Specifically, in the maxout network:

http://proceedings.mlr.press/v28/goodfellow13.pdf

answers:

https://www.quora.com/What-is-a-cross-channel-pooling-in-convolutional-neural-networks

If it is a convolution module outputing 50 feature maps, then the cross channel pooling will output 5 feature map, where each point in the feature map is the max of the points at the same position in the 10 underlying feature maps.

相关文章:

  • 2021-11-27
  • 2022-12-23
  • 2021-10-05
  • 2022-01-04
  • 2021-10-07
  • 2021-07-11
  • 2022-01-10
  • 2021-06-13
猜你喜欢
  • 2021-07-04
  • 2022-12-23
  • 2022-12-23
  • 2021-04-17
  • 2021-11-16
  • 2021-11-04
  • 2021-06-08
相关资源
相似解决方案