Caffe中HDF5Data例子

• Caffe中HDF5Data用于处理多标签数据，例子如下：

name: "LeNet"###for data and labelslayer {  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 alllayer {  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_1layer {  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_2layer {  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"}

• 注：如何生成hdf5文件，详见：生成hdf5文件用于多标签训练
• 注：Hdf5Data详见：HDF5 Input
• 注：Slice详见：Slicing

---

• 最终网络结构如下图：
  
• 注：Caffe学习：使用pycaffe绘制网络结构