Jump to content

Convolutional neural network: Difference between revisions

 
Line 114: Line 114:
** \(p=\frac{k-1}{2}\)
** \(p=\frac{k-1}{2}\)
** Exact behavior varies between ML frameworks. Only apply this when you know you will have symmetric padding on both sides.
** Exact behavior varies between ML frameworks. Only apply this when you know you will have symmetric padding on both sides.
A common conv layer would use a 3x3 kernel with stride 1 and padding 1.


===Dilation===
===Dilation===