Valid Convolution or valid padding

[diptiman.badajena]

In Week-1 lecture “Simple Convolutional Network Example CORRECTION”, it’s mentioned "p=0 means valid convolutions instead of same convolutions. ".

Should it be referred as “Valid padding” and when “p != 0” it’s referred as “Same padding” ?

[jonaslalin]

See my answer here:

Padding to 0. Same vs Valid

For same padding, \begin{aligned} (n + 2p -f) / s + 1 &= n \Leftrightarrow \\ n + 2p - f &= (n - 1) * s \Leftrightarrow \\ p &= ((n - 1) * s + f - n) / 2. \end{aligned} With your example: \begin{aligned} p &= ((39 - 1) * 1 + 3 - 39) / 2 \Rightarrow \\ p &= (38 + 3 - 39) /2 \Rightarrow \\ p &= 1. \end{aligned} Thus, if the padding is 1, you will have the same output size as the input size, hence it is called same convolution. To double check (n + 2p -f) / s + 1 = (39 + 2 * 1 - 3) / 1 + 1…