eltwise sum over multiple channels 逐通道的相加in Caffe

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/xuluhui123/article/details/83614795

//sum over 16 channels
layers {
  name: "sum_1"
  type: CONVOLUTION
  bottom: "conv_1"
  top: "sum_1"
  blobs_lr: 0
  convolution_param {
    num_output: 1
    bias_term: false
    kernel_size: 1
    weight_filler {
      type: 'constant'
      value: 1
    }
  }
}

参考文献：
1 https://groups.google.com/forum/#!topic/caffe-users/80y4vnVocsg