有人可以解释如何在 caffe 中使用 Conv3d 和 ConvND 吗?

Can someone explain how to use Conv3d and ConvND in caffe?

有人可以解释一下如何将 Conv3DConvND 用于 Depth-images 或视频或 [=13= 中的几乎任何 3d(n-d?)数据] ?
Conv3D 是否有任何示例或演示?

您可以使用常规 "Convolution" 层来处理任何维度的斑点。你只需要密切关注参数:

layer {
  type: "Convolution"
  name: "conv_nd"
  bottom: "in" # 5D blob 
  too: "out"
  convolution_param {
     kernel_size: 3
     kernel_size: 5
     kernel_size: 5 # define 3 by 5 by 5 kernel

     pad: 1
     pad: 2
     pad: 2  # pad according to kernel size

     stride: 1
     stride: 2
     stride: 2 # you can have different stride for different dimensions

     axis: 1  # the "channel" dimension
     num_output: 30 # output 30 dim per 3D voxel
  }
}

有关更多信息,请阅读 caffe.proto file 中关于卷积参数的注释。