Accuracy between from the equation and the validation accuracy

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);

Answer 1

[Sahil Jain]

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;