Evaluating Multi-Class Image Classification
4 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Here I written a code for evaluating multi class image classification. Kindly correct if I'm wrong
C=confusionmat(Yactual,YPred)
[row,col]= size(C);
n_class=row;
for i=1:n_class
TP(i)=C(i,i);
FN(i)=sum(C(i,:))-C(i,i);
FP(i)=sum(C(:,i))-C(i,i);
TN(i)=sum(C(:))-TP(i)-FP(i)-FN(i);
end
TP1=sum(TP)
FP1=sum(FP)
FN1=sum(FN)
TN1=sum(TN)
Accuracy=(TP1+TN1)/(TP1+TN1+FP1+FN1)
Error=1-Acc
Recall=TP1/(TP1+FN1)
Precision=TP1/(TP1+FP1)
Specificity = TN1/(TN1+FP1)
Sensitivity = TP1/(TP1+FN1)
FPR=1-Specificity
beta=1;
F1_score=( (1+(beta^2))*(Recall.*Precision)) ./ ( (beta^2)*(Precision+Recall))
I want to know above code is correct or not?
and also when I'm using accuracy = mean(YPred == Yactual) it gives precision value. why?
kindly help me in this regard. Thank you.
0 Kommentare
Antworten (0)
Siehe auch
Kategorien
Mehr zu Get Started with Statistics and Machine Learning Toolbox finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!