有人可以解释如何在caffe中使用Conv3d和ConvND吗?

时间:2016-11-29 19:45:33

标签: computer-vision neural-network deep-learning video-processing caffe

有人可以解释一下如何在Conv3D中使用ConvNDDepth-images Caffe或视频或几乎任何3d(nd?)数据?
有没有Conv3D的例子或演示?

1 个答案:

答案 0 :(得分:2)

您可以使用常规"Convolution"图层来处理任何维度的blob。您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中对Convolution参数的评论。