Is it possible to use non-image data as inputs for the Deep Network Designer App?

I have a 3xn vector of inputs that I would like to use with the Deep Network Designer app. However, it seems that the input layers are generally geared towards image classification. Is there a way to use the numerical data in matrix format as inputs?

Thank you.

Answer 1

[Ive J]

Technically yes you can, I assume something like this would work:

dlData = reshape(data', [1, 1, size(data, 2), size(data, 1)]); 

then your layers would be something like:

layers = [imageInputLayer([1 1 size(data, 2)]);
          % other layers
          ];

[Michael McGeehan]

Thanks for your response. The data options for the input layer require me to specify a folder with images. Is there any way around this?