Caffe HDF5神经网络基础实例解析模型文件失败

Question

我正在尝试使用我使用 caffe 库从 CSV 文件准备的 HDF5 数据构建神经网络的最小示例。

我的原文如下：[wine_train.prototxt]

name:"wineclass"
layers {
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "label"
  hdf5_data_param {
    source: "examples/wine/test.txt"
    batch_size: 10
  }
  include{
   phase:TEST
  }
}
layer {
  name: "data"
  type: "HDF5Data"
  top: "label"
  top: "label"
  hdf5_data_param {
    source: "examples/wine/train.txt"
    batch_size: 2
  }
  include{
   phase:TRAIN
  }
}
layers {
  name: "ip"
  type: "INNER_PRODUCT"
  bottom: "data"
  top: "ip"
  inner_product_param {
    num_output: 3
  }
}
layers {
  name: "loss"
  type: "SOFTMAX_LOSS"
  bottom: "ip"
  bottom: "label"
  top: "loss"
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "ip"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}

我的求解器如下：

net: "examples/wine/wine_train.prototxt"
test_iter: 250
test_interval: 1000
base_lr: 0.01
lr_policy: "step"
gamma: 0.1
stepsize: 5000
display: 1000
max_iter: 10000
momentum: 0.9
weight_decay: 0.0005
snapshot: 10000
snapshot_prefix: "wine/train"
solver_mode: CPU

每次我收到以下错误：

shaunak@ubuntu:~/caffe$ build/tools/caffe train -model '/home/shaunak/caffe/examples/wine/wine_train.prototxt' -solver '/home/shaunak/caffe/examples/wine/solver.prototxt'
I0415 04:31:00.154145 57047 caffe.cpp:117] Use CPU.
I0415 04:31:00.154485 57047 caffe.cpp:121] Starting Optimization
I0415 04:31:00.154552 57047 solver.cpp:32] Initializing solver from parameters:
test_iter: 250
test_interval: 1000
base_lr: 0.01
display: 1000
max_iter: 10000
lr_policy: "step"
gamma: 0.1
momentum: 0.9
weight_decay: 0.0005
stepsize: 5000
snapshot: 10000
snapshot_prefix: "wine/train"
solver_mode: CPU
net: "examples/wine/wine_train.prototxt"
I0415 04:31:00.154660 57047 solver.cpp:70] Creating training net from net file: examples/wine/wine_train.prototxt
[libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 4:9: Expected integer or identifier.
F0415 04:31:00.154774 57047 upgrade_proto.cpp:928] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: examples/wine/wine_train.prototxt
*** Check failure stack trace: ***
    @     0x7f4a30766c3c  google::LogMessage::Fail()
    @     0x7f4a30766b88  google::LogMessage::SendToLog()
    @     0x7f4a3076658a  google::LogMessage::Flush()
    @     0x7f4a30769521  google::LogMessageFatal::~LogMessageFatal()
    @     0x7f4a30b8b1ee  caffe::ReadNetParamsFromTextFileOrDie()
    @     0x7f4a30b6dfa2  caffe::Solver<>::InitTrainNet()
    @     0x7f4a30b6ee63  caffe::Solver<>::Init()
    @     0x7f4a30b6f036  caffe::Solver<>::Solver()
    @           0x40c3c0  caffe::GetSolver<>()
    @           0x406361  train()
    @           0x4048f1  main
    @     0x7f4a2fe86ec5  (unknown)
    @           0x404e9d  (unknown)
Aborted (core dumped)
shaunak@ubuntu:~/caffe$

错误的具体内容是什么，我该如何解决？

更新

这似乎是运行:

name: "WineNet"
layer {
  name: "data"
  type: "HDF5Data"
  top: "wine_train_data"
  top: "wine_train_label"
  hdf5_data_param {
    source: "examples/wine/train.txt"
    batch_size: 10
  }
}
layer {
  name: "fc1"
  type: "InnerProduct"
  bottom: "wine_train_data"
  top: "fc1"
  inner_product_param {
    num_output: 2
    }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "fc1"
  bottom: "wine_train_label"
  top: "loss"
}

更新2

几乎相同的模型：一个有效，另一个无效。我无法解释为什么！

作品：

name: "WineNet"
layer {
  name: "data"
  type: "HDF5Data"
  top: "wine_train_data"
  top: "wine_train_label"
  hdf5_data_param {
    source: "examples/wine/train.txt"
    batch_size: 10
  }
}
layer {
  name: "fc1"
  type: "InnerProduct"
  bottom: "wine_train_data"
  top: "fc1"
  inner_product_param {
    num_output: 2
    }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "fc1"
  bottom: "wine_train_label"
  top: "loss"
}

不会：

name:"wineclass"
layers {
  name: "data"
  type: "HDF5Data"
  top: "wine_train_data"
  top: "wine_train_label"
  hdf5_data_param {
    source: "examples/wine/train.txt"
    batch_size: 10
  }
}
layer {
  name: "ip"
  type: "InnerProduct"
  bottom: "wine_train_data"
  top: "ip"
  inner_product_param {
    num_output: 2
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip"
  bottom: "wine_train_label"
  top: "loss"
}

Answer 1

我运行昨天遇到了同样的问题。您可能需要检查您的 caffe 版本是否是最新的。他们大大改变了 protobuf 的定义。在你的例子中，"type" 曾经是一个枚举，现在它只需要一个字符串。

[更新] 来自评论中的讨论：答案是不用"layers"而是"layer".图层可能存在于一些旧的/过时的示例中。

Caffe HDF5神经网络基础实例解析模型文件失败

Caffe HDF5 neural network basic example fails to parse the model file

caffe

更新

更新2