I am thinking about developing a GAN.

What is the difference between using dense layers as opposed to convolutional layers in my networks when dealing with images?

  • 1
    $\begingroup$ Difference w.r.t what? Performance, speed, memory, etc etc? I think you should edit it in the question. $\endgroup$ – DuttaA Apr 3 '20 at 1:08
  • 1
    $\begingroup$ In general, conv layers are able to learn spatial relationships more efficiently and to a better degree. The specifics are more complicated. $\endgroup$ – Recessive Apr 3 '20 at 1:16
  • $\begingroup$ Hi and welcome to AI SE! This question is indeed a bit unclear. You mention the GAN, but why is it relevant? Are you interested in 1. the structural differences between dense layers and convolutional layers, 2. the functional difference or, 3. both the structural and functional differences? Also, are you interested in some particular context? Again, why do you mention the GAN? What is your goal and why do you want to know the "difference" between the two? $\endgroup$ – nbro Apr 7 '20 at 1:28

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.