caffe中的准确性问题

Question

我有一个有4个布尔输出的网络.这不是分类问题,而且每个问题都是有意义的.我期望每个人得到零或一个.现在我使用了欧几里德损失函数.

有1000000个样本.在输入文件中,每个都有144个功能,因此输入的大小为1000000*144.我使用批量大小为50,否则处理时间太长.输出文件的大小为1000000*4,即每个输入有四个输出.

当我使用精确度层时,它会抱怨输出的维度.它只需要一个布尔输出,而不是四个.我认为这是因为它将问题视为分类问题.我有两个问题.首先,考虑到精度层的误差,欧几里德损失函数是否适合这项任务？我如何才能获得网络的准确性？其次,我将获得四个变量中每个变量的预测输出的确切值.我的意思是我需要每个测试记录的确切预测值.现在,我只有每批的损失值.请指导我解决这些问题.

谢谢,Afshin

火车网络是:

{ state {
 phase: TRAIN
}
 layer {
   name: "abbas"
   type: "HDF5Data"
   top: "data"
   top: "label"
   hdf5_data_param {
     source: "/home/afo214/Research/hdf5/simulation/Train-1000-11-     1/Train-Sc-B-1000-11-1.txt"
     batch_size: 50
   } 
 }

 layer {
   name: "ip1"
   type: "InnerProduct"
   bottom: "data"
   top: "ip1"
   inner_product_param {
     num_output: 350
     weight_filler {
       type: "xavier"
     }
   }
 }

 layer {
   name: "sig1"
   bottom: "ip1"
   top: "sig1"
   type: "Sigmoid"
 }

 layer {
   name: "ip2"
   type: "InnerProduct"
   bottom: "sig1"
   top: "ip2"
   inner_product_param {
     num_output: 150
     weight_filler {
       type: "xavier"
     }
   }
 }

测试网络还包括:

       state {
       phase: TEST
       }
        layer {
        name: "abbas"
        type: "HDF5Data"
        top: "data"
        top: "label"
        hdf5_data_param {
         source: "/home/afo214/Research/hdf5/simulation/Train-1000-11-         1/Train-Sc-B-1000-11-1.txt"
          batch_size: 50
         }
        }

        layer {
         name: "ip1"
  type: "InnerProduct"
  bottom: "data"
  top: "ip1"
  inner_product_param {
  num_output: 350
  weight_filler {
   type: "xavier"
  }
 }
 }

  layer {
  name: "sig1"
  bottom: "ip1"
   top: "sig1"
   type: "Sigmoid"
 }


   layer {
     name: "ip2"
     type: "InnerProduct"
     bottom: "sig1"
     top: "ip2"
     inner_product_param {
       num_output: 150
       weight_filler {
         type: "xavier"
       }
     }
   }


   layer {
     name: "sig2"
     bottom: "ip2"
     top: "sig2"
     type: "Sigmoid"
   }


   layer {
     name: "ip4"
     type: "InnerProduct"
     bottom: "sig2"
     top: "ip4"
     inner_product_param {
       num_output: 4
       weight_filler {
         type: "xavier"
       }
     }
   }
   layer {
     name: "accuracy"
       type: "Accuracy"
         bottom: "ip4"
          bottom: "label"
             top: "accuracy"
             }


   layer {
     name: "loss"
     type: "EuclideanLoss"
     bottom: "ip4"
     bottom: "label"
     top: "loss"
   }

我收到这个错误:

accuracy_layer.cpp:34] Check failed: outer_num_ * inner_num_ ==  bottom[1]->count() (50 vs. 200) Number of labels must match number of   predictions; e.g., if label axis == 1 and prediction shape is (N, C, H,   W), label count (number of labels) must be N*H*W, with integer values in   {0, 1, ..., C-1}.

没有使用精度层caffe给我的损失值.

Answer 1

应该"EuclideanLoss"用于预测二进制输出？

如果您正在尝试预测离散二进制标签,那么"EuclideanLoss"这不是一个很好的选择.这种损失更适合于您希望预测连续值的回归任务(例如,估计边界框的协调等).
用于预测离散标签,"SoftmaxWithLoss"或"InfogainLoss"更适合.通常"SoftmaxWithLoss"使用.
对于预测二进制输出,您也可以考虑"SigmoidCrossEntropyLoss".

为什么"Accuracy"图层中有错误？

在caffe中," Accuracy"层需要两个输入("底部"):一个是预测向量,另一个是基本事实预期的离散标签.在您的情况下,您需要为每个二进制输出提供长度为2的向量预测概率为0和1,以及单个二进制标签:

layer {
  name: "acc01"
  type: "Accuracy"
  bottom: "predict01"
  bottom: "label01"
  top: "acc01"
}

在此示例中,您可以测量单个二进制输出的精度."predict01"对于批处理中的每个示例,输入是双向量(对于batch_size: 50此blob的形状应为50乘2).

你能做什么？

您试图在单个网络中预测4 种不同的输出,因此,您需要4 种不同的损耗和精度层.
首先,您需要"Slice"将地面实况标签拆分为4个标量(而不是单个二进制4向量):

layer {
  name: "label_split"
  bottom: "label" # name of input 4-vector
  top: "label01"
  top: "label02"
  top: "label03"
  top: "label04"
  type: "Slice"
  slice_param {
    axis: 1
    slice_point: 1
    slice_point: 2
    slice_point: 3
  }
}

现在,您必须为每个二进制标签设置预测,丢失和准确度层

layer {
  name: "predict01"
  type: "InnerProduct"
  bottom: "sig2"
  top: "predict01"
  inner_product_param {
    num_outout: 2 # because you need to predict 2 probabilities one for False, one for True
    ...
}
layer {
  name: "loss01"
  type: "SoftmaxWithLoss"
  bottom: "predict01"
  bottom: "label01"
  top: "loss01"
}
layer {
  name: "acc01"
  type: "Accuracy"
  bottom: "predict01"
  bottom: "label01"
  top: "acc01"
}

现在,您需要为要预测的四个二进制标签中的每一个复制这三个图层.