caffe实现多标签输入(multilabel、multitask)

其他资料

以下内容摘自参考文献[2],将caffe中的data和label分别写在两个layer中：

layer {
  name: "data"
  type: "Data"
  top: "data"
  include {
    phase: TRAIN
  }
  transform_param {
    mean_value: 104.00699
    mean_value: 116.66877
    mean_value: 122.67892
  }
  data_param {
    source: "skin/data/traindata_lmdb"
    batch_size: 1
    backend: LMDB
  }
}
layer {
  name: "label"
  type: "Data"
  top: "label"
  include {
    phase: TRAIN
  }
  data_param {
    source: "skin/data/trainlabel_lmdb"
    batch_size: 1
    backend: LMDB
  }
   transform_param {
    # feature scaling coefficient: this maps the [0, 255] MNIST data to [0, 1]
    scale: 0.00390625
  }
}
layer {
  name: "data"
  type: "Data"
  top: "data"
  include {
    phase: TEST
  }
  transform_param {
    mean_value: 104.00699
    mean_value: 116.66877
    mean_value: 122.67892
  }
  data_param {
    source: "skin/data/valdata_lmdb"
    batch_size: 1
    backend: LMDB
  }
}
layer {
  name: "label"
  type: "Data"
  top: "label"
  include {
    phase: TEST
  }
  data_param {
    source: "skin/data/vallabel_lmdb"
    batch_size: 1
    backend: LMDB
  }
   transform_param {
    # feature scaling coefficient: this maps the [0, 255] MNIST data to [0, 1]
    scale: 0.00390625
  }
}

我们首先通过可视化工具可视化一下：

然后，通过训练一下lenet网络，检查一下上面的形式是否可行。

先略。

多标签

以下内容摘自文献[4]，请多支持原文。感谢他们的分享。

train_val.prototxt

name: "LeNet"

###for data and labels

layer {
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "labels"
  include {
    phase: TRAIN
  }
  hdf5_data_param {
    source: "list_train.txt"
    batch_size: 100
  }
}
layer {
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "labels"
  include {
    phase: TEST
  }
  hdf5_data_param {
    source: "list_test.txt"
    batch_size: 100
  }
}
layer {
  name: "slicers"
  type: "Slice"
  bottom: "labels"
  top: "label_1"
  top: "label_2"
  slice_param {
    axis: 1
    slice_point: 1
  }
}

### for all

layer {
  name: "conv_all"
  type: "Convolution"
  bottom: "data"
  top: "conv_all"
  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: "relu_all"
  type: "ReLU"
  bottom: "conv_all"
  top: "conv_all"
}
layer {
  name: "pool_all"
  type: "Pooling"
  bottom: "conv_all"
  top: "pool_all"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}

### for kind_1

layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool_all"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 2
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "accuracy1"
  type: "Accuracy"
  bottom: "ip1"
  bottom: "label_1"
  top: "accuracy1"
  include {
    phase: TEST
  }
}
layer {
  name: "loss_1"
  type: "SoftmaxWithLoss"
  bottom: "ip1"
  bottom: "label_1"
  top: "loss_1"
}

###for kind_2

layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "pool_all"
  top: "ip2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "accuracy2"
  type: "Accuracy"
  bottom: "ip2"
  bottom: "label_2"
  top: "accuracy2"
  include {
    phase: TEST
  }
}
layer {
  name: "loss_2"
  type: "SoftmaxWithLoss"
  bottom: "ip2"
  bottom: "label_2"
  top: "loss_2"
}

使用Netscope可视化：

参考文献:

1 http://blog.csdn.net/u013010889/article/details/53098346 [caffe实现多标签输入(multilabel、multitask)]
2. http://blog.csdn.net/zhikangfu/article/details/45170047 [将caffe中的data和label分别写在两个layer中]
3. https://www.zhihu.com/question/53296707 [已经通过 使用HDF5Data做输入 ，加入slice layer，构建五个小分类器 解决了这个问题，效果也还可以。]
4. http://blog.csdn.net/u011762313/article/details/48851015 [Caffe中HDF5Data例子。]