caffe中‘'Concat'层的作用什么

在一个多任务分类中,这是网络的最后几层,其中'Concat‘层的作用是什么?
layer {
  name: "fc3"
  type: "InnerProduct"
  bottom: "pool_avg"
  top: "fc3"
  param {
    lr_mult: 0.0
    decay_mult: 0.0
  }
  param {
    lr_mult: 0.0
    decay_mult: 0.0
  }
  inner_product_param {
    num_output: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "softmax"
  type: "Softmax"
  bottom: "fc3"
  top: "softmax"
}
layer {
  name: "fc3_t"
  type: "InnerProduct"
  bottom: "pool_avg"
  top: "fc3_t"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 1.0
    decay_mult: 0.0
  }
  inner_product_param {
    num_output: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "softmax_t"
  type: "Softmax"
  bottom: "fc3_t"
  top: "softmax_t"
}
layer {
  name: "concat"
  type: "Concat"
  bottom: "softmax"
  bottom: "softmax_t"
  top: "out"
  concat_param {
    axis: 1
  }
}
已邀请:

要回复问题请先登录注册