实战caffe多标签分类——汽车品牌与车辆外观（C++接口）[详细实现+数据集]

前言

很多地方我们都需要用到多标签分类，比如一张图片，上面有只蓝猫，另一张图片上面有一只黄狗，那么我们要识别的时候，就可以采用多标签分类这一思想了。任务一是识别出这个到底是猫还是狗？（类型）任务二是识别出这是蓝还是黄？（颜色）


网上看了几篇教程，有讲的非常好的，也有出bug飞上了天的（吐槽啊喂！）这里还是主要讲讲这篇：http://chuansong.me/n/494753151240。我自己已经测试了，可行，给薛大牛一个赞！但是遗憾的是这篇文章的内容严重不足啊（连lmdb生成的命令行格式都没有，还是我自己看代码琢磨了一下…）我就给这篇文章补充补充，给一些例子。

任务

我这里给出一个具体的任务咯，要求在以下图片中，识别出汽车品牌和车辆外形。汽车品牌分为：Benz/BMW/Audi 车辆外形分为：Sedan/SUV。这是一个只有72张图片的小数据库,包括了测试和训练集：

其中标注是这样的，Audi=0，BMW=1，Benz=2. Sedan =0, SUV=1。所以如果这辆车是奥迪的SUV，标注就是： xx.jpg 0 1。在数据库中，标注已经做好了。数据集的下载方式在文章的最后。

定义我们的网络结构

我们这里采用的是上述文章中薛大牛的方法，两个data层，一个data只放图片，另一个data放label，label通过slice layer切开。然后我们开始定义网络！修改AlexNet！这是我的网络：

name: "ZnNet"
layer {
  name: "data"
  type: "Data"
  top: "data"  
  transform_param {
    mirror: true
    crop_size: 227
    mean_file: "models/bvlc_alexnet/ZnCarTrainMean.binaryproto"
  }
  include {
    phase: TRAIN
  }
  data_param {
    source: "models/bvlc_alexnet/ZnCarTrainImage" 
    batch_size: 10
    backend: LMDB
  }
}
layer {
  name: "labels"
  type: "Data"
  top: "labels"
  include {
    phase: TRAIN
  }
  data_param {
    source: "models/bvlc_alexnet/ZnCarTrainLabel"
    batch_size: 10
    backend: LMDB
  }
}
layer {
  name: "data"
  type: "Data"
  top: "data"
  transform_param {
     crop_size: 227    
     mean_file: "models/bvlc_alexnet/ZnCarTestMean.binaryproto"
  } 
  include {
    phase: TEST
  }
  data_param {
    source: "models/bvlc_alexnet/ZnCarTestImage"
    batch_size: 12
    backend: LMDB
   }
}
layer {
  name: "labels"
  type: "Data"
  top: "labels"
  include {
     phase: TEST
  }
  data_param {
    source: "models/bvlc_alexnet/ZnCarTestLabel"
    batch_size: 12
    backend: LMDB
  }
}
layer {
  name: "slice"
  type: "Slice"
  bottom: "labels"
  top: "type" #汽车品牌
  top: "surface" #车的外形
  slice_param {
    axis: 1
    slice_point: 1
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 96
    kernel_size: 11
    stride: 4
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "norm1"
  type: "LRN"
  bottom: "conv1"
  top: "norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "norm1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0.1
    }
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "norm2"
  type: "LRN"
  bottom: "conv2"
  top: "norm2"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "norm2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
    }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0.1
    }
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5"