I'm trying to make a neural network that takes a 16x100x100 matrix and splits it into each 100x100 part, puts each through a dense layer, and then puts them them together once again to form a 16x10x10 matrix. I'm running into a bit of trouble just creating the NetModel.

Is there any easier way than sending the input to 16 PartLayers and then each PartLayer to a LinearLayer?

  • 1
    $\begingroup$ Have you looked at NetMapOperator? $\endgroup$ – Carl Lange Jun 24 '19 at 6:22

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.