7.4. Multiple Input and Multiple Output Channels — Dive into Deep Learning 1.0.3 documentation thumbnail
7.4. Multiple Input and Multiple Output Channels — Dive into Deep Learning 1.0.3 documentation
d2l.ai
construct a convolution kernel with the same number of input channels as the input data adding the results together (summing over the channels) to yield a two-dimensional tensor. increase the channel dimension as we go deeper in the neural network ownsampling to trade off spatial resolution for grea
2 Users
0 Comments
15 Highlights
0 Notes

Top Highlights

  • construct a convolution kernel with the same number of input channels as the input data
  • adding the
  • results together (summing over the channels) to yield a two-dimensional tensor.
  • increase the channel dimension as we go deeper in the neural network
  • ownsampling to trade off spatial resolution for greater channel depth.

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.