Azzera filtri
Azzera filtri

Custom Layer- Incorrent number of outputs

5 visualizzazioni (ultimi 30 giorni)
I'm trying to create a custom intermediate layer that can split up data. When I use checkLayer to validate the functionality it throws the error: "Incorrect number of output arguments for 'predict' in Layer splitDataLayer. Expected to have 1, but instead it has 4." although I've set the number of Outputs to 4 in the constructor.
classdef splitDataLayer < nnet.layer.Layer
function obj = splitDataLayer(name)
obj.Name = name;
obj.numOutputs = 4;
obj.OutputNames = {'out1','out2','out3','out4'};
function [Z1, Z2, Z3, Z4] = predict(~, X)
Z1 = X(1, :, :, :);
Z2 = X(2, :, :, :);
Z3 = X(3, :, :, :);
Z4 = X(4, :, :, :);
function [dLdX] = backward(~,~,~,~,~,~,dLdZ1,dLdZ2,dLdZ3,dLdZ4,~)
dLdX = cat(1, dLdZ1,...
As can be seen above, both the number of outputs as well as the output matrix in the predict function have been set correctly. So I don't know what could be wrong about the code and cause that error.
I would be happy for any help!

Risposta accettata

Maria Duarte Rosa
Maria Duarte Rosa il 9 Ago 2019
Hi Valentin,
Thank you for your question.
Multi-input/Multi-output custom layers are supported from R2019a. From your error message I suspect you are on a older release.
Your layer looks good though, apart from obj.numOutputs = 4; which should be obj.NumOutputs = 4;
When I correct for that all the checkLayer tests pass in R2019a:
layer = splitDataLayer('test');
validInputSize = [4 5 20 4]; % Some arbitrary dimensions
Running nnet.checklayer.TestCase
.......... .......... ....
Done nnet.checklayer.TestCase
Test Summary:
24 Passed, 0 Failed, 0 Incomplete, 0 Skipped.
Time elapsed: 1.3818 seconds.
I hope this helps.
  1 Commento
Valentin Steininger
Valentin Steininger il 9 Ago 2019
Hi Maria,
I also just realized that it's not available on 2018b as I tried the "custom weighted addition layer" example from the documenation and it threw the same error.
I'm just about to upgrade to 2019a.
Thanks for the answer!

Accedi per commentare.

Più risposte (0)


Scopri di più su Sequence and Numeric Feature Data Workflows in Help Center e File Exchange




Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by