machine-learning - Caffe - prototxt 中的 num_output 给出了奇怪的行为

Question

这个问题已经有答案了:

Caffe output layer number accuracy (1 个回答)

已关闭 7 年前。

我正在做一些实验，将 Cifar-10 数据集分成两半，每一半包含五个随机类。我用 bvlc_alexnet 训练了一半建筑学。因此，我改变了num_output至5并对网络进行了一些其他的小调整。当我检查日志文件时，我发现损失增加到 80 左右，测试精度为 0。

但是，当我更改num_output时至10 ，训练似乎正常，即损失稳步下降，测试准确率约为 70%。

这该如何解释？

train_val.prototxt

name: "AlexNet"
layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mirror: true
    crop_size: 25

  }
  data_param {
    source: "/home/apples/caffe/cifar/cifarA/cifar_A_train_lmdb"
    batch_size: 256
    backend: LMDB
  }
}
layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    mirror: false
    crop_size: 25

  }
  data_param {
    source: "/home/apples/caffe/cifar/cifarA/cifar_A_val_lmdb"
    batch_size: 100
    backend: LMDB
  }
}
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: 2
    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"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0.1
    }
  }
}
layer {
  name: "relu5"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
}
layer {
  name: "pool5"
  type: "Pooling"
  bottom: "conv5"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "fc6"
  type: "InnerProduct"
  bottom: "pool5"
  top: "fc6"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 4096
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 0.1
    }
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "fc6"
  top: "fc6"
}
layer {
  name: "drop6"
  type: "Dropout"
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc7"
  type: "InnerProduct"
  bottom: "fc6"
  top: "fc7"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 4096
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 0.1
    }
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "fc7"
  top: "fc7"
}
layer {
  name: "drop7"
  type: "Dropout"
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc8_mnist"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc8_mnist"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 5
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "fc8_mnist"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "fc8_mnist"
  bottom: "label"
  top: "loss"
}

此拆分包含类 0、4、5、6 和 8。我使用了 create_imagenet.sh用于创建 lmdb 文件的脚本。

train.txt 示例

0/attack_aircraft_s_001759.png 0
0/propeller_plane_s_001689.png 0
4/fallow_deer_s_000021.png 4
4/alces_alces_s_000686.png 4
5/toy_spaniel_s_000327.png 5
5/toy_spaniel_s_000511.png 5
6/bufo_viridis_s_000502.png 6
6/bufo_viridis_s_001005.png 6
8/passenger_ship_s_000236.png 8
8/passenger_ship_s_000853.png 8

val.txt 示例

0/attack_aircraft_s_000002.png 0
0/propeller_plane_s_000006.png 0
4/fallow_deer_s_000001.png 4
4/alces_alces_s_000012.png 4
5/toy_spaniel_s_000020.png 5
6/bufo_viridis_s_000016.png 6
8/passenger_ship_s_000060.png 8

Answer 1

正如评论中所指出的，Caffe 希望标签是 0 到 num_classes - 1 之间的整数。在您的例子中，当您将标签数量设置为 5 时，Caffe 将在最后一层创建 5 个输出神经元。当你要求它预测第 6 类或第 8 类时，你是在要求它最大化一个不存在的神经元的输出，而 Caffe 显然无法做到这一点。

现在，当您重新标记数据并将 num_classes 设置为 5 时，您做了正确的事情，因此它有效。当您将 num_classes 设置为 10 时，网络仍然可以工作，因为现在它有 10 个输出神经元，这足以对 5 个类别进行分类。它将了解到从​​ 5 到 9 的类永远不会存在，因此永远不应该被预测，并且它只会以始终导致这些输出神经元返回非常小的值的方式调整权重。然而，值得注意的是，神经网络本质上是随机的，因此它仍然可能偶尔返回一个从未呈现给它的类，因此我期望神经网络的 num_classes 大于实际数量类的性能比具有正确 num_classes 的类的性能更差。