caffe源码阅读之layer(1)

Layer为caffe的计算单元，部分Layer带有权值和偏置项，有两个运算方向：前向传播和反向传播；在E:\Caffe\caffe-windows\src\caffe\proto中caffe.proto
message LayerParameter {} 记录了每一个新增的LayerParameter参数，如果自定义了一个卷积等相关的层需要再这定义并修改ID(136之后)
    首先来看layer的定义，这个定义是layer的基类，无论定义什么样的layer需要继承该layer类,接下来具体看看layer是怎么写的。首先在E:\Caffe\caffe-windows\include\caffe下
可以找到layer.hpp和E:\Caffe\caffe-windows\src\caffe下找到layer.cpp文件可以见到layer类的定义和实现。

    接下来看看layer类的成员变量：

LayerParameter layer_param_;//保存layer参数的ProtoBuffer对象，该对象已经在caffe.proto定义
Phase phase_;//Layer当前的阶段，主要有TRAIN和TEST
vector<shared_ptr<Blob<Dtype> > > blobs_;//layer内部的权值或偏置项
vector<bool> param_propagate_down_;//标志是否计算对应的误差和梯度
bool is_shared_;//是否共享

shared_ptr<boost::mutex> forward_mutex_;//互斥锁，如果该层被共享，保证顺序执行前向传播

1、构造函数

 explicit Layer(const LayerParameter& param): layer_param_(param), is_shared_(false) {
      phase_ = param.phase();//设置当前阶段
      if (layer_param_.blobs_size() > 0) {
        blobs_.resize(layer_param_.blobs_size());//设置Blob个数，并将每一个Blob对象调整为layer_param_中的Blob尺寸
        for (int i = 0; i < layer_param_.blobs_size(); ++i) {
          blobs_[i].reset(new Blob<Dtype>());
          blobs_[i]->FromProto(layer_param_.blobs(i));
        }
      }
    }
 //析构函数
 virtual ~Layer() {}

2、配置函数
实现常用层的配置接口，该层不可被覆盖

void SetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
    InitMutex();
    CheckBlobCounts(bottom, top);//检测Blob
    LayerSetUp(bottom, top);//layer相关的配置
    Reshape(bottom, top);//top变形
    SetLossWeights(top);//设置损失因子
  }
  //初始化forward_mutex_
   void InitMutex();
   //校验输入、输出Blob数目是否满足layer要求
   virtual void CheckBlobCounts(const vector<Blob<Dtype>*>& bottom,
                               const vector<Blob<Dtype>*>& top) {
    if (ExactNumBottomBlobs() >= 0) {
      CHECK_EQ(ExactNumBottomBlobs(), bottom.size())
          << type() << " Layer takes " << ExactNumBottomBlobs()
          << " bottom blob(s) as input.";
    }
    if (MinBottomBlobs() >= 0) {
      CHECK_LE(MinBottomBlobs(), bottom.size())
          << type() << " Layer takes at least " << MinBottomBlobs()
          << " bottom blob(s) as input.";
    }
    if (MaxBottomBlobs() >= 0) {
      CHECK_GE(MaxBottomBlobs(), bottom.size())
          << type() << " Layer takes at most " << MaxBottomBlobs()
          << " bottom blob(s) as input.";
    }
    if (ExactNumTopBlobs() >= 0) {
      CHECK_EQ(ExactNumTopBlobs(), top.size())
          << type() << " Layer produces " << ExactNumTopBlobs()
          << " top blob(s) as output.";
    }
    if (MinTopBlobs() >= 0) {
      CHECK_LE(MinTopBlobs(), top.size())
          << type() << " Layer produces at least " << MinTopBlobs()
          << " top blob(s) as output.";
    }
    if (MaxTopBlobs() >= 0) {
      CHECK_GE(MaxTopBlobs(), top.size())
          << type() << " Layer produces at most " << MaxTopBlobs()
          << " top blob(s) as output.";
    }
    if (EqualNumBottomTopBlobs()) {
      CHECK_EQ(bottom.size(), top.size())
          << type() << " Layer produces one top blob as output for each "
          << "bottom blob input.";
    }
  }
  //做特定类型层的相关配置，需要重写
virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top) {}
virtual void Reshape(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top) = 0;
//初始化输出Blob相关的权重并放到diff
 inline void SetLossWeights(const vector<Blob<Dtype>*>& top) {
    const int num_loss_weights = layer_param_.loss_weight_size();//从ProtoBuffer对象中获得layer参数
    if (num_loss_weights) {
      CHECK_EQ(top.size(), num_loss_weights) << "loss_weight must be "
          "unspecified or specified once per top blob.";//loss_weight没有或者loss_weight个数与Top Blob数量相同
      for (int top_id = 0; top_id < top.size(); ++top_id) {
        const Dtype loss_weight = layer_param_.loss_weight(top_id);//从protoBuffer中获取参数（1或0）
        if (loss_weight == Dtype(0)) { continue; }//若果==0：表示当前层不参与loss计算，跳过
        this->set_loss(top_id, loss_weight);//若果不为0：表示当前层参与loss计算，对网络做相关计算
        const int count = top[top_id]->count();
        Dtype* loss_multiplier = top[top_id]->mutable_cpu_diff();
        caffe_set(count, loss_weight, loss_multiplier);//将loss_weight值写入到diff中，传递到其他需要使用的地方，实现远程同步
      }
    }
  }

3、前向传播和反向传播

//给定输入Blob输出输出Blob和loss
  inline Dtype Forward(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top);
  
  template <typename Dtype>
inline Dtype Layer<Dtype>::Forward(const vector<Blob<Dtype>*>& bottom,
    const vector<Blob<Dtype>*>& top) {
  // Lock during forward to ensure sequential forward（枷锁防止其他层使用）
  Lock();
  Dtype loss = 0;
  Reshape(bottom, top);
  switch (Caffe::mode()) {//判断计算机的训练模式
  case Caffe::CPU:
    Forward_cpu(bottom, top);//调用CPU版本的Forward
    for (int top_id = 0; top_id < top.size(); ++top_id) {
      if (!this->loss(top_id)) { continue; }
      const int count = top[top_id]->count();//若为lossLayer计算的全局损失函数放到data域中
      const Dtype* data = top[top_id]->cpu_data();
      const Dtype* loss_weights = top[top_id]->cpu_diff();
      loss += caffe_cpu_dot(count, data, loss_weights);//计算加权后的loss的到一个标量
    }
    break;
  case Caffe::GPU:
    Forward_gpu(bottom, top);
#ifndef CPU_ONLY
    for (int top_id = 0; top_id < top.size(); ++top_id) {
      if (!this->loss(top_id)) { continue; }
      const int count = top[top_id]->count();
      const Dtype* data = top[top_id]->gpu_data();
      const Dtype* loss_weights = top[top_id]->gpu_diff();
      Dtype blob_loss = 0;
      caffe_gpu_dot(count, data, loss_weights, &blob_loss);
      loss += blob_loss;
    }
#endif
    break;
  default:
    LOG(FATAL) << "Unknown caffe mode.";
  }
  Unlock();//解锁
  return loss;
}
  //反向传播，给定输出blob层的diff,该层的diff由该函数计算得到
  inline void Backward(const vector<Blob<Dtype>*>& top,const vector<bool>& propagate_down,const vector<Blob<Dtype>*>& bottom);
  
  template <typename Dtype>
inline void Layer<Dtype>::Backward(const vector<Blob<Dtype>*>& top,
    const vector<bool>& propagate_down,
    const vector<Blob<Dtype>*>& bottom) {
  switch (Caffe::mode()) {
  case Caffe::CPU:
    Backward_cpu(top, propagate_down, bottom);
    break;
  case Caffe::GPU:
    Backward_gpu(top, propagate_down, bottom);
    break;
  default:
    LOG(FATAL) << "Unknown caffe mode.";
  }
}
上面的函数不需要重写，接下来的四个函数需要在创建特有的layer时需要重写
 virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top) = 0;
  virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,const vector<Blob<Dtype>*>& top) {
    return Forward_cpu(bottom, top);
  }
  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,const vector<bool>& propagate_down,const vector<Blob<Dtype>*>& bottom) = 0;
  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,const vector<bool>& propagate_down,const vector<Blob<Dtype>*>& bottom) {
    Backward_cpu(top, propagate_down, bottom);
  }

4、其他
（1）判断和设置layer层是否被共享

virtual inline bool ShareInParallel() const { return false; }//在数据并行时是否会被其他Net共享，默认只能用于数据读取层（Datalayer）
inline bool IsShared() const { return is_shared_; }//该层是否会被其他层共享，ShareInParallel()返回true且被多个GPU使用，网络处于训练阶段时返回true
inline void SetShared(bool is_shared) {//设置该层是否被共享
    CHECK(ShareInParallel() || !is_shared)
        << type() << "Layer does not support sharing.";
    is_shared_ = is_shared;
  }

（2）Blob参数相关操作

 vector<shared_ptr<Blob<Dtype> > >& blobs() {//返回layer内部可训练的权重和偏置项Blob
    return blobs_;
  }
  const LayerParameter& layer_param() const { return layer_param_; }//返回ProtoBuffer中的layer初始化参数
  virtual void ToProto(LayerParameter* param, bool write_diff = false);//将layer初始化参数写入到ProtoBuffer中
   inline Dtype loss(const int top_index) const {//返回某个Blob标量loss值
    return (loss_.size() > top_index) ? loss_[top_index] : Dtype(0);
  }
  inline void set_loss(const int top_index, const Dtype value) {//设置某个Blob标量loss值
    if (loss_.size() <= top_index) {
      loss_.resize(top_index + 1, Dtype(0));
    }
    loss_[top_index] = value;
  }
  virtual inline const char* type() const { return ""; }//返回层类型字符串
  //返回该Layer需要输入的Blob数目
virtual inline int ExactNumBottomBlobs() const { return -1; }
virtual inline int MinBottomBlobs() const { return -1; }
virtual inline int MaxBottomBlobs() const { return -1; }
//返回该层需要输出的Blob数目
virtual inline int ExactNumTopBlobs() const { return -1; }
virtual inline int MinTopBlobs() const { return -1; }
virtual inline int MaxTopBlobs() const { return -1; }
//输入和输出Blob是否相等
virtual inline bool EqualNumBottomTopBlobs() const { return false; }
//返回匿名输出Blob，该Blob由layer自动创建
virtual inline bool AutoTopBlobs() const { return false; }
//Blob是否强制反向传播 
virtual inline bool AllowForceBackward(const int bottom_index) const {
    return true;
  }
//指定layer
inline bool param_propagate_down(const int param_id) {
    return (param_propagate_down_.size() > param_id) ?
        param_propagate_down_[param_id] : false;
  }
 //设置该layer是否计算相对权值或偏置项梯度
  inline void set_param_propagate_down(const int param_id, const bool value) {
    if (param_propagate_down_.size() <= param_id) {
      param_propagate_down_.resize(param_id + 1, true);
    }
    param_propagate_down_[param_id] = value;
  }