8.4. Multi-Branch Networks (GoogLeNet) — Dive into Deep Learning 1.0.3 documentation thumbnail
8.4. Multi-Branch Networks (GoogLeNet) — Dive into Deep Learning 1.0.3 documentation
d2l.ai
lear distinction among the stem (data ingest), body (data processing), and head (prediction) global average pooling layer to change the height and width of each channel to 1, Max-pooling between inception blocks reduces the dimensionality. reducing the model’s complexity first two or three convoluti
2 Users
0 Comments
15 Highlights
0 Notes

Top Highlights

  • lear distinction among the stem (data ingest), body (data processing), and head (prediction)
  • global average pooling layer to change the height and width of each channel to 1,
  • Max-pooling between inception blocks reduces the dimensionality.
  • reducing the model’s complexity
  • first two or three convolutions that operate on the image.

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.