0
$\begingroup$

VGG16 As famous model VGG16 shows(and other famous models), The convolutional layers before pooling usually have the same input and output channel sizes? What's the reason for that? Is there a theory or papers trying to explain this kind of settings?

$\endgroup$
  • $\begingroup$ What do you mean by input and output channel sizes? $\endgroup$ – nbro Jun 10 '19 at 13:42
0
$\begingroup$

Keeping the same channel size allows the model to maintain rank but i would say the main reason is convenience. Its easier book keeping.

Also in many model cases output features need some form of alignment with the input (example being all models using residual units -- $\hat{x} = F(x) + x$

|improve this answer|||||
$\endgroup$
  • $\begingroup$ What do you mean by "rank" in this context? It is also not clear the question because the depth of the input and output volumes are usually different. $\endgroup$ – nbro Jun 10 '19 at 17:11
  • $\begingroup$ also good point about alignment because GPU and CPU vector ops need this $\endgroup$ – user8426627 Jun 10 '19 at 17:54

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.