how can I replace the softmax layer with another classifier as svm in convolution network

I made deep learning application that using softmax

layers = [ imageInputLayer(varSize); conv1; reluLayer;

    convolution2dLayer(5,32,'Padding',2,'BiasLearnRateFactor',2);
    reluLayer()

    maxPooling2dLayer(4,'Stride',2);

    convolution2dLayer(5,32,'Padding',2,'BiasLearnRateFactor',2);
    reluLayer()

    maxPooling2dLayer(2,'Stride',2);

    convolution2dLayer(5,64,'Padding',2,'BiasLearnRateFactor',2);
    reluLayer();
    maxPooling2dLayer(4,'Stride',2)

    fc1;
    reluLayer();
    fc2;
    reluLayer();

    %returns a softmax layer for classification problems. The softmax layer uses the softmax activation function.
    softmaxLayer()
    classificationLayer()];

I want to use SVM and random forest classifiers instead of softmax. and use a deep learning for feature extraction. I hope I can get a link for a tutorial.

[mona benhari]

I have the same problemI have you got the answer?

Answer 1

[Johannes Bergstrom]

Here is an example: https://www.mathworks.com/help/nnet/examples/feature-extraction-using-alexnet.html

[Suheer Ali]

Thanks for your answer but I don't want to use pre-trained models. I want to design mine and use it as a feature extraction.

Answer 2

[Nagwa megahed]

the only possible solution is to save the extracted features by the deep model , then use this features as an input to the SVM or any other wanted classifier.

[amel yasser]

or he can freeze the result and add SVM classifier

Answer 3

[Saifullah Razali]

hello.. just wondering.. have u got the answer yet? i have the same exact problem

Answer 4

[Mahzad Pirghayesh]

I have the same problem too,can any body help us