tar -xzf protobuf-2.1.0.tar.gz 
 cd protobuf-2.1.0 
 ./configure --prefix=$INSTALL_DIR 
 make 
 make check 
 make install

关于简单例子的描述

我打算使用 Protobuf 和 C++ 开发一个十分简单的例子程序。 
该程序由两部分组成。第一部分被称为 Writer，第二部分叫做 Reader。 
Writer 负责将一些结构化的数据写入一个磁盘文件，Reader 则负责从该磁盘文件中读取结构化数据并打印到屏幕上。 
准备用于演示的结构化数据是 HelloWorld，它包含两个基本数据：

• ID，为一个整数类型的数据
• Str，这是一个字符串

书写 .proto 文件

首先我们需要编写一个 proto 文件，定义我们程序中需要处理的结构化数据，在 protobuf 的术语中，结构化数据被称为 Message。proto 文件非常类似 java 或者 C 语言的数据定义。代码清单 1 显示了例子应用中的 proto 文件内容。 
清单 1. proto 文件

package lm; 
 message helloworld 
 { 
    required int32     id = 1;  // ID 
    required string    str = 2;  // str 
    optional int32     opt = 3;  //optional field 
 }

编译 .proto 文件

写好 proto 文件之后就可以用 Protobuf 编译器将该文件编译成目标语言了。本例中我们将使用 C++。 
假设您的 proto 文件存放在 $SRC_DIR 下面，您也想把生成的文件放在同一个目录下，则可以使用如下命令：

编写 writer 和 Reader

如前所述，Writer将把一个结构化数据写入磁盘，以便其他人来读取。假如我们不使用 Protobuf，其实也有许多的选择。一个可能的方法是将数据转换为字符串，然后将字符串写入磁盘。转换为字符串的方法可以使用sprintf()，这非常简单。数字123可以变成字符串“123”。 
这样做似乎没有什么不妥，但是仔细考虑一下就会发现，这样的做法对写 Reader 的那个人的要求比较高，Reader 的作者必须了 Writer 的细节。比如”123”可以是单个数字 123，但也可以是三个数字 1,2 和 3，等等。这么说来，我们还必须让 Writer 定义一种分隔符一样的字符，以便 Reader 可以正确读取。但分隔符也许还会引起其他的什么问题。最后我们发现一个简单的 Helloworld 也需要写许多处理消息格式的代码。 
如果使用 Protobuf，那么这些细节就可以不需要应用程序来考虑了。 
使用 Protobuf，Writer 的工作很简单，需要处理的结构化数据由 .proto 文件描述，经过上一节中的编译过程后，该数据化结构对应了一个 C++ 的类，并定义在 lm.helloworld.pb.h 中。对于本例，类名为 lm::helloworld。 
Writer 需要 include 该头文件，然后便可以使用这个类了。 
现在，在 Writer 代码中，将要存入磁盘的结构化数据由一个 lm::helloworld 类的对象表示，它提供了一系列的 get/set 函数用来修改和读取结构化数据中的数据成员，或者叫 field。 
当我们需要将该结构化数据保存到磁盘上时，类 lm::helloworld 已经提供相应的方法来把一个复杂的数据变成一个字节序列，我们可以将这个字节序列写入磁盘。 
对于想要读取这个数据的程序来说，也只需要使用类 lm::helloworld 的相应反序列化方法来将这个字节序列重新转换会结构化数据。这同我们开始时那个“123”的想法类似，不过 Protobuf 想的远远比我们那个粗糙的字符串转换要全面，因此，我们不如放心将这类事情交给 Protobuf 吧。 
程序清单 2 演示了 Writer 的主要代码，您一定会觉得很简单吧？ 
清单 2. Writer 的主要代码

 #include "lm.helloworld.pb.h"
…

 int main(void) 
 { 

  lm::helloworld msg1; 
  msg1.set_id(101); 
  msg1.set_str(“hello”); 

  // Write the new address book back to disk. 
  fstream output("./log", ios::out | ios::trunc | ios::binary); 

  if (!msg1.SerializeToOstream(&output)) { 
      cerr << "Failed to write msg." << endl; 
      return -1; 
  }         
  return 0; 
 }

 #include "lm.helloworld.pb.h" 
…
 void ListMsg(const lm::helloworld & msg) { 
  cout << msg.id() << endl; 
  cout << msg.str() << endl; 
 } 

 int main(int argc, char* argv[]) { 

  lm::helloworld msg1; 

  { 
    fstream input("./log", ios::in | ios::binary); 
    if (!msg1.ParseFromIstream(&input)) { 
      cerr << "Failed to parse address book." << endl; 
      return -1; 
    } 
  } 

  ListMsg(msg1); 
  … 
 }

\>writer 
\>reader 
101 
Hello

二、caffe.proto中的几个重要数据类型

看完了上面关于protocol buffer的介绍，大家应该可以知道其实caffe.pb.cc里面的东西都是从caffe.proto编译而来的，无非就是一些关于这些数据结构（类）的标准化操作，比如

  void CopyFrom();
  void MergeFrom();
  void CopyFrom();
  void MergeFrom;
  void Clear();
  bool IsInitialized() const;
  int ByteSize() const;
  bool MergePartialFromCodedStream();
  void SerializeWithCachedSizes() const;
  SerializeWithCachedSizesToArray() const;
  int GetCachedSize()
  void SharedCtor();
  void SharedDtor();
  void SetCachedSize() const;

message BlobProto {//blob的属性以及blob中的数据(data\diff)
  optional int32 num = 1 [default = 0];
  optional int32 channels = 2 [default = 0];
  optional int32 height = 3 [default = 0];
  optional int32 width = 4 [default = 0];
  repeated float data = 5 [packed = true];
  repeated float diff = 6 [packed = true];
}

 message Datum {
  optional int32 channels = 1;
  optional int32 height = 2;
  optional int32 width = 3;
  optional bytes data = 4;//真实的图像数据，以字节存储(bytes)
  optional int32 label = 5;
  repeated float float_data = 6;//datum也能存float类型的数据(float)
}

message LayerParameter {
  repeated string bottom = 2; //输入的blob的名字(string)
  repeated string top = 3; //输出的blob的名字(string)
  optional string name = 4; //层的名字
  enum LayerType { //层的枚举（enum，和c++中的enum一样）
    NONE = 0;
    ACCURACY = 1;
    BNLL = 2;
    CONCAT = 3;
    CONVOLUTION = 4;
    DATA = 5;
    DROPOUT = 6;
    EUCLIDEAN_LOSS = 7;
    ELTWISE_PRODUCT = 25;
    FLATTEN = 8;
    HDF5_DATA = 9;
    HDF5_OUTPUT = 10;
    HINGE_LOSS = 28;
    IM2COL = 11;
    IMAGE_DATA = 12;
    INFOGAIN_LOSS = 13;
    INNER_PRODUCT = 14;
    LRN = 15;
    MEMORY_DATA = 29;
    MULTINOMIAL_LOGISTIC_LOSS = 16;
    POOLING = 17;
    POWER = 26;
    RELU = 18;
    SIGMOID = 19;
    SIGMOID_CROSS_ENTROPY_LOSS = 27;
    SOFTMAX = 20;
    SOFTMAX_LOSS = 21;
    SPLIT = 22;
    TANH = 23;
    WINDOW_DATA = 24;
  }
  optional LayerType type = 5; // 层的类型
  repeated BlobProto blobs = 6; //blobs的数值参数
  repeated float blobs_lr = 7; //学习速率(repeated)，如果你想那个设置一个blob的学习速率，你需要设置所有blob的学习速率。
  repeated float weight_decay = 8; //权值衰减(repeated)

  // 相对于某一特定层的参数(optional)
  optional ConcatParameter concat_param = 9;
  optional ConvolutionParameter convolution_param = 10;
  optional DataParameter data_param = 11;
  optional DropoutParameter dropout_param = 12;
  optional HDF5DataParameter hdf5_data_param = 13;
  optional HDF5OutputParameter hdf5_output_param = 14;
  optional ImageDataParameter image_data_param = 15;
  optional InfogainLossParameter infogain_loss_param = 16;
  optional InnerProductParameter inner_product_param = 17;
  optional LRNParameter lrn_param = 18;
  optional MemoryDataParameter memory_data_param = 22;
  optional PoolingParameter pooling_param = 19;
  optional PowerParameter power_param = 21;
  optional WindowDataParameter window_data_param = 20;
  optional V0LayerParameter layer = 1;
}

message NetParameter {
  optional string name = 1;//网络的名字
  repeated LayerParameter layers = 2; //repeated类似于数组
  repeated string input = 3;//输入层blob的名字
  repeated int32 input_dim = 4;//输入层blob的维度，应该等于(4*#input)
  optional bool force_backward = 5 [default = false];//网络是否进行反向传播。如果设置为否，则由网络的结构和学习速率来决定是否进行反向传播。
}

message SolverParameter {
  optional string train_net = 1; // 训练网络的proto file
  optional string test_net = 2; // 测试网络的proto file
  optional int32 test_iter = 3 [default = 0]; // 每次测试时的迭代次数
  optional int32 test_interval = 4 [default = 0]; // 两次测试的间隔迭代次数
  optional bool test_compute_loss = 19 [default = false];
  optional float base_lr = 5; // 基本学习率
  optional int32 display = 6; // 两次显示的间隔迭代次数
  optional int32 max_iter = 7; // 最大迭代次数
  optional string lr_policy = 8; // 学习速率衰减方式
  optional float gamma = 9; // 关于梯度下降的一个参数
  optional float power = 10; // 计算学习率的一个参数
  optional float momentum = 11; // 动量
  optional float weight_decay = 12; // 权值衰减
  optional int32 stepsize = 13; // 学习速率的衰减步长
  optional int32 snapshot = 14 [default = 0]; // snapshot的间隔
  optional string snapshot_prefix = 15; // snapshot的前缀
  optional bool snapshot_diff = 16 [default = false]; // 是否对于 diff 进行 snapshot
  enum SolverMode {
    CPU = 0;
    GPU = 1;
  }
  optional SolverMode solver_mode = 17 [default = GPU]; // solver的模式，默认为GPU
  optional int32 device_id = 18 [default = 0]; // GPU的ID
  optional int64 random_seed = 20 [default = -1]; // 随机数种子
}

三、caffe.proto源码

//
caffe.proto文件注释，
caffe版本:MS-caffe-master github 2016.8.20
caffe版本:BVLC-caffe-master github 2016.8.20
//
syntax = "proto2";
package caffe;  
// 数据块形状{指定Blob的形状或维度-4D}
message BlobShape {
  //数据块形状定义为Num×Channel×Height×Wight原因在于caffe基于容器的多维嵌套
  //来实现高维数据的封装。即vector(N)>。
  repeated int64 dim = 1 [packed = true];
}

// 数据块{形状，数据，微分}
message BlobProto {
  optional BlobShape shape = 7;
  repeated float data = 5 [packed = true];
  repeated float diff = 6 [packed = true];
  repeated double double_data = 8 [packed = true];
  repeated double double_diff = 9 [packed = true];

  //数据4D形状 -- 旧版本，已使用"BlobShape shape"代替：
  optional int32 num = 1 [default = 0]; //样本
  optional int32 channels = 2 [default = 0];
  optional int32 height = 3 [default = 0];
  optional int32 width = 4 [default = 0];
}

// 存放多个BlobProto实例的对应Index，易于引用
message BlobProtoVector {
  repeated BlobProto blobs = 1;
}

// 数据:{C,H,W,data(uchar&float),label} 图像样本
message Datum {
  optional int32 channels = 1;
  optional int32 height = 2;
  optional int32 width = 3;
  // the actual image data, in bytes
  optional bytes data = 4;
  optional int32 label = 5;
  // Optionally, the datum could also hold float data.
  repeated float float_data = 6;
  // If true data contains an encoded image that need to be decoded
  optional bool encoded = 7 [default = false];
}

//滤波器参数{Type(const|uniform|gauss),}
message FillerParameter {
  // The filler type.
  optional string type = 1 [default = 'constant'];
  optional float value = 2 [default = 0]; // the value in constant filler
  optional float min = 3 [default = 0]; // the min value in uniform filler
  optional float max = 4 [default = 1]; // the max value in uniform filler
  optional float mean = 5 [default = 0]; // the mean value in Gaussian filler
  optional float std = 6 [default = 1]; // the std value in Gaussian filler
  // 给定输入与权值相乘后应该得到非零输出，默认值-1意为不稀疏化高斯模板。
  optional int32 sparse = 7 [default = -1];
  // Normalize the filler variance by fan_in, fan_out, or their average.
  // Applies to 'xavier' and 'msra' fillers.（扇入，扇出）
  // 通过fanIn,fanOut,及其均值来归一化填充值的方差，有“xavier法”或“msra法”
  enum VarianceNorm {
    FAN_IN = 0;
    FAN_OUT = 1;
    AVERAGE = 2;
  }
  optional VarianceNorm variance_norm = 8 [default = FAN_IN];
}

//网络参数{网名，输入参数，数据块形状，forceBack，NetState,debugInfo,}
message NetParameter {
  optional string name = 1; // consider giving the network a name
  // 旧版--输入网络的数据块Blobs; 改为新版--InputParameter
  repeated string input = 3;
  // DEPRECATED. See InputParameter. The shape of the input blobs.
  // 旧版--输入的Blobs的形状； 改为新版--InputerParameter
  repeated BlobShape input_shape = 8;

  // 指定Blobs的4D输入形状 -- 已改为新版：input_shape代替
  // 如要使用旧版，对每个输入的blob都需要指定4个参数，Num×Cha×H×W
  // 因此 input_dim需要重复4次
  repeated int32 input_dim = 4;

  //确定网络是否要让每个层都强制反向传播。
  //如果设置为false,将根据网络结构和学习率来自动确定是否需要反向传播。
  //网络的当前状态"state"包括"phase","level","stage"。(???)
  //某些层需要设置phase属性，使其跳过网络运行时的某些状态.
  optional NetState state = 6;

  // 当运行Net::Forward/Backward/Update时，打印调试信息，默认false.
  optional bool debug_info = 7 [default = false];

  // 构成net的layers。每个layer的链接和行为通过LayerParameter配置。
  repeated LayerParameter layer = 100;  // ID 100 so layers are printed last.

  // DEPRECATED: use 'layer' instead.
  repeated V1LayerParameter layers = 2;
}

// NOTE：注意
// Update the next available ID when you add a new SolverParameter field.
// 当你添加一个新的SolverParameter属性时，需要更新下一个可获得的ID
// SolverParameter next available ID: 41 (last added: type)

//求解器参数{网络，}
message SolverParameter {
  //
  // Specifying the train and test networks
  //
  // Exactly one train net must be specified using one of the following fields:
  //     train_net_param, train_net, net_param, net
  // One or more test nets may be specified using any of the following fields:
  //     test_net_param, test_net, net_param, net
  // If more than one test net field is specified (e.g., both net and
  // test_net are specified), they will be evaluated in the field order given
  // above: (1) test_net_param, (2) test_net, (3) net_param/net.
  // A test_iter must be specified for each test_net.
  // A test_level and/or a test_stage may also be specified for each test_net.
  //
  //指定网络，可有以下的多种形式
  // Proto filename for the train net, possibly combined with one or more
  // test nets.
  optional string net = 24;
  // Inline train net param, possibly combined with one or more test nets.
  optional NetParameter net_param = 25;

  optional string train_net = 1; // Proto filename for the train net.
  repeated string test_net = 2; // Proto filenames for the test nets.
  optional NetParameter train_net_param = 21; // Inline train net params.
  repeated NetParameter test_net_param = 22; // Inline test net params.

 // 指定网络状态
 // The states for the train/test nets. Must be unspecified or
  // specified once per net.
  //
  // By default, all states will have solver = true;
  // train_state will have phase = TRAIN,
  // and all test_state's will have phase = TEST.
  // Other defaults are set according to the NetState defaults.
  optional NetState train_state = 26;
  repeated NetState test_state = 27;

  //测试迭代批次数：
  //合理设置可使得测试遍历完全部测试样本
  //合理值 = 测试样本总数/每批次测试数 = totalTestSamples/batchSize
  repeated int32 test_iter = 3;

  //训练迭代批次数：
  //两次测试之间所经历的训练迭代次数:合理设置可使得训练遍历完全部训练样本
  //合理值 = 训练样本总数/每批次训练数 = totalTrainSamples/batchSize
  optional int32 test_interval = 4 [default = 0];
  //训练test_interval个批次，再测试test_iter个批次，为一个回合(epoch)
  //合理设置应使得每个回合内，遍历覆盖到全部训练样本和测试样本

  //默认不计算测试时损失
  optional bool test_compute_loss = 19 [default = false];

  // 如设置为真，则在训练前运行一次测试，以确保内存足够，并打印初始损失值
  optional bool test_initialization = 32 [default = true];
  // 基本学习速率
  optional float base_lr = 5; // The base learning rate
  // 打印信息的遍历间隔，遍历多少个批次打印一次信息。设置为0则不打印。
  optional int32 display = 6;
  // Display the loss averaged over the last average_loss iterations
  // 打印最后一个迭代批次下的平均损失（？）
  optional int32 average_loss = 33 [default = 1];
  // 训练最大迭代次数
  optional int32 max_iter = 7;
  // accumulate gradients over `iter_size` x `batch_size` instances
  // 累积梯度误差基于“iter_size×batchSize”个样本实例
  // “批次数×批量数”=“遍历的批次数×每批的样本数”个样本实例
  optional int32 iter_size = 36 [default = 1];

  //学习率衰减策略(7种)
  // The learning rate decay policy. The currently implemented learning rate
  // policies are as follows:
  //    - fixed: always return base_lr.
  //    - step: return base_lr * gamma ^ (floor(iter / step))
  //    - exp: return base_lr * gamma ^ iter
  //    - inv: return base_lr * (1 + gamma * iter) ^ (- power)
  //    - multistep: similar to step butallows non uniform steps defined by
  //      stepvalue
  //    - poly: the effective learning rate follows a polynomial decay, to be
  //      zero by the max_iter. return base_lr (1 - iter/max_iter) ^ (power)
  //    - sigmoid: the effective learning rate follows a sigmod decay
  //      return base_lr ( 1/(1 + exp(-gamma * (iter - stepsize))))
  //
  // 在上述参数中，base_lr, max_iter, gamma, step, stepvalue and power 被定义
  // 在solver.prototxt文件中，iter是当前迭代次数。
  optional string lr_policy = 8; //学习率调节策略
  optional float gamma = 9; // The parameter to compute the learning rate.
  optional float power = 10; // The parameter to compute the learning rate.
  optional float momentum = 11; // The momentum value.动量
  optional float weight_decay = 12; // The weight decay.权值衰减系数
  //由权值衰减系数所控制的正则化类型：L1或L2范数，默认L2
  optional string regularization_type = 29 [default = "L2"];
  //"step"策略下，学习率的步长值
  optional int32 stepsize = 13;
  //"multistep"策略下的步长值
  repeated int32 stepvalue = 34;

  //设置梯度裁剪阈值为>=0，当其实际L2范数超出此值时(?)
  optional float clip_gradients = 35 [default = -1];

  //快照间隔，遍历多少次对模型和求解器状态保存一次
  optional int32 snapshot = 14 [default = 0]; // The snapshot interval
  optional string snapshot_prefix = 15; // The prefix for the snapshot.
  //是否对diff快照，有助调试，但最终的protocol buffer尺寸会很大
  optional bool snapshot_diff = 16 [default = false];
  //快照数据保存格式{hdf5,binaryproto(默认)}
  enum SnapshotFormat {
    HDF5 = 0;
    BINARYPROTO = 1;
  }
  optional SnapshotFormat snapshot_format = 37 [default = BINARYPROTO];
  // the mode solver will use: 0 for CPU and 1 for GPU. Use GPU in default.
  enum SolverMode {
    CPU = 0;
    GPU = 1;
  }
  求解模式{GPU(device_id),CPU}
  optional SolverMode solver_mode = 17 [default = GPU];
  optional int32 device_id = 18 [default = 0];
  //随机数种子，设为正则表示Solver会以此为随机数初始化caffe,可产生重复随机
  //数，易于重复试验；设为默认-1代表使用系统时钟作为种子。
  optional int64 random_seed = 20 [default = -1];

  //求解器类型=SGD(默认)
  optional string type = 40 [default = "SGD"];

  // numerical stability for RMSProp, AdaGrad and AdaDelta and Adam
  optional float delta = 31 [default = 1e-8];
  // parameters for the Adam solver
  optional float momentum2 = 39 [default = 0.999];

  // RMSProp decay value
  // MeanSquare(t) = rms_decay*MeanSquare(t-1) + (1-rms_decay)*SquareGradient(t)
  optional float rms_decay = 38;

  //若真，则打印网络状态信息，有助于调试问题
  optional bool debug_info = 23 [default = false];

  //若假，则不会在训练后保存快照
  optional bool snapshot_after_train = 28 [default = true];

  // DEPRECATED: old solver enum types, use string instead
  enum SolverType {
    SGD = 0;
    NESTEROV = 1;
    ADAGRAD = 2;
    RMSPROP = 3;
    ADADELTA = 4;
    ADAM = 5;
  }
  // DEPRECATED: use type instead of solver_type
  optional SolverType solver_type = 30 [default = SGD];
}

//对求解器状态进行快照的消息
message SolverState {
  optional int32 iter = 1; // The current iteration
  optional string learned_net = 2; // The file that stores the learned net.
  repeated BlobProto history = 3; // The history for sgd solvers
  optional int32 current_step = 4 [default = 0]; // The current step for learning rate
}

enum Phase {
   TRAIN = 0;
   TEST = 1;
}
//NetState{phase,level,stage}
message NetState {
  optional Phase phase = 1 [default = TEST];
  optional int32 level = 2 [default = 0];
  repeated string stage = 3;
}

//网络状态规则{phases,levels,stages}
message NetStateRule {
  //在NetState中设置phase值(TRAIN|TEST)，使其符合此规则
  optional Phase phase = 1;

  //设置layer中所使用的最小最大levels。使其不定义以满足忽视level的规则。
  optional int32 min_level = 2;
  optional int32 max_level = 3;

  // Customizable sets of stages to include or exclude.
  // The net must have ALL of the specified stages and NONE of the specified
  // "not_stage"s to meet the rule.
  // (Use multiple NetStateRules to specify conjunctions of stages.)
  //可定制的stages集合，用于include或exclude在网络中。网络必须包含全
  //部制定的"stages"或不包含全部制定的"not_stage"
  repeated string stage = 4;
  repeated string not_stage = 5;
}

// Specifies training parameters (multipliers on global learning constants,
// and the name and other settings used for weight sharing).
//指定训练参数(乘数及全局学习率常数)和其名称，以及其他用于权值共享的设置。
message ParamSpec {
  // 设定参数blobs的名称--用于在层间共享参数，若无此需求则不用设计。
  optional string name = 1;

  //共享权重时是否需要其形状相同或仅仅数量相同，默认为形状相同
  optional DimCheckMode share_mode = 2;
  enum DimCheckMode {
    // STRICT (default) 形状相同(num, channels, height, width)都匹配.
    STRICT = 0;
    // PERMISSIVE 数量相同
    PERMISSIVE = 1;
  }

  // The multiplier on the global learning rate for this parameter.
  // 全局学习率的乘数
  optional float lr_mult = 3 [default = 1.0];

  // The multiplier on the global weight decay for this parameter.
  // 全局权值衰减系数的乘数
  optional float decay_mult = 4 [default = 1.0];
}

//注意：
//当在LayerParameter中新增字段时，需要为其更新下一个可用ID。
//比如，最近新增了smooth_l1_loss_param层，则为其指定层专属ID:149。
//层参数{名称，类型，输入底，输出顶，阶段，损失加权系数，全局乘数，}
message LayerParameter {
  optional string name = 1; // 类名称
  optional string type = 2; // 类类型
  repeated string bottom = 3; // the name of each bottom blob 输入blob名称
  repeated string top = 4; // the name of each top blob 输出blob名称

  // The train / test phase for computation. //阶段，运行时状态
  optional Phase phase = 10;

  //每层输出blob在目标损失函数中的加权系数，每层默认为0或1
  repeated float loss_weight = 5;

  //指定训练参数(全局学习率上的乘数lr_mrlt)
  repeated ParamSpec param = 6;


  // The blobs containing the numeric parameters of the layer.
  //包含每层数值参数的blobs
  repeated BlobProto blobs = 7;

  // Specifies whether to backpropagate to each bottom. If unspecified,
  // Caffe will automatically infer whether each input needs backpropagation
  // to compute parameter gradients. If set to true for some inputs,
  // backpropagation to those inputs is forced; if set false for some inputs,
  // backpropagation to those inputs is skipped.
  //
  // The size must be either 0 or equal to the number of bottoms.

  repeated bool propagate_down = 11;

  // Rules控制每层是否被包含在网络中，基于当前的NetState. 可使用非0数规则来
  // include或exclude，但不能兼有。如果未指定include或exclude规则，则该层总是
  // 被包含在内。
  repeated NetStateRule include = 8;
  repeated NetStateRule exclude = 9;

  // 用于数据预处理的参数
  optional TransformationParameter transform_param = 100;

  // 由loss层共享的参数.
  optional LossParameter loss_param = 101;

  // Layer type-specific parameters.
  //
  // Note: certain layers may have more than one computational engine
  // for their implementation. These layers include an Engine type and
  // engine parameter for selecting the implementation.
  // The default for the engine is set by the ENGINE switch at compile-time.
  // 层类型指定参数
  // 注意：
  optional AccuracyParameter accuracy_param = 102;
  optional ArgMaxParameter argmax_param = 103;
  optional BatchNormParameter batch_norm_param = 139;
  optional BiasParameter bias_param = 141;
  optional ConcatParameter concat_param = 104;
  optional ContrastiveLossParameter contrastive_loss_param = 105;
  optional ConvolutionParameter convolution_param = 106;
  optional CropParameter crop_param = 144;
  optional DataParameter data_param = 107;
  optional DropoutParameter dropout_param = 108;
  optional DummyDataParameter dummy_data_param = 109;
  optional EltwiseParameter eltwise_param = 110;
  optional ELUParameter elu_param = 140;
  optional EmbedParameter embed_param = 137;
  optional ExpParameter exp_param = 111;
  optional FlattenParameter flatten_param = 135;
  optional HDF5DataParameter hdf5_data_param = 112;
  optional HDF5OutputParameter hdf5_output_param = 113;
  optional HingeLossParameter hinge_loss_param = 114;
  optional ImageDataParameter image_data_param = 115;
  optional InfogainLossParameter infogain_loss_param = 116;
  optional InnerProductParameter inner_product_param = 117;
  optional InputParameter input_param = 143;
  optional LogParameter log_param = 134;
  optional LRNParameter lrn_param = 118;
  optional MemoryDataParameter memory_data_param = 119;
  optional MVNParameter mvn_param = 120;
  optional ParameterParameter parameter_param = 145;
  optional PoolingParameter pooling_param = 121;
  optional PowerParameter power_param = 122;
  optional PReLUParameter prelu_param = 131;
  optional PythonParameter python_param = 130;
  optional RecurrentParameter recurrent_param = 146;
  optional ReductionParameter reduction_param = 136;
  optional ReLUParameter relu_param = 123;
  optional ReshapeParameter reshape_param = 133;
  optional ROIPoolingParameter roi_pooling_param = 147;
  optional ScaleParameter scale_param = 142;
  optional SigmoidParameter sigmoid_param = 124;
  optional SmoothL1LossParameter smooth_l1_loss_param = 148;
  optional SoftmaxParameter softmax_param = 125;
  optional SPPParameter spp_param = 132;
  optional SliceParameter slice_param = 126;
  optional TanHParameter tanh_param = 127;
  optional ThresholdParameter threshold_param = 128;
  optional TileParameter tile_param = 138;
  optional WindowDataParameter window_data_param = 129;
  optional MILDataParameter mil_data_param = 0x004d4944; //"MID"
  optional MILParameter mil_param = 0x004d494c; //"MIL"
}

// 对数据层进行转换的参数
message TransformationParameter {
  // 对data执行预处理，比如简单缩放,去均值。
  optional float scale = 1 [default = 1];
  // Specify if we want to randomly mirror data.//镜像
  optional bool mirror = 2 [default = false];
  // Specify if we would like to randomly crop an image.//随机裁剪
  optional uint32 crop_size = 3 [default = 0];
  // 指定均值文件或均值，二者不可兼有；在对应通道上减去此均值；
  optional string mean_file = 4;
  repeated float mean_value = 5;
  // 强制转换图像为3通道彩色
  optional bool force_color = 6 [default = false];
  // 强制转换为灰度图
  optional bool force_gray = 7 [default = false];
}

// Loss层参数
message LossParameter {
  // 如果被指定，则忽略给定label的实例
  optional int32 ignore_label = 1;
  // 如何对loss层损失归一化，使其跨越"batches,spatial(H*W)"或其他维度。
  // 目前仅仅在SoftmaxWithLoss层中实现。
  // 归一化模式
  enum NormalizationMode {
    // 基于batchSize×spatialDim归一化.所设定的忽略标签将不被忽略。
    FULL = 0;
    // 基于输出位置的总数量(batchSize×H×W)归一化，不包括被忽视的标签。
    // 若未设置被忽视标签，则其行为与FULL相同。
    VALID = 1;
    // Divide by the batch size.基于batchSize进行归一化。
    BATCH_SIZE = 2;
    // Do not normalize the loss.不归一化损失
    NONE = 3;
  }
  optional NormalizationMode normalization = 3 [default = VALID];
  // 旧版--新版如上所述。
  // 若"normalization"被指定则忽略此参数；若未被指定，可设置下值为false
  // 则基于batchSize归一化。
  optional bool normalize = 2;
}

// Messages that store parameters used by individual layer types follow, in
// alphabetical order.

message AccuracyParameter {
  // When computing accuracy, count as correct by comparing the true label to
  // the top k scoring classes.  By default, only compare to the top scoring
  // class (i.e. argmax). //Topk正确率计算
  optional uint32 top_k = 1 [default = 1];

  // The "label" axis of the prediction blob, whose argmax corresponds to the
  // predicted label -- may be negative to index from the end (e.g.,-1 for the
  // last axis).  For example, if axis == 1 and the predictions are
  // (N x C x H x W), the label blob is expected to contain N*H*W ground truth
  // labels with integer values in {0, 1, ..., C-1}.
  // 预测blob的"label"轴--其最大值才对应于预测标签--的索引有可能从负值开始。
  // 即: predicted_labels=argmax(predictions blob,label_axis)
  // 比如axis==1,其预测blob为(N x C x H x W), 而标签blob被期望包含(N×H×W)个
  // 真实标签，且标签值为{0,1,2...C-1}。
  optional int32 axis = 2 [default = 1];

  // If specified, ignore instances with the given label.
  // 如果指定，则忽略给定标签的对应实例
  optional int32 ignore_label = 3;
}
//输出最大化参数，对预测标签进行最大化
message ArgMaxParameter {
  // If true produce pairs (argmax, maxval)
  // 如果真，则产生(argmax,maxval)对
  optional bool out_max_val = 1 [default = false];
  optional uint32 top_k = 2 [default = 1];
  // The axis along which to maximise -- may be negative to index from the
  // end (e.g., -1 for the last axis).
  // By default ArgMaxLayer maximizes over the flattened trailing dimensions
  // for each index of the first / num dimension. ??
  //
  optional int32 axis = 3;
}
//拼接参数
message ConcatParameter {
  // The axis along which to concatenate -- may be negative to index from the
  // end (e.g., -1 for the last axis).  Other axes must have the
  // same dimension for all the bottom blobs.
  // By default, ConcatLayer concatenates blobs along the "channels" axis (1).
  optional int32 axis = 2 [default = 1];

  // DEPRECATED: alias for "axis" -- does not support negative indexing.
  optional uint32 concat_dim = 1 [default = 1];
}
//BatchNormParameter参数，源于论文batchNorm
message BatchNormParameter {
  // If false, accumulate global mean/variance values via a moving average. If
  // true, use those accumulated values instead of computing mean/variance
  // across the batch.
  optional bool use_global_stats = 1;
  // How much does the moving average decay each iteration?
  optional float moving_average_fraction = 2 [default = .999];
  // Small value to add to the variance estimate so that we don't divide by
  // zero.
  optional float eps = 3 [default = 1e-5];
}
//偏置参数
message BiasParameter {
  // The first axis of bottom[0] (the first input Blob) along which to apply
  // bottom[1] (the second input Blob).  May be negative to index from the end
  // (e.g., -1 for the last axis).
  //
  // For example, if bottom[0] is 4D with shape 100x3x40x60, the output
  // top[0] will have the same shape, and bottom[1] may have any of the
  // following shapes (for the given value of axis):
  //    (axis == 0 == -4) 100; 100x3; 100x3x40; 100x3x40x60
  //    (axis == 1 == -3)          3;     3x40;     3x40x60
  //    (axis == 2 == -2)                   40;       40x60
  //    (axis == 3 == -1)                                60
  // Furthermore, bottom[1] may have the empty shape (regardless of the value of
  // "axis") -- a scalar bias.
  optional int32 axis = 1 [default = 1];

  // (num_axes is ignored unless just one bottom is given and the bias is
  // a learned parameter of the layer.  Otherwise, num_axes is determined by the
  // number of axes by the second bottom.)
  // The number of axes of the input (bottom[0]) covered by the bias
  // parameter, or -1 to cover all axes of bottom[0] starting from `axis`.
  // Set num_axes := 0, to add a zero-axis Blob: a scalar.
  optional int32 num_axes = 2 [default = 1];

  // (filler is ignored unless just one bottom is given and the bias is
  // a learned parameter of the layer.)
  // The initialization for the learned bias parameter.
  // Default is the zero (0) initialization, resulting in the BiasLayer
  // initially performing the identity operation.
  optional FillerParameter filler = 3;
}
//对比度损失参数
message ContrastiveLossParameter {
  // margin for dissimilar pair
  optional float margin = 1 [default = 1.0];
  // The first implementation of this cost did not exactly match the cost of
  // Hadsell et al 2006 -- using (margin - d^2) instead of (margin - d)^2.
  // legacy_version = false (the default) uses (margin - d)^2 as proposed in the
  // Hadsell paper. New models should probably use this version.
  // legacy_version = true uses (margin - d^2). This is kept to support /
  // reproduce existing models and results
  optional bool legacy_version = 2 [default = false];
}
//卷积参数
message ConvolutionParameter {
  optional uint32 num_output = 1; // The number of outputs for the layer
  optional bool bias_term = 2 [default = true]; // whether to have bias terms

  // Pad, kernel size, and stride are all given as a single value for equal
  // dimensions in all spatial dimensions, or once per spatial dimension.
  repeated uint32 pad = 3; // The padding size; defaults to 0
  repeated uint32 kernel_size = 4; // The kernel size
  repeated uint32 stride = 6; // The stride; defaults to 1
  // Factor used to dilate the kernel, (implicitly) zero-filling the resulting
  // holes. (Kernel dilation is sometimes referred to by its use in the
  // algorithme 脿 trous from Holschneider et al. 1987.)
  repeated uint32 dilation = 18; // The dilation; defaults to 1

  // For 2D convolution only, the *_h and *_w versions may also be used to
  // specify both spatial dimensions.
  optional uint32 pad_h = 9 [default = 0]; // The padding height (2D only)
  optional uint32 pad_w = 10 [default = 0]; // The padding width (2D only)
  optional uint32 kernel_h = 11; // The kernel height (2D only)
  optional uint32 kernel_w = 12; // The kernel width (2D only)
  optional uint32 stride_h = 13; // The stride height (2D only)
  optional uint32 stride_w = 14; // The stride width (2D only)

  optional uint32 group = 5 [default = 1]; // The group size for group conv

  optional FillerParameter weight_filler = 7; // The filler for the weight
  optional FillerParameter bias_filler = 8; // The filler for the bias
  enum Engine {
    DEFAULT = 0; //CPU
    CAFFE = 1;   //GPU-CUDA
    CUDNN = 2;   //GPU-CUDA-CUDNN
  }
  optional Engine engine = 15 [default = DEFAULT];

  // The axis to interpret as "channels" when performing convolution.
  // Preceding dimensions are treated as independent inputs;
  // succeeding dimensions are treated as "spatial".
  // With (N, C, H, W) inputs, and axis == 1 (the default), we perform
  // N independent 2D convolutions, sliding C-channel (or (C/g)-channels, for
  // groups g>1) filters across the spatial axes (H, W) of the input.
  // With (N, C, D, H, W) inputs, and axis == 1, we perform
  // N independent 3D convolutions, sliding (C/g)-channels
  // filters across the spatial axes (D, H, W) of the input.
  optional int32 axis = 16 [default = 1];

  // Whether to force use of the general ND convolution, even if a specific
  // implementation for blobs of the appropriate number of spatial dimensions
  // is available. (Currently, there is only a 2D-specific convolution
  // implementation; for input blobs with num_axes != 2, this option is
  // ignored and the ND implementation will be used.)
  optional bool force_nd_im2col = 17 [default = false];
}
//裁剪参数
message CropParameter {
  // To crop, elements of the first bottom are selected to fit the dimensions
  // of the second, reference bottom. The crop is configured by
  // - the crop `axis` to pick the dimensions for cropping
  // - the crop `offset` to set the shift for all/each dimension
  // to align the cropped bottom with the reference bottom.
  // All dimensions up to but excluding `axis` are preserved, while
  // the dimensions including and trailing `axis` are cropped.
  // If only one `offset` is set, then all dimensions are offset by this amount.
  // Otherwise, the number of offsets must equal the number of cropped axes to
  // shift the crop in each dimension accordingly.
  // Note: standard dimensions are N,C,H,W so the default is a spatial crop,
  // and `axis` may be negative to index from the end (e.g., -1 for the last
  // axis).
  optional int32 axis = 1 [default = 2];
  repeated uint32 offset = 2;
}
//数据参数
message DataParameter {
  enum DB {
    LEVELDB = 0;
    LMDB = 1;
  }
  // Specify the data source.
  optional string source = 1;
  // Specify the batch size.
  optional uint32 batch_size = 4;
  // The rand_skip variable is for the data layer to skip a few data points
  // to avoid all asynchronous sgd clients to start at the same point. The skip
  // point would be set as rand_skip * rand(0,1). Note that rand_skip should not
  // be larger than the number of keys in the database.
  // DEPRECATED. Each solver accesses a different subset of the database.
  optional uint32 rand_skip = 7 [default = 0];
  optional DB backend = 8 [default = LEVELDB];
  // DEPRECATED. See TransformationParameter. For data pre-processing, we can do
  // simple scaling and subtracting the data mean, if provided. Note that the
  // mean subtraction is always carried out before scaling.
  optional float scale = 2 [default = 1];
  optional string mean_file = 3;
  // DEPRECATED. See TransformationParameter. Specify if we would like to randomly
  // crop an image.
  optional uint32 crop_size = 5 [default = 0];
  // DEPRECATED. See TransformationParameter. Specify if we want to randomly mirror
  // data.
  optional bool mirror = 6 [default = false];
  // Force the encoded image to have 3 color channels
  optional bool force_encoded_color = 9 [default = false];
  // Prefetch queue (Number of batches to prefetch to host memory, increase if
  // data access bandwidth varies).
  optional uint32 prefetch = 10 [default = 4];
}
//DropoutParameter参数
message DropoutParameter {
  optional float dropout_ratio = 1 [default = 0.5]; // dropout ratio
  optional bool scale_train = 2 [default = true];  // scale train or test phase
}

// DummyDataLayer fills any number of arbitrarily shaped blobs with random
// (or constant) data generated by "Fillers" (see "message FillerParameter").
message DummyDataParameter {
  // This layer produces N >= 1 top blobs.  DummyDataParameter must specify 1 or N
  // shape fields, and 0, 1 or N data_fillers.
  //
  // If 0 data_fillers are specified, ConstantFiller with a value of 0 is used.
  // If 1 data_filler is specified, it is applied to all top blobs.  If N are
  // specified, the ith is applied to the ith top blob.
  repeated FillerParameter data_filler = 1;
  repeated BlobShape shape = 6;

  // 4D dimensions -- deprecated.  Use "shape" instead.
  repeated uint32 num = 2;
  repeated uint32 channels = 3;
  repeated uint32 height = 4;
  repeated uint32 width = 5;
}

message EltwiseParameter {
  enum EltwiseOp {
    PROD = 0;
    SUM = 1;
    MAX = 2;
  }
  optional EltwiseOp operation = 1 [default = SUM]; // element-wise operation
  repeated float coeff = 2; // blob-wise coefficient for SUM operation

  // Whether to use an asymptotically slower (for >2 inputs) but stabler method
  // of computing the gradient for the PROD operation. (No effect for SUM op.)
  optional bool stable_prod_grad = 3 [default = true];
}

// Message that stores parameters used by ELULayer
message ELUParameter {
  // Described in:
  // Clevert, D.-A., Unterthiner, T., & Hochreiter, S. (2015). Fast and Accurate
  // Deep Network Learning by Exponential Linear Units (ELUs). arXiv
  optional float alpha = 1 [default = 1];
}

// Message that stores parameters used by EmbedLayer
message EmbedParameter {
  optional uint32 num_output = 1; // The number of outputs for the layer
  // The input is given as integers to be interpreted as one-hot
  // vector indices with dimension num_input.  Hence num_input should be
  // 1 greater than the maximum possible input value.
  optional uint32 input_dim = 2;

  optional bool bias_term = 3 [default = true]; // Whether to use a bias term
  optional FillerParameter weight_filler = 4; // The filler for the weight
  optional FillerParameter bias_filler = 5; // The filler for the bias

}

// Message that stores parameters used by ExpLayer
message ExpParameter {
  // ExpLayer computes outputs y = base ^ (shift + scale * x), for base > 0.
  // Or if base is set to the default (-1), base is set to e,
  // so y = exp(shift + scale * x).
  optional float base = 1 [default = -1.0];
  optional float scale = 2 [default = 1.0];
  optional float shift = 3 [default = 0.0];
}

/// Message that stores parameters used by FlattenLayer
message FlattenParameter {
  // The first axis to flatten: all preceding axes are retained in the output.
  // May be negative to index from the end (e.g., -1 for the last axis).
  optional int32 axis = 1 [default = 1];

  // The last axis to flatten: all following axes are retained in the output.
  // May be negative to index from the end (e.g., the default -1 for the last
  // axis).
  optional int32 end_axis = 2 [default = -1];
}

// Message that stores parameters used by HDF5DataLayer
message HDF5DataParameter {
  // Specify the data source.
  optional string source = 1;
  // Specify the batch size.
  optional uint32 batch_size = 2;

  // Specify whether to shuffle the data.
  // If shuffle == true, the ordering of the HDF5 files is shuffled,
  // and the ordering of data within any given HDF5 file is shuffled,
  // but data between different files are not interleaved; all of a file's
  // data are output (in a random order) before moving onto another file.
  optional bool shuffle = 3 [default = false];
}

message HDF5OutputParameter {
  optional string file_name = 1;
}

message HingeLossParameter {
  enum Norm {
    L1 = 1;
    L2 = 2;
  }
  // Specify the Norm to use L1 or L2
  optional Norm norm = 1 [default = L1];
}
//数据集参数
message ImageDataParameter {
  // 指定数据源文件
  optional string source = 1;
  // 指定批量大小batchSize
  optional uint32 batch_size = 4 [default = 1];
  // The rand_skip variable is for the data layer to skip a few data points
  // to avoid all asynchronous sgd clients to start at the same point. The skip
  // point would be set as rand_skip * rand(0,1). Note that rand_skip should not
  // be larger than the number of keys in the database.
  // 随机跳过rand_skip * rand(0,1)个样本，以使得SGD从不同状态点启动
  optional uint32 rand_skip = 7 [default = 0];
  // Whether or not ImageLayer should shuffle the list of files at every epoch.是否在每个回合都混排图片，默认否
  optional bool shuffle = 8 [default = false];
  // It will also resize images if new_height or new_width are not zero.
  // 若以下2个值不为0，则将图片缩放为下面的形状
  optional uint32 new_height = 9 [default = 0];
  optional uint32 new_width = 10 [default = 0];
  // Specify if the images are color or gray指明是彩色还是灰度图
  optional bool is_color = 11 [default = true];
  // DEPRECATED. See TransformationParameter. For data pre-processing, we can do
  // simple scaling and subtracting the data mean, if provided. Note that the
  // mean subtraction is always carried out before scaling.
  // 旧版--图片预处理参数，新版用TransformationParameter
  optional float scale = 2 [default = 1];
  optional string mean_file = 3;
  // DEPRECATED. See TransformationParameter. Specify if we would like to randomly
  // crop an image.
  optional uint32 crop_size = 5 [default = 0];
  // DEPRECATED. See TransformationParameter. Specify if we want to randomly mirror
  // data.
  optional bool mirror = 6 [default = false];
  optional string root_folder = 12 [default = ""];
}
//信息增益损失参数
message InfogainLossParameter {
  // Specify the infogain matrix source.
  optional string source = 1;
}
//内积参数
message InnerProductParameter {
  optional uint32 num_output = 1; // The number of outputs for the layer
  optional bool bias_term = 2 [default = true]; // whether to have bias terms
  optional FillerParameter weight_filler = 3; // The filler for the weight
  optional FillerParameter bias_filler = 4; // The filler for the bias

  // The first axis to be lumped into a single inner product computation;
  // all preceding axes are retained in the output.
  // May be negative to index from the end (e.g., -1 for the last axis).
  optional int32 axis = 5 [default = 1];
  // Specify whether to transpose the weight matrix or not.
  // If transpose == true, any operations will be performed on the transpose
  // of the weight matrix. The weight matrix itself is not going to be transposed
  // but rather the transfer flag of operations will be toggled accordingly.
  optional bool transpose = 6 [default = false];
}
//输入参数
message InputParameter {
  // This layer produces N >= 1 top blob(s) to be assigned manually.
  // Define N shapes to set a shape for each top.
  // Define 1 shape to set the same shape for every top.
  // Define no shape to defer to reshaping manually.
  // 此层管理输入(top)blobs，当输入blob个数N≥1，可使其自动分配。
  // 设定N个shapes为N个输入blob；设定1个shape使得全部输入blob形状相同；
  // 不设定，可手动调整。
  // 可查看.\models\bvlc_reference_caffenet\deploy.prototxt中指定1个shape
  repeated BlobShape shape = 1;
}

// LogLayer的参数
message LogParameter {
  // LogLayer computes outputs y = log_base(shift + scale * x), for base > 0.
  // Or if base is set to the default (-1), base is set to e,
  // so y = ln(shift + scale * x) = log_e(shift + scale * x)
  optional float base = 1 [default = -1.0];
  optional float scale = 2 [default = 1.0];
  optional float shift = 3 [default = 0.0];
}

// LRNLayer层参数
message LRNParameter {
  optional uint32 local_size = 1 [default = 5];
  optional float alpha = 2 [default = 1.];
  optional float beta = 3 [default = 0.75];
  enum NormRegion {
    ACROSS_CHANNELS = 0;
    WITHIN_CHANNEL = 1;
  }
  optional NormRegion norm_region = 4 [default = ACROSS_CHANNELS];
  optional float k = 5 [default = 1.];
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 6 [default = DEFAULT];
}

//数据内存占用参数
message MemoryDataParameter {
  optional uint32 batch_size = 1;
  optional uint32 channels = 2;
  optional uint32 height = 3;
  optional uint32 width = 4;
}
//MVN参数{均值，方差，跨通道}(mean-varance-normalization)
message MVNParameter {
  // This parameter can be set to false to normalize mean only
  // 设定为false时仅归一化均值，否则包括方差
  optional bool normalize_variance = 1 [default = true];

  // This parameter can be set to true to perform DNN-like MVN
  // 执行跨通道归一化,类似于DNN的MVN；默认否，只执行Spatial内归一化。
  optional bool across_channels = 2 [default = false];

  // Epsilon for not dividing by zero while normalizing variance
  // 防止除0的极小数
  optional float eps = 3 [default = 1e-9];
}

//？？
message ParameterParameter {
  optional BlobShape shape = 1;
}
//池化层参数
message PoolingParameter {
  enum PoolMethod {
    MAX = 0;
    AVE = 1;
    STOCHASTIC = 2;
  }
  optional PoolMethod pool = 1 [default = MAX]; // The pooling method
  // Pad, kernel size, and stride are all given as a single value for equal
  // dimensions in height and width or as Y, X pairs.
  optional uint32 pad = 4 [default = 0]; // The padding size (equal in Y, X)
  optional uint32 pad_h = 9 [default = 0]; // The padding height
  optional uint32 pad_w = 10 [default = 0]; // The padding width
  optional uint32 kernel_size = 2; // The kernel size (square)
  optional uint32 kernel_h = 5; // The kernel height
  optional uint32 kernel_w = 6; // The kernel width
  optional uint32 stride = 3 [default = 1]; // The stride (equal in Y, X)
  optional uint32 stride_h = 7; // The stride height
  optional uint32 stride_w = 8; // The stride width
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 11 [default = DEFAULT];
  // If global_pooling then it will pool over the size of the bottom by doing
  // kernel_h = bottom->height and kernel_w = bottom->width
  optional bool global_pooling = 12 [default = false];
}

message PowerParameter {
  // PowerLayer computes outputs y = (shift + scale * x) ^ power.
  optional float power = 1 [default = 1.0];
  optional float scale = 2 [default = 1.0];
  optional float shift = 3 [default = 0.0];
}
//Python参数
message PythonParameter {
  optional string module = 1;
  optional string layer = 2;
  // This value is set to the attribute `param_str` of the `PythonLayer` object
  // in Python before calling the `setup()` method. This could be a number,
  // string, dictionary in Python dict format, JSON, etc. You may parse this
  // string in `setup` method and use it in `forward` and `backward`.
  optional string param_str = 3 [default = ''];
  // Whether this PythonLayer is shared among worker solvers during data parallelism.
  // If true, each worker solver sequentially run forward from this layer.
  // This value should be set true if you are using it as a data layer.
  optional bool share_in_parallel = 4 [default = false];
}

// RecurrentLayer参数
message RecurrentParameter {
  // 输出表示的维度必须是非0的
  optional uint32 num_output = 1 [default = 0];

  optional FillerParameter weight_filler = 2; //weight权值参数
  optional FillerParameter bias_filler = 3;   //bias偏置参数

  // Whether to enable displaying debug_info in the unrolled recurrent net.
  // 在展开RCNN时是否打印deuginfo
  optional bool debug_info = 4 [default = false];

  // Whether to add as additional inputs (bottoms) the initial hidden state
  // blobs, and add as additional outputs (tops) the final timestep hidden state
  // blobs.  The number of additional bottom/top blobs required depends on the
  // recurrent architecture -- e.g., 1 for RNNs, 2 for LSTMs.
  // 是否添加初始化的隐藏blobs作为额外输入(bottoms)，以及添加最终的timestep隐
  // 藏blobs作为额外输出（tops）。
  optional bool expose_hidden = 5 [default = false];
}

// ReductionLayer参数
message ReductionParameter {
  enum ReductionOp {
    SUM = 1;
    ASUM = 2;
    SUMSQ = 3;
    MEAN = 4;
  }

  optional ReductionOp operation = 1 [default = SUM]; // reduction operation

  // The first axis to reduce to a scalar -- may be negative to index from the
  // end (e.g., -1 for the last axis).
  // (Currently, only reduction along ALL "tail" axes is supported; reduction
  // of axis M through N, where N < num_axes - 1, is unsupported.)
  // Suppose we have an n-axis bottom Blob with shape:
  //     (d0, d1, d2, ..., d(m-1), dm, d(m+1), ..., d(n-1)).
  // If axis == m, the output Blob will have shape
  //     (d0, d1, d2, ..., d(m-1)),
  // and the ReductionOp operation is performed (d0 * d1 * d2 * ... * d(m-1))
  // times, each including (dm * d(m+1) * ... * d(n-1)) individual data.
  // If axis == 0 (the default), the output Blob always has the empty shape
  // (count 1), performing reduction across the entire input --
  // often useful for creating new loss functions.
  optional int32 axis = 2 [default = 0];

  optional float coeff = 3 [default = 1.0]; // coefficient for output
}

// ReLULayer参数
message ReLUParameter {
  // 允许非0斜率可以加速优化:
  // Maas, A. L., Hannun, A. Y., & Ng, A. Y. (2013). Rectifier nonlinearities
  // improve neural network acoustic models. In ICML Workshop on Deep Learning
  // for Audio, Speech, and Language Processing.
  optional float negative_slope = 1 [default = 0];
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 2 [default = DEFAULT];
}

message ReshapeParameter {
  // Specify the output dimensions. If some of the dimensions are set to 0,
  // the corresponding dimension from the bottom layer is used (unchanged).
  // Exactly one dimension may be set to -1, in which case its value is
  // inferred from the count of the bottom blob and the remaining dimensions.
  // For example, suppose we want to reshape a 2D blob "input" with shape 2 x 8:
  //
  //   layer {
  //     type: "Reshape" bottom: "input" top: "output"
  //     reshape_param { ... }
  //   }
  //
  // If "input" is 2D with shape 2 x 8, then the following reshape_param
  // specifications are all equivalent, producing a 3D blob "output" with shape
  // 2 x 2 x 4:
  //
  //   reshape_param { shape { dim:  2  dim: 2  dim:  4 } }
  //   reshape_param { shape { dim:  0  dim: 2  dim:  4 } }
  //   reshape_param { shape { dim:  0  dim: 2  dim: -1 } }
  //   reshape_param { shape { dim:  0  dim:-1  dim:  4 } }
  //
  optional BlobShape shape = 1;

  // axis and num_axes control the portion of the bottom blob's shape that are
  // replaced by (included in) the reshape. By default (axis == 0 and
  // num_axes == -1), the entire bottom blob shape is included in the reshape,
  // and hence the shape field must specify the entire output shape.
  //
  // axis may be non-zero to retain some portion of the beginning of the input
  // shape (and may be negative to index from the end; e.g., -1 to begin the
  // reshape after the last axis, including nothing in the reshape,
  // -2 to include only the last axis, etc.).
  //
  // For example, suppose "input" is a 2D blob with shape 2 x 8.
  // Then the following ReshapeLayer specifications are all equivalent,
  // producing a blob "output" with shape 2 x 2 x 4:
  //
  //   reshape_param { shape { dim: 2  dim: 2  dim: 4 } }
  //   reshape_param { shape { dim: 2  dim: 4 } axis:  1 }
  //   reshape_param { shape { dim: 2  dim: 4 } axis: -3 }
  //
  // num_axes specifies the extent of the reshape.
  // If num_axes >= 0 (and axis >= 0), the reshape will be performed only on
  // input axes in the range [axis, axis+num_axes].
  // num_axes may also be -1, the default, to include all remaining axes
  // (starting from axis).
  //
  // For example, suppose "input" is a 2D blob with shape 2 x 8.
  // Then the following ReshapeLayer specifications are equivalent,
  // producing a blob "output" with shape 1 x 2 x 8.
  //
  //   reshape_param { shape { dim:  1  dim: 2  dim:  8 } }
  //   reshape_param { shape { dim:  1  dim: 2  }  num_axes: 1 }
  //   reshape_param { shape { dim:  1  }  num_axes: 0 }
  //
  // On the other hand, these would produce output blob shape 2 x 1 x 8:
  //
  //   reshape_param { shape { dim: 2  dim: 1  dim: 8  }  }
  //   reshape_param { shape { dim: 1 }  axis: 1  num_axes: 0 }
  //
  optional int32 axis = 2 [default = 0];
  optional int32 num_axes = 3 [default = -1];
}

// ROIPoolingLayer参数
message ROIPoolingParameter {
  // Pad, kernel size, and stride are all given as a single value for equal
  // dimensions in height and width or as Y, X pairs.
  optional uint32 pooled_h = 1 [default = 0]; // The pooled output height
  optional uint32 pooled_w = 2 [default = 0]; // The pooled output width
  // Multiplicative spatial scale factor to translate ROI coords from their
  // input scale to the scale used when pooling
  optional float spatial_scale = 3 [default = 1];
}
//ScaleParameter参数
message ScaleParameter {
  // The first axis of bottom[0] (the first input Blob) along which to apply
  // bottom[1] (the second input Blob).  May be negative to index from the end
  // (e.g., -1 for the last axis).
  // ？？？？？？？？？？？？？？？？？？？？？？？？？？？？？？？
  // 第一个输入Blob的首axis，被应用到第二个输入Blob。但第2个Blob的形状可能不同
  // For example, if bottom[0] is 4D with shape 100x3x40x60, the output
  // top[0] will have the same shape, and bottom[1] may have any of the
  // following shapes (for the given value of axis):
  //    (axis == 0 == -4) 100; 100x3; 100x3x40; 100x3x40x60
  //    (axis == 1 == -3)          3;     3x40;     3x40x60
  //    (axis == 2 == -2)                   40;       40x60
  //    (axis == 3 == -1)                                60
  // Furthermore,bottom[1]may have the empty shape (regardless of the value of
  // "axis") -- a scalar multiplier.
  optional int32 axis = 1 [default = 1];

  // (num_axes is ignored unless just one bottom is given and the scale is
  // a learned parameter of the layer.  Otherwise, num_axes is determined by the
  // number of axes by the second bottom.)
  // The number of axes of the input (bottom[0]) covered by the scale
  // parameter, or -1 to cover all axes of bottom[0] starting from `axis`.
  // Set num_axes := 0, to multiply with a zero-axis Blob: a scalar.
  optional int32 num_axes = 2 [default = 1];

  // (filler is ignored unless just one bottom is given and the scale is
  // a learned parameter of the layer.)
  // The initialization for the learned scale parameter.
  // Default is the unit (1) initialization, resulting in the ScaleLayer
  // initially performing the identity operation.
  optional FillerParameter filler = 3;

  // Whether to also learn a bias (equivalent to a ScaleLayer+BiasLayer, but
  // may be more efficient).  Initialized with bias_filler (defaults to 0).
  optional bool bias_term = 4 [default = false];
  optional FillerParameter bias_filler = 5;
}
//SigmoidParameter参数
message SigmoidParameter {
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 1 [default = DEFAULT];
}
//SliceParameter参数
message SliceParameter {
  // The axis along which to slice -- may be negative to index from the end
  // (e.g., -1 for the last axis).
  // By default, SliceLayer concatenates blobs along the "channels" axis (1).
  optional int32 axis = 3 [default = 1];
  repeated uint32 slice_point = 2;

  // DEPRECATED: alias for "axis" -- does not support negative indexing.
  optional uint32 slice_dim = 1 [default = 1];
}
//SmoothL1LossParameter参数
message SmoothL1LossParameter {
  // SmoothL1Loss(x) =
  //   0.5 * (sigma * x) ** 2    -- if x < 1.0 / sigma / sigma
  //   |x| - 0.5 / sigma / sigma -- otherwise
  optional float sigma = 1 [default = 1];
}

//SoftmaxLayer, SoftmaxWithLossLayer的参数
message SoftmaxParameter {
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 1 [default = DEFAULT];

  // The axis along which to perform the softmax -- may be negative to index
  // from the end (e.g., -1 for the last axis).
  // Any other axes will be evaluated as independent softmaxes.
  // 沿着哪一个轴运用softmax，该轴上必须是相互独立的分量。
  // eg.预测时对类标签运用，计算损失时对每个类的对数损失运用。
  optional int32 axis = 2 [default = 1];
}
//TanHParameter参数
message TanHParameter {
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 1 [default = DEFAULT];
}

// TileLayer参数
message TileParameter {
  // The index of the axis to tile.
  optional int32 axis = 1 [default = 1];

  // The number of copies (tiles) of the blob to output.
  optional int32 tiles = 2;
}

// ThresholdLayer参数
message ThresholdParameter {
  optional float threshold = 1 [default = 0]; // Strictly positive values
}

// MILLayer参数
message MILParameter {
  enum MILType {
    MAX = 0;
    NOR = 1;
  }
  optional MILType type = 1 [default = MAX]; // The MIL method
}

//窗口数据参数：专用于目标检测或分割
message WindowDataParameter {
  // Specify the data source.指定数据源
  optional string source = 1;
  // 数据预处理：尺度缩放，去均值等。去均值应在缩放前执行。
  optional float scale = 2 [default = 1];
  optional string mean_file = 3;
  // 指定批处理的数据量
  optional uint32 batch_size = 4;
  // 是否随机裁剪
  optional uint32 crop_size = 5 [default = 0];
  // 是否镜像变换
  optional bool mirror = 6 [default = false];
  // Foreground (object) overlap threshold 前景目标重合阈值
  optional float fg_threshold = 7 [default = 0.5];
  // Background (non-object) overlap threshold背景重合阈值
  optional float bg_threshold = 8 [default = 0.5];
  // Fraction of batch that should be foreground objects
  // 前景目标在batch中的比例
  optional float fg_fraction = 9 [default = 0.25];
  // Amount of contextual padding to add around a window
  // (used only by the window_data_layer)
  // 窗口周边需要添加的上下文padding
  optional uint32 context_pad = 10 [default = 0];
  // Mode for cropping out a detection window
  // warp: cropped window is warped to a fixed size and aspect ratio
  // square: the tightest square around the window is cropped
  // mode:裁剪出一个检测窗口的模式
  // warp:裁剪窗口被扭曲为某个固定尺寸和形状
  // square:裁剪窗口周边最紧？的方框
  optional string crop_mode = 11 [default = "warp"];
  // cache_images: will load all images in memory for faster access
  //将全部图像(裁剪得到的小图像)放入内存以便快速存取
  optional bool cache_images = 12 [default = false];
  // append root_folder to locate images
  // 添加根文件夹以定位文件
  optional string root_folder = 13 [default = ""];
}
//MILDataParameter参数
message MILDataParameter {
  // Specify the data source.
  optional string source = 1;

  // Number of scales for each image
  optional uint32 num_scales = 2 [default = 1];

  // Side length ratio between neighbouring scales
  optional float scale_factor = 6 [default = 1];

  // Number of channels in the image
  optional uint32 channels = 4 [default = 3];

  // Specify the number of images per batch
  optional uint32 images_per_batch = 3;
  // Specify the number of classes
  optional uint32 n_classes = 5;
  // specify the box_dir and label_dir
  optional string label_file = 7;

  // Root directory which contains all the images
  optional string root_dir = 11;
  // Extention for the file
  optional string ext = 12;

  // To randomize or not
  optional bool randomize = 13 [default = true];
}

//SPP参数,源于论文SPPNet
message SPPParameter {
  enum PoolMethod {
    MAX = 0;
    AVE = 1;
    STOCHASTIC = 2;
  } //池化方法，获得金字塔的方法，最大/平均/随机
  optional uint32 pyramid_height = 1; //金字塔高度
  optional PoolMethod pool = 2 [default = MAX]; // The pooling method
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 6 [default = DEFAULT];
}

// DEPRECATED: use LayerParameter.
// 旧版：使用层参数。 V1可能是第一版version1的意思
message V1LayerParameter {
  repeated string bottom = 2;  //输入
  repeated string top = 3;     //输出
  optional string name = 4;    //层名称
  repeated NetStateRule include = 32; //运行时状态：包含
  repeated NetStateRule exclude = 33; //运行时状态：不包含
  enum LayerType {             //层类型
    NONE = 0;
    ABSVAL = 35;
    ACCURACY = 1;
    ARGMAX = 30;
    BNLL = 2;
    CONCAT = 3;
    CONTRASTIVE_LOSS = 37;
    CONVOLUTION = 4;
    DATA = 5;
    DECONVOLUTION = 39;
    DROPOUT = 6;
    DUMMY_DATA = 32;
    EUCLIDEAN_LOSS = 7;
    ELTWISE = 25;
    EXP = 38;
    FLATTEN = 8;
    HDF5_DATA = 9;
    HDF5_OUTPUT = 10;
    HINGE_LOSS = 28;
    IM2COL = 11;
    IMAGE_DATA = 12;
    INFOGAIN_LOSS = 13;
    INNER_PRODUCT = 14;
    LRN = 15;
    MEMORY_DATA = 29;
    MULTINOMIAL_LOGISTIC_LOSS = 16;
    MVN = 34;
    POOLING = 17;
    POWER = 26;
    RELU = 18;
    SIGMOID = 19;
    SIGMOID_CROSS_ENTROPY_LOSS = 27;
    SILENCE = 36;
    SOFTMAX = 20;
    SOFTMAX_LOSS = 21;
    SPLIT = 22;
    SLICE = 33;
    TANH = 23;
    WINDOW_DATA = 24;
    THRESHOLD = 31;
  }
  optional LayerType type = 5;
  repeated BlobProto blobs = 6;
  repeated string param = 1001;
  repeated DimCheckMode blob_share_mode = 1002;
  enum DimCheckMode {
    STRICT = 0;
    PERMISSIVE = 1;
  }
  repeated float blobs_lr = 7;
  repeated float weight_decay = 8;
  repeated float loss_weight = 35;
  optional AccuracyParameter accuracy_param = 27;
  optional ArgMaxParameter argmax_param = 23;
  optional ConcatParameter concat_param = 9;
  optional ContrastiveLossParameter contrastive_loss_param = 40;
  optional ConvolutionParameter convolution_param = 10;
  optional DataParameter data_param = 11;
  optional DropoutParameter dropout_param = 12;
  optional DummyDataParameter dummy_data_param = 26;
  optional EltwiseParameter eltwise_param = 24;
  optional ExpParameter exp_param = 41;
  optional HDF5DataParameter hdf5_data_param = 13;
  optional HDF5OutputParameter hdf5_output_param = 14;
  optional HingeLossParameter hinge_loss_param = 29;
  optional ImageDataParameter image_data_param = 15;
  optional InfogainLossParameter infogain_loss_param = 16;
  optional InnerProductParameter inner_product_param = 17;
  optional LRNParameter lrn_param = 18;
  optional MemoryDataParameter memory_data_param = 22;
  optional MVNParameter mvn_param = 34;
  optional PoolingParameter pooling_param = 19;
  optional PowerParameter power_param = 21;
  optional ReLUParameter relu_param = 30;
  optional SigmoidParameter sigmoid_param = 38;
  optional SoftmaxParameter softmax_param = 39;
  optional SliceParameter slice_param = 31;
  optional TanHParameter tanh_param = 37;
  optional ThresholdParameter threshold_param = 25;
  optional WindowDataParameter window_data_param = 20;
  optional TransformationParameter transform_param = 36;
  optional LossParameter loss_param = 42;
  optional V0LayerParameter layer = 1;
}

// DEPRECATED: V0LayerParameter is the old way of specifying layer parameters
// in Caffe.  We keep this message type around for legacy support.
// 旧版本：V0LayerParameter version-0版
message V0LayerParameter {
  optional string name = 1; // the layer name
  optional string type = 2; // the string to specify the layer type

  // Parameters to specify layers with inner products.
  optional uint32 num_output = 3; // The number of outputs for the layer
  optional bool biasterm = 4 [default = true]; // whether to have bias terms
  optional FillerParameter weight_filler = 5; // The filler for the weight
  optional FillerParameter bias_filler = 6; // The filler for the bias

  optional uint32 pad = 7 [default = 0]; // The padding size
  optional uint32 kernelsize = 8; // The kernel size
  optional uint32 group = 9 [default = 1]; // The group size for group conv
  optional uint32 stride = 10 [default = 1]; // The stride
  enum PoolMethod {
    MAX = 0;
    AVE = 1;
    STOCHASTIC = 2;
  }
  optional PoolMethod pool = 11 [default = MAX]; // The pooling method
  optional float dropout_ratio = 12 [default = 0.5]; // dropout ratio

  optional uint32 local_size = 13 [default = 5]; // for local response norm
  optional float alpha = 14 [default = 1.]; // for local response norm
  optional float beta = 15 [default = 0.75]; // for local response norm
  optional float k = 22 [default = 1.];

  // For data layers, specify the data source
  optional string source = 16;
  // For data pre-processing, we can do simple scaling and subtracting the
  // data mean, if provided. Note that the mean subtraction is always carried
  // out before scaling.
  optional float scale = 17 [default = 1];
  optional string meanfile = 18;
  // For data layers, specify the batch size.
  optional uint32 batchsize = 19;
  // For data layers, specify if we would like to randomly crop an image.
  optional uint32 cropsize = 20 [default = 0];
  // For data layers, specify if we want to randomly mirror data.
  optional bool mirror = 21 [default = false];

  // The blobs containing the numeric parameters of the layer
  repeated BlobProto blobs = 50;
  // The ratio that is multiplied on the global learning rate. If you want to
  // set the learning ratio for one blob, you need to set it for all blobs.
  repeated float blobs_lr = 51;
  // The weight decay that is multiplied on the global weight decay.
  repeated float weight_decay = 52;

  // The rand_skip variable is for the data layer to skip a few data points
  // to avoid all asynchronous sgd clients to start at the same point. The skip
  // point would be set as rand_skip * rand(0,1). Note that rand_skip should not
  // be larger than the number of keys in the database.
  optional uint32 rand_skip = 53 [default = 0];

  // Fields related to detection (det_*)
  // foreground (object) overlap threshold
  optional float det_fg_threshold = 54 [default = 0.5];
  // background (non-object) overlap threshold
  optional float det_bg_threshold = 55 [default = 0.5];
  // Fraction of batch that should be foreground objects
  optional float det_fg_fraction = 56 [default = 0.25];

  // optional bool OBSOLETE_can_clobber = 57 [default = true];

  // Amount of contextual padding to add around a window
  // (used only by the window_data_layer)
  optional uint32 det_context_pad = 58 [default = 0];

  // Mode for cropping out a detection window
  // warp: cropped window is warped to a fixed size and aspect ratio
  // square: the tightest square around the window is cropped
  optional string det_crop_mode = 59 [default = "warp"];

  // For ReshapeLayer, one needs to specify the new dimensions.
  optional int32 new_num = 60 [default = 0];
  optional int32 new_channels = 61 [default = 0];
  optional int32 new_height = 62 [default = 0];
  optional int32 new_width = 63 [default = 0];

  // Whether or not ImageLayer should shuffle the list of files at every epoch.
  // It will also resize images if new_height or new_width are not zero.
  optional bool shuffle_images = 64 [default = false];

  // For ConcatLayer, one needs to specify the dimension for concatenation, and
  // the other dimensions must be the same for all the bottom blobs.
  // By default it will concatenate blobs along the channels dimension.
  optional uint32 concat_dim = 65 [default = 1];

  optional HDF5OutputParameter hdf5_output_param = 1001;
}
//PReLUParameter,源于论文
message PReLUParameter {
  // Parametric ReLU described in K. He et al, Delving Deep into Rectifiers:
  // Surpassing Human-Level Performance on ImageNet Classification, 2015.

  // Initial value of a_i. Default is a_i=0.25 for all i.
  optional FillerParameter filler = 1;
  // Whether or not slope paramters are shared across channels.
  optional bool channel_shared = 2 [default = false];
}