3
$\begingroup$

I have a data input vector ( No Image classification) which size varys from 2 to 7 entrys. Every one of them belongs to a class Out of 7. So I have a variable Input size and a variable Output size. How can I deal with the variable Input sizes? I know Zero padding is a option but maybe there are better ways?

Seconds: Is multi Label classification possible in one Network? What I mean: The first entry has to bei classified in one of the seven classes, the second entry... and so on.

I am also open to other classification techniques, If there is a better one that suits the problem.

Best regards, Gesetzt

$\endgroup$

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.