How to decide the padding size and stride size in CNN

Question

In CNN in 2d, what situation is the size of the padding and stride changed in?

So far, I could make sense of the basic concepts with padding and stride.

Padding and stride can be used to adjust the dimensionality of the data effectively. https://d2l.ai/chapter_convolutional-neural-networks/padding-and-strides.html

On the one hand, the examples I had confirmed seemed to use padding = 1 and stride = 1.

My question is

1. Using padding = 1 and stride = 1 is the basic and common method?
2. What situation do we adjust padding and stride size to over 1 in?

Answer 1

Take a text classification as an example:

If you just look at one word at a time, you might not get the "meaning" of the word e.g the word run. But if you include two words at a time then you get the context e.g didn't run which is the oposite of did run.

Here we have stride=2 since we stride/include 2 words at a time and not one.

When to use what padding/striding is defined by your data and model.