The formula to determine the output size is [(W−K+2P)/S]+1. Here the number of filters used is not significant for determining the ouput size, I was wondering why?

Is it because Each filter is separately applied to the input to obtain a feature map and the output of the that part is considered as dimension size?

Please note:

  • W refers to the input size, K refers to the filter size where as P stands for padding and S stands for stride
  • 1
    $\begingroup$ Can you please define the variables? Not all people use the same letters for these parameters. $\endgroup$
    – Kota Mori
    Sep 10 '21 at 11:17
  • $\begingroup$ Updated the question with terms explained $\endgroup$ Sep 10 '21 at 11:34

The formula you've given is for 1 filter. If you have $N$ filters, then you have $N$ outputs of the size you describe.


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.