Neural network 精度始终为1 Caffe回归

我的数据集包含400幅32x32x3的图像，标签包含浮点数（-1,1）。例如：

faceCroppedImages/img1.jpg 0
faceCroppedImages/img2.jpg 0.0128
faceCroppedImages/img3.jpg 0.0128
faceCroppedImages/img4.jpg 0.0128
faceCroppedImages/img22.jpg 0.0128
faceCroppedImages/img23.jpg 0.0085
faceCroppedImages/img24.jpg 0.0077
faceCroppedImages/img25.jpg 0.0077
faceCroppedImages/img293.jpg -0.023
faceCroppedImages/img294.jpg -0.023
faceCroppedImages/img295.jpg -0.0204
faceCroppedImages/img296.jpg -0.0179
faceCroppedImages/img297.jpg -0.017
faceCroppedImages/img298.jpg -0.0128

我的

'solver.prototxt'

是：

net: "train_test_hdf5.prototxt"
test_iter: 100
test_interval: 500
base_lr: 0.003
momentum: 0.9
weight_decay: 0.0005
lr_policy: "inv"
gamma: 0.0001
power: 0.75
display: 100
max_iter: 10000
snapshot: 5000
snapshot_prefix: "lenet_hdf5"
solver_mode: CPU

name: "MSE regression"
layer{
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "label"
  hdf5_data_param {
    source: "train_hdf5file.txt"
    batch_size: 64
    shuffle: true
  }
  include: { phase: TRAIN }
}

layer{
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "label"
  hdf5_data_param {
    source: "test_hdf5file.txt"
    batch_size: 128
  }
  include: { phase: TEST }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param { lr_mult: 1 }
  param { lr_mult: 2 }
  convolution_param {
    num_output: 20
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "dropout1"
  type: "Dropout"
  bottom: "pool1"
  top: "pool1"
  dropout_param {
    dropout_ratio: 0.1
  }
}

layer{
  name: "fc1"
  type: "InnerProduct"
  bottom: "pool1"
  top: "fc1"
  param { lr_mult: 1 decay_mult: 1 }
  param { lr_mult: 2 decay_mult: 0 }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "dropout2"
  type: "Dropout"
  bottom: "fc1"
  top: "fc1"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer{
  name: "fc2"
  type: "InnerProduct"
  bottom: "fc1"
  top: "fc2"
  param { lr_mult: 1 decay_mult: 1 }
  param { lr_mult: 2 decay_mult: 0 }
  inner_product_param {
    num_output: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
 }
}
layer {
  name: "accuracy1"
  type: "Accuracy"
  bottom: "fc2"
  bottom: "label"
  top: "accuracy1"
  include {
    phase: TEST
  }
}
layer{
  name: "loss"
  type: "EuclideanLoss"
  bottom: "fc2"
  bottom: "label"
  top: "loss"
}

而

'train\u test\u hdf5.prototxt'

是：

net: "train_test_hdf5.prototxt"
test_iter: 100
test_interval: 500
base_lr: 0.003
momentum: 0.9
weight_decay: 0.0005
lr_policy: "inv"
gamma: 0.0001
power: 0.75
display: 100
max_iter: 10000
snapshot: 5000
snapshot_prefix: "lenet_hdf5"
solver_mode: CPU

name: "MSE regression"
layer{
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "label"
  hdf5_data_param {
    source: "train_hdf5file.txt"
    batch_size: 64
    shuffle: true
  }
  include: { phase: TRAIN }
}

layer{
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "label"
  hdf5_data_param {
    source: "test_hdf5file.txt"
    batch_size: 128
  }
  include: { phase: TEST }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param { lr_mult: 1 }
  param { lr_mult: 2 }
  convolution_param {
    num_output: 20
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "dropout1"
  type: "Dropout"
  bottom: "pool1"
  top: "pool1"
  dropout_param {
    dropout_ratio: 0.1
  }
}

layer{
  name: "fc1"
  type: "InnerProduct"
  bottom: "pool1"
  top: "fc1"
  param { lr_mult: 1 decay_mult: 1 }
  param { lr_mult: 2 decay_mult: 0 }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "dropout2"
  type: "Dropout"
  bottom: "fc1"
  top: "fc1"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer{
  name: "fc2"
  type: "InnerProduct"
  bottom: "fc1"
  top: "fc2"
  param { lr_mult: 1 decay_mult: 1 }
  param { lr_mult: 2 decay_mult: 0 }
  inner_product_param {
    num_output: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
 }
}
layer {
  name: "accuracy1"
  type: "Accuracy"
  bottom: "fc2"
  bottom: "label"
  top: "accuracy1"
  include {
    phase: TEST
  }
}
layer{
  name: "loss"
  type: "EuclideanLoss"
  bottom: "fc2"
  bottom: "label"
  top: "loss"
}

但是，当我测试数据时，精度始终为1:

我尝试使用整数标签将我的当前标签乘以1000，但得到了nan错误：

你能告诉我哪里做错了吗？我是caffe和神经网络的初学者。任何建议都是有价值的。TIA。

在回归任务中使用

“准确性”层没有意义：该层测量分类输出的准确性。

例如，如果您试图预测一个
L
标签，
fc2
层的
num\u输出将是
L
——即预测每个类别的概率。然后
“准确性”
层检查与预期输出
l
相对应的
l
第个条目的概率是否最大。

当
fc2
输出仅为一维时，如何计算这种精度

在您的情况下，您只能检查欧几里德损失，并看到它在测试和训练中都在减少。
在回归任务中使用
“准确性”
层没有意义：该层测量分类输出的准确性。

例如，如果您试图预测一个
L
标签，
fc2
层的
num\u输出将是
L
——即预测每个类别的概率。然后
“准确性”
层检查与预期输出
l
相对应的
l
第个条目的概率是否最大。

当
fc2
输出仅为一维时，如何计算这种精度

在您的情况下，您只能检查欧几里德损失，并看到它在测试和训练中都在减少。
感谢您解释“准确性”层。我想知道是否有任何方法可以真正看到回归输出？与网络的预测输出类似，以便我可以将其与测试标签进行比较？@损耗层正是这样做的-它输出标签与测试集/训练批平均预测之间的L2距离谢谢您解释“准确性”层。我想知道是否有任何方法可以真正看到回归输出？与网络的预测输出类似，以便我可以将其与测试标签进行比较？@损耗层正是这样做的-它输出标签与测试集/训练批次上平均的预测之间的L2距离