Guocheng Wei

I will share my side projects, paper readings, trending news, and my life here with you.

1 minute read

The main benefits of padding are the following:

  • It allows you to use a CONV layer without necessarily shrinking the height and width of the volumes. This is important for building deeper networks, since otherwise the height/width would shrink as you go to deeper layers. An important special case is the “same” convolution, in which the height/width is exactly preserved after one layer.

  • It helps us keep more of the information at the border of an image. Without padding, very few values at the next layer would be affected by pixels as the edges of an image.

    • None
comments powered by Disqus

Recent posts

See more



Passion in core network, ML, and software engineer. Love food, hiking, and snow skiing.