1

For example, in PointNet, you see the 1D convolutions with the following channels 64 -> 128 -> 1024. Why not e.g. 64 -> 1024 -> 1024 or 1024 -> 1024 -> 1024?

nbro
  • 42,615
  • 12
  • 119
  • 217
user3180
  • 648
  • 5
  • 15

0 Answers0