Accuracy between from the equation and the validation accuracy

1 vue (au cours des 30 derniers jours)
TAN HOR YAN
TAN HOR YAN le 13 Oct 2021
What is the different between the accuracy by using the Accuracy = sum ( diag (C)) / sum (C (:)) ×100 and the validation accuracy which run by the following coding:
[XTrain,YTrain] = digitTrain4DArrayData;
idx = randperm(size(XTrain,4),403);
XValidation = XTrain(:,:,:,idx);
XTrain(:,:,:,idx) = [];
YValidation = YTrain(idx);
YTrain(idx) = [];
layers = [
imageInputLayer([28 28 1])
convolution2dLayer(3,8,'Padding','same')
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(3,16,'Padding','same')
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(3,32,'Padding','same')
batchNormalizationLayer
reluLayer
fullyConnectedLayer(10)
softmaxLayer
classificationLayer];
options = trainingOptions('sgdm', ...
'MaxEpochs',8, ...
'ValidationData',{XValidation,YValidation}, ...
'ValidationFrequency',30, ...
'Verbose',false, ...
'Plots','training-progress');
NET = trainNetwork(XTrain,YTrain,layers,options);

Réponses (1)

Sahil Jain
Sahil Jain le 18 Oct 2021
Hi. You have not mentioned what "C" is. Assuming that "C" is the confusion matrix, accuracy values evaluated using both the approaches are equivalent and give the same result. Upon replacing the last line of your code with the following, you can observe that "accuracy1" and "accuracy2" both have the same value.
[NET, info] = trainNetwork(XTrain,YTrain,layers,options);
YPred = classify(NET, XValidation);
C = confusionmat(YValidation, YPred);
accuracy1 = sum (diag (C))/sum (C(:))*100;
accuracy2 = info.FinalValidationAccuracy;

Catégories

En savoir plus sur Deep Learning Toolbox dans Help Center et File Exchange

Produits


Version

R2020b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by