0
$\begingroup$

I am doing multi-class classification and comparing the effects of 2 image enhancement techniques (IET). IET 1 performs better than IET 2 at random seed x (for train-test-val split) IET 2 performs better than IET 1 at random seed y (for train-test-val split)

Is this normal, or am I doing something wrong?

$\endgroup$
0
$\begingroup$

Yes, it can depend on it because it changes the data distribution with the network is trained.

You shouldn't consider random seed as a hyperparameter. Keep the same random seed and run comparison. Do this for at least 5 or 10 random seeds. You will definitely have a winner. If you don't go for more than 10 unless you get a winner. That will give you sufficient proof about the efficacy of the method. Otherwise since one is good in random seed or other one in other, just choose one of those random seeds, choose the method that gives best in it and continue your work.

$\endgroup$

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.