【caffe Net】使用举例和代码中文注释

 首先是Net使用的小例子：

#include <vector>
#include <iostream>
#include <caffe/net.hpp>
using namespace std;
using namespace caffe;
int main()
{
    std::string proto("./bambootry/deploy.prototxt");
    Net<float> nn(proto,caffe::TEST);
    vector<string> bn=nn.blob_names();//获取Net中所有Blob对象名
    for(int i=0;i<bn.size();i++)
    {
        cout<<"Blob #"<<i<<" : "<<bn[i]<<endl;
    }
    return 0;
}

linux下编译（bambootry为自己创建的文件夹）

g++ -o ./bambootry/netapp ./bambootry/net.cpp -I ./include -D CPU_ONLY 
-I ./.build_release/src/ -L ./build/lib -lcaffe -lglog -lboost_system 
-lprotobuf

结果：

……中间省略

继续省略……

代码注释

 src/caffe/proto/caffe.proto中NetParameter

message NetParameter {
  optional string name = 1; // consider giving the network a name 网络名称
  // DEPRECATED. See InputParameter. The input blobs to the network.
  repeated string input = 3;//网络的输入blob名称，可以有多个blob
  // DEPRECATED. See InputParameter. The shape of the input blobs.
  repeated BlobShape input_shape = 8;//输入Blob维度信息

  // 4D input dimensions -- deprecated.  Use "input_shape" instead.
  // If specified, for each input blob there should be four
  // values specifying the num, channels, height and width of the input blob.
  // Thus, there should be a total of (4 * #input) numbers.
  repeated int32 input_dim = 4;//旧版维度信息

  // Whether the network will force every layer to carry out backward operation.
  // If set False, then whether to carry out backward is determined
  // automatically according to the net structure and learning rates.
  // 网络是否强制每个层进行反向传播运算，如果设置为false，则由网络结构和学习速率自动确定是否进行反向传播运算
  optional bool force_backward = 5 [default = false];
  // The current "state" of the network, including the phase, level, and stage.
  // Some layers may be included/excluded depending on this state and the states
  // specified in the layers' include and exclude fields.
  optional NetState state = 6;//网络当前状态，phase, level, 和 stage，根据状态可以确定是否包含某些层

  // Print debugging information about results while running Net::Forward,
  // Net::Backward, and Net::Update. 
  // 运行Net::Forward,Net::Backward, and Net::Update是否打印结果的调试信息
  optional bool debug_info = 7 [default = false];

  // The layers that make up the net.  Each of their configurations, including
  // connectivity and behavior, is specified as a LayerParameter.
  //组成net的所有层。每个层的配置都包括连接属性和行为，由LayerParameter定义。
  //ID设为100可以保证层描述置于末尾
  repeated LayerParameter layer = 100;  // ID 100 so layers are printed last.

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

 include/caffe/net.hpp

#ifndef CAFFE_NET_HPP_
#define CAFFE_NET_HPP_

#include <map>
#include <set>
#include <string>
#include <utility>
#include <vector>

#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"

namespace caffe {

/**
 * @brief Connects Layer%s together into a directed acyclic graph (DAG)
 *        specified by a NetParameter.
 *
 * TODO(dox): more thorough description.
 */
template <typename Dtype>
class Net {
 public:
  explicit Net(const NetParameter& param);
  explicit Net(const string& param_file, Phase phase,
      const int level = 0, const vector<string>* stages = NULL);
  virtual ~Net() {}

  /// @brief Initialize a network with a NetParameter.
  void Init(const NetParameter& param);//用NetParameter对象初始化Net

  /**
   * @brief Run Forward and return the result.
   *
   */
  //前向传播
  const vector<Blob<Dtype>*>& Forward(Dtype* loss = NULL);
  /// @brief DEPRECATED; use Forward() instead.已舍弃
  const vector<Blob<Dtype>*>& ForwardPrefilled(Dtype* loss = NULL) {
    LOG_EVERY_N(WARNING, 1000) << "DEPRECATED: ForwardPrefilled() "
        << "will be removed in a future version. Use Forward().";
    return Forward(loss);
  }

  /**
   * The From and To variants of Forward and Backward operate on the
   * (topological) ordering by which the net is specified. For general DAG
   * networks, note that (1) computing from one layer to another might entail
   * extra computation on unrelated branches, and (2) computation starting in
   * the middle may be incorrect if all of the layers of a fan-in are not
   * included.
   */
  //前向传播的几种形式
  Dtype ForwardFromTo(int start, int end);
  Dtype ForwardFrom(int start);
  Dtype ForwardTo(int end);
  /// @brief DEPRECATED; set input blobs then use Forward() instead.
  //弃用。指定输入Blob返回输出Blob。确定输入Blob后使用Forward（）替代。
  const vector<Blob<Dtype>*>& Forward(const vector<Blob<Dtype>* > & bottom,
      Dtype* loss = NULL);

  /**
   * @brief Zeroes out the diffs of all net parameters.
   *        Should be run before Backward.
   */
  //将diff的所有权值参数清零。应在反向传播之前调用。
  void ClearParamDiffs();

  /**
   * The network backward should take no input and output, since it solely
   * computes the gradient w.r.t the parameters, and the data has already been
   * provided during the forward pass.
   */
  //反向传播的几个函数。不需要输入或输出的Blob，数据已经在前向传播时提供。
  void Backward();
  void BackwardFromTo(int start, int end);
  void BackwardFrom(int start);
  void BackwardTo(int end);

  /**
   * @brief Reshape all layers from bottom to top.
   *
   * This is useful to propagate changes to layer sizes without running
   * a forward pass, e.g. to compute output feature size.
   */
  //对Net中所有层自底向上的变形函数。无需进行一次前向传播就可以计算各层所需的Blob尺寸。
  void Reshape();
  //前向传播+反向传播。输入为bottom blob，输出为loss。
  Dtype ForwardBackward() {
    Dtype loss;
    Forward(&loss);
    Backward();
    return loss;
  }

  /// @brief Updates the network weights based on the diff values computed.
  void Update();//根据（Solver）准备好的diff更新网络权值
  /**
   * @brief Shares weight data of owner blobs with shared blobs.
   *
   * Note: this is called by Net::Init, and thus should normally not be
   * called manually.
   */
  void ShareWeights();//由初始化函数调用，不能随意调用

  /**
   * @brief For an already initialized net, implicitly copies (i.e., using no
   *        additional memory) the pre-trained layers from another Net.
   */
  void ShareTrainedLayersWith(const Net* other);
  // For an already initialized net, CopyTrainedLayersFrom() copies the already
  // trained layers from another net parameter instance.
  /**
   * @brief For an already initialized net, copies the pre-trained layers from
   *        another Net.
   */
  void CopyTrainedLayersFrom(const NetParameter& param);
  void CopyTrainedLayersFrom(const string trained_filename);
  void CopyTrainedLayersFromBinaryProto(const string trained_filename);
  void CopyTrainedLayersFromHDF5(const string trained_filename);
  /// @brief Writes the net to a proto.
  void ToProto(NetParameter* param, bool write_diff = false) const;
  /// @brief Writes the net to an HDF5 file.
  void ToHDF5(const string& filename, bool write_diff = false) const;

  /// @brief returns the network name.返回网络名称
  inline const string& name() const { return name_; }
  /// @brief returns the layer names 返回层名
  inline const vector<string>& layer_names() const { return layer_names_; }
  /// @brief returns the blob names 
  inline const vector<string>& blob_names() const { return blob_names_; }
  /// @brief returns the blobs
  inline const vector<shared_ptr<Blob<Dtype> > >& blobs() const {
    return blobs_;
  }
  /// @brief returns the layers
  inline const vector<shared_ptr<Layer<Dtype> > >& layers() const {
    return layers_;
  }
  /// @brief returns the phase: TRAIN or TEST
  inline Phase phase() const { return phase_; }
  /**
   * @brief returns the bottom vecs for each layer -- usually you won't
   *        need this unless you do per-layer checks such as gradients.
   */
  inline const vector<vector<Blob<Dtype>*> >& bottom_vecs() const {
    return bottom_vecs_;//grad check 需要调用返回每一层的输入。平时不需要。
  }
  /**
   * @brief returns the top vecs for each layer -- usually you won't
   *        need this unless you do per-layer checks such as gradients.
   */
  inline const vector<vector<Blob<Dtype>*> >& top_vecs() const {
    return top_vecs_;//grad check 需要调用返回每一层的输出。平时不需要。
  }
  /// @brief returns the ids of the top blobs of layer i
  inline const vector<int> & top_ids(int i) const {
    CHECK_GE(i, 0) << "Invalid layer id";
    CHECK_LT(i, top_id_vecs_.size()) << "Invalid layer id";
    return top_id_vecs_[i];
  }
  /// @brief returns the ids of the bottom blobs of layer i
  inline const vector<int> & bottom_ids(int i) const {
    CHECK_GE(i, 0) << "Invalid layer id";
    CHECK_LT(i, bottom_id_vecs_.size()) << "Invalid layer id";
    return bottom_id_vecs_[i];
  }
  inline const vector<vector<bool> >& bottom_need_backward() const {
    return bottom_need_backward_;
  }
  inline const vector<Dtype>& blob_loss_weights() const {
    return blob_loss_weights_;
  }
  inline const vector<bool>& layer_need_backward() const {
    return layer_need_backward_;
  }
  /// @brief returns the parameters
  inline const vector<shared_ptr<Blob<Dtype> > >& params() const {
    return params_;
  }
  inline const vector<Blob<Dtype>*>& learnable_params() const {
    return learnable_params_;
  }
  /// @brief returns the learnable parameter learning rate multipliers
  inline const vector<float>& params_lr() const { return params_lr_; }
  inline const vector<bool>& has_params_lr() const { return has_params_lr_; }
  /// @brief returns the learnable parameter decay multipliers
  inline const vector<float>& params_weight_decay() const {
    return params_weight_decay_;
  }
  inline const vector<bool>& has_params_decay() const {
    return has_params_decay_;
  }
  const map<string, int>& param_names_index() const {
    return param_names_index_;
  }
  inline const vector<int>& param_owners() const { return param_owners_; }
  inline const vector<string>& param_display_names() const {
    return param_display_names_;
  }
  /// @brief Input and output blob numbers 输入输出的blob数量
  inline int num_inputs() const { return net_input_blobs_.size(); }
  inline int num_outputs() const { return net_output_blobs_.size(); }
  inline const vector<Blob<Dtype>*>& input_blobs() const {
    return net_input_blobs_;//返回输入blob
  }
  inline const vector<Blob<Dtype>*>& output_blobs() const {
    return net_output_blobs_;//返回输出blob
  }
  inline const vector<int>& input_blob_indices() const {
    return net_input_blob_indices_;//返回输入blob下标
  }
  inline const vector<int>& output_blob_indices() const {
    return net_output_blob_indices_;//返回输出blob下标
  }
  bool has_blob(const string& blob_name) const;//查找网络是否包含该blob
  const shared_ptr<Blob<Dtype> > blob_by_name(const string& blob_name) const;//如果有则找出
  bool has_layer(const string& layer_name) const;//查找网络是否包含该层
  const shared_ptr<Layer<Dtype> > layer_by_name(const string& layer_name) const;//如果有则找出

  void set_debug_info(const bool value) { debug_info_ = value; }

  // Helpers for Init.以下用于初始化
  /**
   * @brief Remove layers that the user specified should be excluded given the current
   *        phase, level, and stage.
   */
  //过滤掉用户指定的在某阶段、级别、状态下不应包含的层
  static void FilterNet(const NetParameter& param,
      NetParameter* param_filtered);
  /// @brief return whether NetState state meets NetStateRule rule
  //判断网络状态是否满足网络规则
  static bool StateMeetsRule(const NetState& state, const NetStateRule& rule,
      const string& layer_name);

  // Invoked at specific points during an iteration
  class Callback {
   protected:
    virtual void run(int layer) = 0;

    template <typename T>
    friend class Net;
  };
  const vector<Callback*>& before_forward() const { return before_forward_; }
  void add_before_forward(Callback* value) {
    before_forward_.push_back(value);
  }
  const vector<Callback*>& after_forward() const { return after_forward_; }
  void add_after_forward(Callback* value) {
    after_forward_.push_back(value);
  }
  const vector<Callback*>& before_backward() const { return before_backward_; }
  void add_before_backward(Callback* value) {
    before_backward_.push_back(value);
  }
  const vector<Callback*>& after_backward() const { return after_backward_; }
  void add_after_backward(Callback* value) {
    after_backward_.push_back(value);
  }

 protected:
  // Helpers for Init.
  /// @brief Append a new top blob to the net.给网络追加新的输出blob
  void AppendTop(const NetParameter& param, const int layer_id,
                 const int top_id, set<string>* available_blobs,
                 map<string, int>* blob_name_to_idx);
  /// @brief Append a new bottom blob to the net.给网络追加新的输入blob
  int AppendBottom(const NetParameter& param, const int layer_id,
                   const int bottom_id, set<string>* available_blobs,
                   map<string, int>* blob_name_to_idx);
  /// @brief Append a new parameter blob to the net.给网络追加新的权值blob
  void AppendParam(const NetParameter& param, const int layer_id,
                   const int param_id);
  //以下几个函数显示调试信息
  /// @brief Helper for displaying debug info in Forward.
  void ForwardDebugInfo(const int layer_id);
  /// @brief Helper for displaying debug info in Backward.
  void BackwardDebugInfo(const int layer_id);
  /// @brief Helper for displaying debug info in Update.
  void UpdateDebugInfo(const int param_id);

  /// @brief The network name网络名
  string name_;
  /// @brief The phase: TRAIN or TEST 网络当前阶段（训练 测试）
  Phase phase_;
  /// @brief Individual layers in the net 网络中的独立层
  vector<shared_ptr<Layer<Dtype> > > layers_;
  vector<string> layer_names_;//层名称
  map<string, int> layer_names_index_;//层名称与索引映射表
  vector<bool> layer_need_backward_;//标记某个层是否需要反向传播
  /// @brief the blobs storing intermediate results between the layer.
  vector<shared_ptr<Blob<Dtype> > > blobs_;//层与层之间传递数据通道
  vector<string> blob_names_;//Blob名称
  map<string, int> blob_names_index_;//Blob名称和索引映射表
  vector<bool> blob_need_backward_;//标记Blob是否需要反向传播
  /// bottom_vecs stores the vectors containing the input for each layer.
  /// They don't actually host the blobs (blobs_ does), so we simply store
  /// pointers.
  //存放每个层的输入Blob指针（真正数据所有者为blobs_）
  vector<vector<Blob<Dtype>*> > bottom_vecs_;
  vector<vector<int> > bottom_id_vecs_;
  vector<vector<bool> > bottom_need_backward_;
  /// top_vecs stores the vectors containing the output for each layer
  //存放每个层的输出Blob指针（真正数据所有者为blobs_）
  vector<vector<Blob<Dtype>*> > top_vecs_;
  vector<vector<int> > top_id_vecs_;
  /// Vector of weight in the loss (or objective) function of each net blob,
  /// indexed by blob_id.
  //每个blob对全局损失（目标函数）的贡献权重
  vector<Dtype> blob_loss_weights_;
  vector<vector<int> > param_id_vecs_;
  vector<int> param_owners_;
  vector<string> param_display_names_;
  vector<pair<int, int> > param_layer_indices_;
  map<string, int> param_names_index_;
  /// blob indices for the input and the output of the net
  //网络输入输出blob的索引
  vector<int> net_input_blob_indices_;
  vector<int> net_output_blob_indices_;
  vector<Blob<Dtype>*> net_input_blobs_;
  vector<Blob<Dtype>*> net_output_blobs_;
  /// The parameters in the network. 网络权值
  vector<shared_ptr<Blob<Dtype> > > params_;
  vector<Blob<Dtype>*> learnable_params_;//可训练的网络权值
  /**
   * The mapping from params_ -> learnable_params_: we have
   * learnable_param_ids_.size() == params_.size(),
   * and learnable_params_[learnable_param_ids_[i]] == params_[i].get()
   * if and only if params_[i] is an "owner"; otherwise, params_[i] is a sharer
   * and learnable_params_[learnable_param_ids_[i]] gives its owner.
   */
   //params_ 到 learnable_params_映射: 
   //当且仅当params_[i]是所有者时，learnable_param_ids_.size() == params_.size(),
   //learnable_params_[learnable_param_ids_[i]] == params_[i].get()
   //否则 params_[i] 只是共享者，learnable_params_[learnable_param_ids_[i]] 给出所有者
  vector<int> learnable_param_ids_;
  /// the learning rate multipliers for learnable_params_
  vector<float> params_lr_;//学习率倍乘因子
  vector<bool> has_params_lr_;
  /// the weight decay multipliers for learnable_params_
  vector<float> params_weight_decay_;//权值衰减因子
  vector<bool> has_params_decay_;
  /// The bytes of memory used by this net
  size_t memory_used_;//记录网络占用的内存大小
  /// Whether to compute and display debug info for the net.
  bool debug_info_;//是否显示调试信息
  // Callbacks
  vector<Callback*> before_forward_;
  vector<Callback*> after_forward_;
  vector<Callback*> before_backward_;
  vector<Callback*> after_backward_;

DISABLE_COPY_AND_ASSIGN(Net);//禁止拷贝构造函数、赋值运算函数
};


}  // namespace caffe

#endif  // CAFFE_NET_HPP_

未完待续……

内容来自赵永科《深度学习 21天实战caffe》