why am I getting worst results when using CNN for feature extraction and SVM for classification

Question

I am using 3d cnn for feature extraction and svm for classification But I got worst results then using the 3d cnn for both feature extraction and classification is that a normal thing ?

Answer 1

There is no one method that always works best. (Google the "No Free Lunch" theorem.)

That means that, conversely, different tools work best in different situations.

And that of course also applies to entire pipelines of tools.

So no, this is not strange at all. You would need to dig more deeply into your task, your data and your notion of "working well" to understand whether there is anything systematic as to why one method would work better in your particular situation.