How to Classify New Dataset using Two trained models

I have trained two models on a dataset

I want to Classify new data using the both the trained model. But Classify take one trained network. How can i do that?

Resnet50.mat
Resnet18.mat


rxTestPred = classify(resnet.trainedNet,rxTestFrames);
testAccuracy = mean(rxTestPred == rxTestLabels);
disp("Test accuracy: " + testAccuracy*100 + "%")

[KSSV]

Question is not clear. What problem you have in using the trained model ofr new data?

[hammad younas]

@KSSV I want to Classify rxTestFrames using Two trained Model one is Resnet18 and other is Resnet50

Answer 1

[yanqi liu]

yes，sir，may be use different load variable，such as

net1 = load('Resnet50.mat')
net2 = load('Resnet18.mat')


rxTestPred = classify(net1.resnet.trainedNet,rxTestFrames);
testAccuracy = mean(rxTestPred == rxTestLabels);
disp("Resnet50 Test accuracy: " + testAccuracy*100 + "%")

rxTestPred = classify(net2.resnet.trainedNet,rxTestFrames);
testAccuracy = mean(rxTestPred == rxTestLabels);
disp("Resnet18 Test accuracy: " + testAccuracy*100 + "%")

[Med Future]

@yanqi but the prediction are different, i want two models to give combine prediction. Not each model to give its prediction like you can say ensemble learning /majority voting

[Nagwa megahed]

please i ask if you reach to how implement ensemble learning in matlab ?? as i need to perform ensemble learning between more than three different networks

[David Willingham]

See this page for information on how to work with multi-input multi-output networks in MATLAB: Multiple-Input and Multiple-Output Networks