Neural network caffe:conv层过滤器的平均值(通道上)

Neural network caffe:conv层过滤器的平均值(通道上),neural-network,deep-learning,caffe,conv-neural-network,pycaffe,Neural Network,Deep Learning,Caffe,Conv Neural Network,Pycaffe,我有一个尺寸为nXmx16x1的conv层,我想计算16个滤波器的平均值或和,因此结果是1个尺寸为nxmx1x1的滤波器 类似于matlab中的平均值(A,3)的东西使用常量1x1“Conv”过滤器: layer { name: "avg" type: "Convolution" bottom: "input" top: "output" param { lr_mult: 0 decay_mult: 0 } # fix this layer, do not train

我有一个尺寸为nXmx16x1的conv层,我想计算16个滤波器的平均值或和,因此结果是1个尺寸为nxmx1x1的滤波器

类似于matlab中的平均值(A,3)的东西使用常量1x1
“Conv”
过滤器:

layer {
  name: "avg"
  type: "Convolution"
  bottom: "input"
  top: "output"
  param { lr_mult: 0 decay_mult: 0 }  # fix this layer, do not train
  convolution_param {
    num_output: 1
    kernel_size: 1
    bias: false  # no bias
    weight_filler: { type: "constant" value: 0.0625 }  # 1/16.
  }
}

@尼玛,你怎么能这么快就接受这个答案?你查过了吗?