Hi,
Is there any particular reason why I can't use padding of zero in convolve2NN() to get a valid convolution? Right now, the padding argument must not contain any non-zero elements, which feels overly restrictive to me.
Thanks for any insights you can give me.
Regards,
Gé Vissers
Hi,
Is there any particular reason why I can't use padding of zero in convolve2NN() to get a valid convolution? Right now, the padding argument must not contain any non-zero elements, which feels overly restrictive to me.
Thanks for any insights you can give me.
Regards,
Gé Vissers