DNNDK车辆特征提取

一、prototxt

car.prototxt：原本的训练文件（A）

deploy.prototxt：GoogLeNet Caffe示例文件（B）

Inception_v1_float.prototxt：Inception v1 DNNDK示例文件（C）

1、data层（三者存在差异）：

A:
layer {
   name: "data"
   type:"MemoryData"
   top: "data"
   top: "label"
   memory_data_param {
        batch_size: 1
        channels:3
        height: 224
        width: 224
    }
  transform_param {
    crop_size: 224
    mirror: false
  }
}

B:
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 10 dim: 3 dim: 224 dim: 224 } }
}

C:
layer {
  name: "data"
  type: "ImageData"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mirror: false
    mean_value: 104
    mean_value: 117
    mean_value: 123
  }
  image_data_param {
    source: "./data/imagenet_256/calibration.txt"
    root_folder: "./data/imagenet_256/calibration_images/"
    batch_size: 10
    shuffle: false
    new_height: 224
    new_width: 224
  }
}

View Code

2、convolution_param中weight_filter的std属性（A无，B有）：

3、inception_4a/output之后（A比B多出几层）：

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
  }
}
layer {
  name: "model_loss1/classifier"
  type: "InnerProduct"
  bottom: "loss1/fc"
  top: "model_loss1/classifier"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1232
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}

View Code

4、inception_4d/output之后（A比B多出几层）：

layer {
  name: "loss2/ave_pool"
  type: "Pooling"
  bottom: "inception_4d/output"
  top: "loss2/ave_pool"
  pooling_param {
    pool: AVE
    kernel_size: 5
    stride: 3
  }
}
layer {
  name: "loss2/conv"
  type: "Convolution"
  bottom: "loss2/ave_pool"
  top: "loss2/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: "loss2/relu_conv"
  type: "ReLU"
  bottom: "loss2/conv"
  top: "loss2/conv"
}
layer {
  name: "loss2/fc"
  type: "InnerProduct"
  bottom: "loss2/conv"
  top: "loss2/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: "loss2/relu_fc"
  type: "ReLU"
  bottom: "loss2/fc"
  top: "loss2/fc"
}
layer {
  name: "loss2/drop_fc"
  type: "Dropout"
  bottom: "loss2/fc"
  top: "loss2/fc"
  dropout_param {
    dropout_ratio: 0.7
  }
}
layer {
  name: "model_loss2/classifier"
  type: "InnerProduct"
  bottom: "loss2/fc"
  top: "model_loss2/classifier"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1232
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}

View Code

5、pool5/drop_7x7_s1之后（A与B存在差异）：

A：
layer {
  name: "fc/hash"
  type: "InnerProduct"
  bottom: "pool5/7x7_s1"
  top: "fc/hash"
  param {
    lr_mult: 10
    decay_mult: 10
  }
  param {
    lr_mult: 20
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1024
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "fc_hash/relu"
  type: "ReLU"
  bottom: "fc/hash"
  top: "fc_hash/relu"
}

B：
layer {
  name: "loss3/classifier"
  type: "InnerProduct"
  bottom: "pool5/7x7_s1"
  top: "loss3/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: "prob"
  type: "Softmax"
  bottom: "loss3/classifier"
  top: "prob"
}

View Code