7.3. Padding and Stride — Dive into Deep Learning 1.0.3 documentation thumbnail
7.3. Padding and Stride — Dive into Deep Learning 1.0.3 documentation
d2l.ai
lose pixels on the perimeter of our image since kernels generally have width and height greater than outputs that are considerably smaller than our input. give the input and output the same height and width. preserve the dimensionality while padding with the same number of rows on top and bottom, an
2 Users
0 Comments
11 Highlights
0 Notes

Top Highlights

  • lose pixels on the perimeter of our image
  • since kernels generally have width and height greater than
  • outputs that are considerably smaller than our input.
  • give the input and output the same height and width.
  • preserve the dimensionality while padding with the same number of rows on top and bottom, and the same number of columns on left and right.

Domain

Ready to highlight and find good content?

Glasp is a social web highlighter that people can highlight and organize quotes and thoughts from the web, and access other like-minded people’s learning.