Caffe_Layer源码解析

include/caffe/layer.hpp

template <typename Dtype>
class Layer {
 public:
  /**
   * You should not implement your own constructor. Any set up code should go
   * to SetUp(), where the dimensions of the bottom blobs are provided to the
   * layer.
   */
  explicit Layer(const LayerParameter& param)
  //显示构造函数，从LayerParameter对象中加载配置，并赋值给类成员变量layer_param_和is_shared_。
    : layer_param_(param), is_shared_(false) {
          // Set phase and copy blobs (if there are any).
      phase_ = param.phase();
      if (layer_param_.blobs_size() > 0) {
      //blobs_是vector类型的类成员变量，储存lay内部权值和偏置项，以blob形式组织。
        blobs_.resize(layer_param_.blobs_size());
      //根据layer_param_类中的参数设置本身Blob的数目及大小。
        for (int i = 0; i < layer_param_.blobs_size(); ++i) {
          blobs_[i].reset(new Blob<Dtype>());
          blobs_[i]->FromProto(layer_param_.blobs(i));
        }
      }
    }
  virtual ~Layer() {}//层虚析构函数。

下面是层的建立，实现通用层的接口。

//所有层都具有如下基本功能。
void SetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
    InitMutex();
    // Checks that the number of bottom and top blobs is correct.
    CheckBlobCounts(bottom, top);
    //特定层的setup是在这里实现的。
    LayerSetUp(bottom, top);
    //set up sizes of top blobs and 内部缓冲区.
    Reshape(bottom, top);
    SetLossWeights(top);//设置损失权值因子blob
  }

实现特定层：

virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {}

  /**
   * @brief Whether a layer should be shared by multiple nets during data
   *        parallelism. By default, all layers except for data layers should
   *        not be shared. data layers should be shared to ensure each worker
   *        solver access data sequentially during data parallelism.
   */该层是否可以被多个网络共享，只有datalayer返回true。
  virtual inline bool ShareInParallel() const { return false; }

  /** @brief Return whether this layer is actually shared by other nets.
   *         If ShareInParallel() is true and using more than one GPU and the
   *         net has TRAIN phase, then this function is expected return true.
   */返回该层实际上是否被多个网络共享。
  inline bool IsShared() const { return is_shared_; }

  /** @brief Set whether this layer is actually shared by other nets
   *         If ShareInParallel() is true and using more than one GPU and the
   *         net has TRAIN phase, then is_shared should be set true.
   */设置该层实际上是否被多个网络共享。
  inline void SetShared(bool is_shared) {
    CHECK(ShareInParallel() || !is_shared)
        << type() << "Layer does not support sharing.";
    is_shared_ = is_shared;
  }

// 根据需要reshape top_blob的形状。//纯虚函数，仅仅是一个声明作用，具体实现需要在子类中实现后才能调用。
virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) = 0;

//inline 说明这个函数是内联的，在编译过程中内联函数会直接被源代码替换，提高执行效率 如果类中的某个函数会被调用很多次或者放在循环中，那么建议将这个函数声明为内联，可以提高程序的运行效率。

// **实现前向传播，给定Bottom Blob，计算Top Blob和Loss，返回值为当前层loss。
inline Dtype Forward(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);

// 实现后向传播，给定Top Blob的误差梯度，计算Bottom Blob的误差梯度。
   * @brief Given the top blob error gradients, compute the bottom blob error
   *     the output blobs, whose diff fields store the gradient of the error
   *    // a vector with equal length to bottom, with each index indicating
   *     //whether to propagate the error gradients down to the bottom blob at the corresponding index
   * @param bottom
   *     the input blobs, whose diff fields will store the gradient of the error
   *     with respect to themselves after Backward is run
   *
   * The Backward wrapper calls the relevant device wrapper function
   * (Backward_cpu or Backward_gpu) to compute the bottom blob diffs given the
   * top blob diffs.
   *
   // Your layer should implement Backward_cpu and (optionally) Backward_gpu.
   */
  inline void Backward(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down,
      const vector<Blob<Dtype>*>& bottom);

返回存储的blobs

vector<shared_ptr<Blob<Dtype> > >& blobs() {
    return blobs_;
  }

  /**
   * @brief Returns the layer parameter.
   *
  const LayerParameter& layer_param() const { return layer_param_; }
* @brief Writes the layer parameter to a protocol buffer
   */
  virtual void ToProto(LayerParameter* param, bool write_diff = false);

  /**
   * @brief Returns the scalar loss associated with a top blob at a given index.
   */
  inline Dtype loss(const int top_index) const {
    return (loss_.size() > top_index) ? loss_[top_index] : Dtype(0);
  }

  /**
   * @brief Sets the loss associated with a top blob at a given index.
   */
  inline void set_loss(const int top_index, const Dtype value) {
    if (loss_.size() <= top_index) {
      loss_.resize(top_index + 1, Dtype(0));
    }
    loss_[top_index] = value;
  }

  /**
   * @brief Returns the layer type.
   //返回层的类型，派生类中实现。
  virtual inline const char* type() const { return ""; }

  /**

没注释部分的英文简单，解释的很清楚。中间的一些不重要的代码就不贴了，只贴重要部分。

//下面四个函数在派生类中经常看到。也是layer功能的最重要的部分。
/** @brief Using the CPU device, compute the layer output. */
  virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) = 0;
  /**
   * @brief Using the GPU device, compute the layer output.
   *        Fall back to Forward_cpu() if unavailable.
   */
  virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
    // LOG(WARNING) << "Using CPU code as backup.";
    return Forward_cpu(bottom, top);
  }

  /**
   * @brief Using the CPU device, compute the gradients for any parameters and
   *        for the bottom blobs if propagate_down is true.
   */
  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down,
      const vector<Blob<Dtype>*>& bottom) = 0;
  /**
   * @brief Using the GPU device, compute the gradients for any parameters and
   *        for the bottom blobs if propagate_down is true.
   *        Fall back to Backward_cpu() if unavailable.
   */
  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down,
      const vector<Blob<Dtype>*>& bottom) {
    // LOG(WARNING) << "Using CPU code as backup.";
    Backward_cpu(top, propagate_down, bottom);
  }

检查bottom和top的数目是否满足要求。并根据top设置loss_weight

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.";
    }
  }
inline void SetLossWeights(const vector<Blob<Dtype>*>& top) {
    const int num_loss_weights = layer_param_.loss_weight_size();
    if (num_loss_weights) {
      CHECK_EQ(top.size(), num_loss_weights) << "loss_weight must be "
          "unspecified or specified once per top blob.";
      for (int top_id = 0; top_id < top.size(); ++top_id) {
        const Dtype loss_weight = layer_param_.loss_weight(top_id);
        if (loss_weight == Dtype(0)) { continue; }
        this->set_loss(top_id, loss_weight);
        const int count = top[top_id]->count();
        Dtype* loss_multiplier = top[top_id]->mutable_cpu_diff();
        caffe_set(count, loss_weight, loss_multiplier);
      }
    }
  }

前向传播包装和后向传播包装，具体实现的时候，不需要改变这两个函数，只要具体实现其中的foward_cpu,forward_gpu,backward_cpu,backward_gpu。

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
  Lock();
  Dtype loss = 0;
  Reshape(bottom, top);
  switch (Caffe::mode()) {
  case Caffe::CPU:
  //派生类中需要实现这部分前向传播cpu模式。
    Forward_cpu(bottom, top);
    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]->cpu_data();
      const Dtype* loss_weights = top[top_id]->cpu_diff();
      loss += caffe_cpu_dot(count, data, loss_weights);
    }
    break;
  case Caffe::GPU:
  //派生类中需要实现这部分前向传播的gpu模式。
    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();
  return loss;
}

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:
   //派生类中需要实现这部分后向传播的cpu模式。
    Backward_cpu(top, propagate_down, bottom);
    break;
  case Caffe::GPU:
  //派生类中需要实现这部分后向传播的gpu模式。
    Backward_gpu(top, propagate_down, bottom);
    break;
  default:
    LOG(FATAL) << "Unknown caffe mode.";
  }
}

// Serialize LayerParameter to protocol buffer
template <typename Dtype>
void Layer<Dtype>::ToProto(LayerParameter* param, bool write_diff) {
  param->Clear();
  param->CopyFrom(layer_param_);
  param->clear_blobs();
  for (int i = 0; i < blobs_.size(); ++i) {
    blobs_[i]->ToProto(param->add_blobs(), write_diff);
  }
}

}  // namespace caffe