I have seen U-Nets that use a single convolution before the pooling operator and some that use two or more.

My question is, what is better? Or what are the benefits of using more or less convolutions?

  • 1
    $\begingroup$ Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. $\endgroup$
    – Community Bot
    May 28 at 22:28
  • 1
    $\begingroup$ Can you please provide links to these U-net versions that you're mentioning? $\endgroup$
    – nbro
    May 29 at 8:52


You must log in to answer this question.

Browse other questions tagged .