题。