Hi. I am using mse funtion to find the mse of my network. In my opinion mse should change for every input.once i save the network and reload it. the mse command doesnt work and produces error.kindly help

1 Ansicht (letzte 30 Tage)
if true
[baboon_fit,tr]=train(baboonnet,input,target);
output=sim(baboon_fit,input);
MeansqEr= mse(baboon_fit,target,output)
save baboon_fit
%in new program
load baboon_fit
output=sim(baboon_fit,newinput);
MeansqEr= mse(baboon_fit,target,output)
end
%Function 'subsindex' is not defined for values of class 'network' error message is displayed.

Akzeptierte Antwort

Greg Heath
Greg Heath am 24 Aug. 2017
Just use
MSE = mse(target-output)
Hope this helps.
Thank you for formally accepting my answer
Greg
P.S. You can also just use
output = baboon_fit(newinput);

Weitere Antworten (0)

Kategorien

Mehr zu Deep Learning Toolbox finden Sie in Help Center und File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by