Regarding Input shape of data into CNN deep learning extension

varunm1

Hello

In the current deep learning extension, how is the input shape of CNN considered? In tensorflow, when I train images(converted to pixels) the shape of an array is (nb_samples, rows, columns, channels) for a 2d Conv. How will this happen in CNN of RM? Can we specify the samples? Is there a different convolution 1D or 2D or 3D option that can be chosen which I didn't find in the operator. 

@hughesfleming68 any input on this?

Thanks,
Varun

hughesfleming68

Hi Varun, unfortunately I don't have an answer. Perhaps @pschlunder could explain. I have only just started to scratch the surface with some CNN tests on time series problems with DL4J. If anything, I should be asking you questions not the other way around. Have you taken a look at the DL4J documentation and cheat sheets? https://deeplearning4j.org/docs/latest/deeplearning4j-cheat-sheet#layers-conv

varunm1

Hi @hughesfleming68

I have gone through the document, thanks for sharing. It says that normal convolution operator is a 2D, but I am not sure how it's taking (nb_samples,channels, image_rows, image_columns) values. Will try to check it out.

Thanks,
Varun

varunm1

@pschlunder can you provide some insights on this? Thanks