Question

我正在尝试估算单个图像的深度。为此，我有一个图像和一个ground_truth = depth_image和一个非常简单的完全卷积网络。我的图像和深度图像都具有1x227x227的形状

我有一个像这样的 train_val.prototxt ：

 layer {
  name: "train-data"
  type: "Data"
  top: "data"
  include {
    phase: TRAIN
  }
  transform_param {
    mean_file: "mean_train.binaryproto"
  }
  data_param {
    source: ".../train_lmdb"
    batch_size: 4
    backend: LMDB
  }
}
layer {
  name: "train-depth"
  type: "Data"
  top: "depth"
  include {
    phase: TRAIN
  }
  transform_param {
    mean_file: "mean_train.binaryproto"
  }
  data_param {
    source: ".../train_depth_lmdb"
    batch_size: 4
    backend: LMDB
  }
}
layer {
  name: "val-data"
  type: "Data"
  top: "data"
  include {
    phase: TEST
  }
  transform_param {
    mean_file: "mean_val.binaryproto"
  }
  data_param {
    source: ".../val_lmdb"
    batch_size: 4
    backend: LMDB
  }
}
layer {
  name: "val-depth"
  type: "Data"
  top: "depth"
  include {
    phase: TEST
  }
  transform_param {
    mean_file: "mean_train.binaryproto"
  }
  data_param {
    source: ".../val_depth_lmdb"
    batch_size: 4
    backend: LMDB
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  convolution_param {
    num_output: 16
    kernel_size: 17
    stride: 1
    pad: 8
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "conv1"
  top: "conv2"
  convolution_param {
    num_output: 16
    kernel_size: 15
    stride: 1
    pad: 7
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "conv2"
  top: "conv3"
  convolution_param {
    num_output: 32
    kernel_size: 11
    stride: 1
    pad: 5
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4"
  convolution_param {
    num_output: 32
    kernel_size: 9
    stride: 1
    pad: 4
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5"
  convolution_param {
    num_output: 32
    kernel_size: 9
    stride: 1
    pad: 4
  }
}
layer {
  name: "relu5"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
}
layer {
  name: "conv6"
  type: "Convolution"
  bottom: "conv5"
  top: "conv6"
  convolution_param {
    num_output: 64
    kernel_size: 3
    stride: 1
    pad: 1
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "conv6"
  top: "conv6"
}
layer {
  name: "conv7"
  type: "Convolution"
  bottom: "conv6"
  top: "conv7"
  convolution_param {
    num_output: 1
    kernel_size: 1
    stride: 1
    pad: 0
  }
}
layer {
  name: "loss"
  type: "EuclideanLoss"
  bottom: "conv7"
  bottom: "depth"
  top: "loss"
}

这是我的日志文件。正如您所看到的，损失值太高了。我不知道为什么。我已经改变了学习率，但这似乎不是问题所在。有什么想法吗？

I1101 12:26:48.211413 14410 solver.cpp:404]     Test net output #0: loss = 1.75823e+08 (* 1 = 1.75823e+08 loss)
I1101 12:26:48.231112 14410 solver.cpp:228] Iteration 0, loss = 1.08477e+08
I1101 12:26:48.231155 14410 solver.cpp:244]     Train net output #0: loss = 1.08477e+08 (* 1 = 1.08477e+08 loss)
I1101 12:26:48.231180 14410 sgd_solver.cpp:106] Iteration 0, lr = 0.001
I1101 12:26:48.275223 14410 solver.cpp:228] Iteration 1, loss = 1.34519e+08
I1101 12:26:48.275249 14410 solver.cpp:244]     Train net output #0: loss = 1.34519e+08 (* 1 = 1.34519e+08 loss)
I1101 12:26:48.275254 14410 sgd_solver.cpp:106] Iteration 1, lr = 0.001
I1101 12:26:48.313233 14410 solver.cpp:228] Iteration 2, loss = 1.57773e+08
I1101 12:26:48.313277 14410 solver.cpp:244]     Train net output #0: loss = 1.57773e+08 (* 1 = 1.57773e+08 loss)
I1101 12:26:48.313282 14410 sgd_solver.cpp:106] Iteration 2, lr = 0.001
I1101 12:26:48.349695 14410 solver.cpp:228] Iteration 3, loss = 1.12463e+08
I1101 12:26:48.349742 14410 solver.cpp:244]     Train net output #0: loss = 1.12463e+08 (* 1 = 1.12463e+08 loss)
...
I1101 12:29:00.106989 14410 solver.cpp:317] Iteration 3390, loss = 1.21181e+08
I1101 12:29:00.107023 14410 solver.cpp:337] Iteration 3390, Testing net (#0)
I1101 12:29:00.107029 14410 net.cpp:693] Ignoring source layer train-data
I1101 12:29:00.107033 14410 net.cpp:693] Ignoring source layer train-depth
I1101 12:29:00.294692 14410 solver.cpp:404]     Test net output #0: loss = 1.7288e+08 (* 1 = 1.7288e+08 loss)
I1101 12:29:00.294737 14410 solver.cpp:322] Optimization Done.
I1101 12:29:00.294741 14410 caffe.cpp:254] Optimization Done.

为了好玩，我已经将标签数据设置为与输入数据完全相同的数据，这意味着它将学习图像本身但输出仍然相同。必须有一些完全错误的东西？

Caffe输出仅返回零值

0 个答案: