You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I read your paper and like it. but I have a one question.
In this equation(3), there is (2d-1)^2 operations.
It is depth-wise convolution so I think this may be (2d-1)^2 * C.
why the number of parameter is (2d-1)^2? Am I misunderstanding about LKA structure?
The text was updated successfully, but these errors were encountered:
Hi @sihyeong671
I am not one of the authors, but I also found a mistake in the formula. The correct formula for Parameter count should be:
P(K,d) =C((K/d)^2+(2d-1)^2+3+C). This formula also gives the fitting number with the table of the paper. Hope this helps you.
I read your paper and like it. but I have a one question.
In this equation(3), there is (2d-1)^2 operations.
It is depth-wise convolution so I think this may be (2d-1)^2 * C.
why the number of parameter is (2d-1)^2? Am I misunderstanding about LKA structure?
The text was updated successfully, but these errors were encountered: