GoogLeNet

GoogLeNet 系列

GoogLeNet v1

Going Deeper with Convolutions
参考：http://blog.csdn.net/sunbaigui/article/details/50807362
论文网络结构定义中，accuracy-1,accuracy-5,辅助loss层指定所占比例，定义:

layer {
  name: "loss1/ave_pool"
  type: "Pooling"
  bottom: "inception_4a/output"
  top: "loss1/ave_pool"
  pooling_param {
    pool: AVE
    kernel_size: 5
    stride: 3
  }
}
layer {
  name: "loss1/conv"
  type: "Convolution"
  bottom: "loss1/ave_pool"
  top: "loss1/conv"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    kernel_size: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "loss1/relu_conv"
  type: "ReLU"
  bottom: "loss1/conv"
  top: "loss1/conv"
}
layer {
  name: "loss1/fc"
  type: "InnerProduct"
  bottom: "loss1/conv"
  top: "loss1/fc"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1024
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.2
    }
  }
}
layer {
  name: "loss1/relu_fc"
  type: "ReLU"
  bottom: "loss1/fc"
  top: "loss1/fc"
}
layer {
  name: "loss1/drop_fc"
  type: "Dropout"
  bottom: "loss1/fc"
  top: "loss1/fc"
  dropout_param {
    dropout_ratio: 0.7 #loss2:0.7 loss3:0.6
  }
}
layer {
  name: "loss1/classifier"
  type: "InnerProduct"
  bottom: "loss1/fc"
  top: "loss1/classifier"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1000
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "loss1/loss"
  type: "SoftmaxWithLoss"
  bottom: "loss1/classifier"
  bottom: "label"
  top: "loss1/loss1"
  loss_weight: 0.3 # loss2:0.3  loss3:1
}
layer {
  name: "loss1/top-1"
  type: "Accuracy"
  bottom: "loss1/classifier"
  bottom: "label"
  top: "loss1/top-1"
  include {
    phase: TEST
  }
}
layer {
  name: "loss1/top-5"
  type: "Accuracy"
  bottom: "loss1/classifier"
  bottom: "label"
  top: "loss1/top-5"
  include {
    phase: TEST
  }
  accuracy_param {
    top_k: 5
  }
}

GoogLeNet v2

Rethinking the Inception Architecture for Computer Vision
参考：http://blog.csdn.net/shuzfan/article/details/50738394