LeNet-5模型描述

本節例程中的LeNet-5模型與原版稍有不同（例如，將Sigmoid啟用函式改為ReLU），其描述檔案在Caffe目錄下的examples/mnist/lenet_train_test.prototxt中，內容及程式碼註釋如下：

name: "LeNet"			//網路（Net）的名稱為LeNet
layer {					//定義一個層（Layer）
  name: "mnist"			//層的名稱為mnist
  type: "Data"			//層的型別為資料層
  top: "data"				//層的輸出blob有兩個：data和label				
  top: "label"				
  include {
 

    phase: TRAIN			//該層引數只在訓練階段有效
  }
  transform_param {
    scale: 0.00390625			//資料變換使用的資料縮放因子
  }
  data_param {					//資料層引數
    source: "examples/mnist/mnist_train_lmdb"	//LMDB的路徑
    batch_size: 64		// 批量數目，一次讀取64張圖
    backend: LMDB		// 資料格式為LMDB
  }
}
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top:
 
 "label"
  include {
    phase: TEST
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "examples/mnist/mnist_test_lmdb"
    batch_size: 100
    backend: LMDB
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult:
 
 2
  }
  convolution_param {
    num_output: 20
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 50
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool2"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}
layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 10
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "ip2"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip2"
  bottom: "label"
  top: "loss"
}

注：（本文引用自書籍《深度學習——21天實戰Caffe》，趙永科著，中國工信出版集團&電子工業出版社出版）本文內容僅供參考；