Pretrained networks in matlab for extraction of deep features from images

I have found the Pretrained networks list in matlab documentation. I want to use a pretrained network for binary classification. The input is a 32x32 image patch.

In the documentation the minimum input size found is 224x224. How can I use my 32x32 image patch in this? Which is the good pretrained network for binary classification. I just started learning deep learning. Please help me with this.

Answer 1

[Shounak Mitra]

Try using imresize() to scale your image to fit the network dimensions.

Usage Example:

% Access the trained model 
net = alexnet 
% See details of the architecture 
net.Layers 
% Read the image to classify 
I = imread('peppers.png'); 
% Adjust size of the image 
sz = net.Layers(1).InputSize 
I = I(1:sz(1),1:sz(2),1:sz(3)); 
% Classify the image using AlexNet 
label = classify(net, I) 
% Show the image and the classification results 
figure 
imshow(I) 
text(10,20,char(label),'Color','white')

To learn more about Transfer Learning, refer https://www.mathworks.com/help/deeplearning/examples/transfer-learning-using-alexnet.html