【caffe Layer】代码中文注释

src/caffe/proto/caffe.proto 中LayerParameter部分

// NOTE
// Update the next available ID when you add a new LayerParameter field.
// 如果增加一个新的LayerParameter域，需要更新下一个可用的ID
// LayerParameter next available layer-specific ID: 147 (last added: recurrent_param)
message LayerParameter {
  optional string name = 1; // the layer name 名称
  optional string type = 2; // the layer type 类型
  repeated string bottom = 3; // the name of each bottom blob 输入的Bottom Blob的名称
  repeated string top = 4; // the name of each top blob 输出的Top Blob名称

  // The train / test phase for computation.当前阶段TRAIN或TEST
  optional Phase phase = 10;

  // The amount of weight to assign each top blob in the objective.
  // Each layer assigns a default value, usually of either 0 or 1,
  // to each top blob.
  // 为每个输出Top Blob分配对损失函数的权重，每个Layer都有默认值，0表示不参与计算，1表示参与损失函数计算
  repeated float loss_weight = 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（例如相对全局学习常熟的缩放因子，以及用于权值共享的名称或其他设置）
  repeated ParamSpec param = 6;

  // The blobs containing the numeric parameters of the layer.
  // 承载该曾数值参数的Blob
  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.
  // 是否对Bottom Blob进行反向传播过程。该字段维度应与Bottom Blob个数一致。
  // The size must be either 0 or equal to the number of bottoms.
  repeated bool propagate_down = 11;

  // Rules controlling whether and when a layer is included in the network,
  // based on the current NetState.  You may specify a non-zero number of rules
  // to include OR exclude, but not both.  If no include or exclude rules are
  // specified, the layer is always included.  If the current NetState meets
  // ANY (i.e., one or more) of the specified rules, the layer is
  // included/excluded.
  // 控制某个层在某个时刻是否包含在网络中（基于当前的NetState）
  // 可以为include或exclude指定非零值（不能同时）
  // 如果没有规则，该层一直包含在网络中
  // 如果当前的NetState满足一定条件，那么该层被包含或被排斥
  repeated NetStateRule include = 8;
  repeated NetStateRule exclude = 9;

  // Parameters for data pre-processing. 数据预处理参数
  optional TransformationParameter transform_param = 100;

  // Parameters shared by loss layers. 所有损失层共享的参数
  optional LossParameter loss_param = 101;

  // Layer type-specific parameters.特定类型层参数
  // 注意：一些层实现时可能有多于一种计算引擎，这些层通过选择引擎类型和引擎参数来实现。
  // 默认引擎是在编译阶段由引擎开关设置的
  // 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.
  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 ScaleParameter scale_param = 142;
  optional SigmoidParameter sigmoid_param = 124;
  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;
}

 include/caffe/layer.hpp

#ifndef CAFFE_LAYER_H_
#define CAFFE_LAYER_H_

#include <algorithm>
#include <string>
#include <vector>

#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/layer_factory.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/util/math_functions.hpp"

/**
 Forward declare boost::thread instead of including boost/thread.hpp
 to avoid a boost/NVCC issues (#1009, #1010) on OSX.
 */
namespace boost { class mutex; }

namespace caffe {

/**
 * @brief An interface for the units of computation which can be composed into a
 *        Net.
 *
 * Layer%s must implement a Forward function, in which they take their input
 * (bottom) Blob%s (if any) and compute their output Blob%s (if any).
 * They may also implement a Backward function, in which they compute the error
 * gradients with respect to their input Blob%s, given the error gradients with
 * their output Blob%s.
 */
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.
   */
   // 显式构造函数，从LayerParameter中加载配置
  explicit Layer(const LayerParameter& param)
    : layer_param_(param) {
      // Set phase and copy blobs (if there are any).
      phase_ = param.phase();//设置当前阶段（训练或预测）
      if (layer_param_.blobs_size() > 0) {
        blobs_.resize(layer_param_.blobs_size());
        //按照layer_param_设置本身Blob对象个数，并依次把每个Blob对象尺寸调整为与layer_param_中Blob尺寸一致
        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() {}

  /**
   * @brief Implements common layer setup functionality.
   *
   * @param bottom the preshaped input blobs
   * @param top
   *     the allocated but unshaped output blobs, to be shaped by Reshape
   *
   * Checks that the number of bottom and top blobs is correct.
   * Calls LayerSetUp to do special layer setup for individual layer types,
   * followed by Reshape to set up sizes of top blobs and internal buffers.
   * Sets up the loss weight multiplier blobs for any non-zero loss weights.
   * This method may not be overridden.
   */
   //配置函数，实现常用层配置借口，不可被覆盖
  void SetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
    CheckBlobCounts(bottom, top);//检查blob
    LayerSetUp(bottom, top);     //与层类型相关的配置过程
    Reshape(bottom, top);        //对TopBlob进行变形
    SetLossWeights(top);         //设置损失权值因子Blob
  }

  /**
   * @brief Does layer-specific setup: your layer should implement this function
   *        as well as Reshape.
   *
   * @param bottom
   *     the preshaped input blobs, whose data fields store the input data for
   *     this layer
   * @param top
   *     the allocated but unshaped output blobs
   *
   * This method should do one-time layer specific setup. This includes reading
   * and processing relevent parameters from the <code>layer_param_</code>.
   * Setting up the shapes of top blobs and internal buffers should be done in
   * <code>Reshape</code>, which will be called before the forward pass to
   * adjust the top blob sizes.
   */
   //层配置虚函数，做特定类型层相关配置，由该类型层自己实现
  virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {}

  /**
   * @brief Adjust the shapes of top blobs and internal buffers to accommodate
   *        the shapes of the bottom blobs.
   *
   * @param bottom the input blobs, with the requested input shapes
   * @param top the top blobs, which should be reshaped as needed
   *
   * This method should reshape top blobs as needed according to the shapes
   * of the bottom (input) blobs, as well as reshaping any internal buffers
   * and making any other necessary adjustments so that the layer can
   * accommodate the bottom blobs.
   */
   //纯虚函数。变形函数，修改Top Blob以及内部Blob缓冲区形状
  virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) = 0;

  /**
   * @brief Given the bottom blobs, compute the top blobs and the loss.
   *
   * @param bottom
   *     the input blobs, whose data fields store the input data for this layer
   * @param top
   *     the preshaped output blobs, whose data fields will store this layers'
   *     outputs
   * 
eturn The total loss from the layer.
   *
   * The Forward wrapper calls the relevant device wrapper function
   * (Forward_cpu or Forward_gpu) to compute the top blob values given the
   * bottom blobs.  If the layer has any non-zero loss_weights, the wrapper
   * then computes and returns the loss.
   *
   * Your layer should implement Forward_cpu and (optionally) Forward_gpu.
   */
   // 前向传播函数
   // 给定Bottom Blob，计算TopBlob和loss，返回值为当前层的loss
   // 该函数会调用相应设备包装函数，如Forward_cpu or Forward_gpu来实现真正计算过程
   // 如果该层有非零loss权重参数，包装函数会计算并返回loss
   // 派生类应该实现Forward_cpu，Forward_gpu（可选）
  inline Dtype Forward(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);

  /**
   * @brief Given the top blob error gradients, compute the bottom blob error
   *        gradients.
   *
   * @param top
   *     the output blobs, whose diff fields store the gradient of the error
   *     with respect to themselves
   * @param propagate_down
   *     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.
   */
   //反向传播函数
   //给定输出的Top Blob误差梯度，计算输入的Bottom Blob的误差梯度
   //propagate_down为多路开关，与Bottom Blob矢量维度相同，每个值表示是否将误差梯度传递到对应的Bottom Blob
   //该函数会调用相应设备包装函数，如Backward_cpu and (可选) Backward_gpu实现计算过程，由派生类负责实现
  inline void Backward(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down,
      const vector<Blob<Dtype>*>& bottom);

  /**
   * @brief Returns the vector of learnable parameter blobs.
   */
  vector<shared_ptr<Blob<Dtype> > >& blobs() {
    return blobs_;//返回Layer内部可训练的权值、偏置项Blob向量
  }

  /**
   * @brief Returns the layer parameter.
   */
   //返回Layer初始化参数（由ProtoBuffer提供）
  const LayerParameter& layer_param() const { return layer_param_; }

  /**
   * @brief Writes the layer parameter to a protocol buffer
   */
   //将Layer初始化参数写入ProtoBuffer缓冲区
  virtual void ToProto(LayerParameter* param, bool write_diff = false);

  /**
   * @brief Returns the scalar loss associated with a top blob at a given index.
   */
   //返回与某个Top Blob相关的标量loss值
  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.
   */
   //设置与某个Top Blob相关的标量loss值
  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.
   */
   //返回层类型字符串，便于识别，由派生类实现
  virtual inline const char* type() const { return ""; }

  /**
   * @brief Returns the exact number of bottom blobs required by the layer,
   *        or -1 if no exact number is required.
   *
   * This method should be overridden to return a non-negative value if your
   * layer expects some exact number of bottom blobs.
   */
   //返回Layer需要的输入Bottom Blob数目，-1表示不关心，需要派生类实现
  virtual inline int ExactNumBottomBlobs() const { return -1; }
  /**
   * @brief Returns the minimum number of bottom blobs required by the layer,
   *        or -1 if no minimum number is required.
   *
   * This method should be overridden to return a non-negative value if your
   * layer expects some minimum number of bottom blobs.
   */
  virtual inline int MinBottomBlobs() const { return -1; }
  /**
   * @brief Returns the maximum number of bottom blobs required by the layer,
   *        or -1 if no maximum number is required.
   *
   * This method should be overridden to return a non-negative value if your
   * layer expects some maximum number of bottom blobs.
   */
  virtual inline int MaxBottomBlobs() const { return -1; }
  /**
   * @brief Returns the exact number of top blobs required by the layer,
   *        or -1 if no exact number is required.
   *
   * This method should be overridden to return a non-negative value if your
   * layer expects some exact number of top blobs.
   */
  //返回Layer需要的输出Top Blob数目，-1表示不关心，需要派生类实现
  virtual inline int ExactNumTopBlobs() const { return -1; }
  /**
   * @brief Returns the minimum number of top blobs required by the layer,
   *        or -1 if no minimum number is required.
   *
   * This method should be overridden to return a non-negative value if your
   * layer expects some minimum number of top blobs.
   */
  virtual inline int MinTopBlobs() const { return -1; }
  /**
   * @brief Returns the maximum number of top blobs required by the layer,
   *        or -1 if no maximum number is required.
   *
   * This method should be overridden to return a non-negative value if your
   * layer expects some maximum number of top blobs.
   */
  virtual inline int MaxTopBlobs() const { return -1; }
  /**
   * @brief Returns true if the layer requires an equal number of bottom and
   *        top blobs.
   *
   * This method should be overridden to return true if your layer expects an
   * equal number of bottom and top blobs.
   */
   //返回Layer是否有相同的输入输出Blob，需要派生类实现
  virtual inline bool EqualNumBottomTopBlobs() const { return false; }

  /**
   * @brief Return whether "anonymous" top blobs are created automatically
   *        by the layer.
   *
   * If this method returns true, Net::Init will create enough "anonymous" top
   * blobs to fulfill the requirement specified by ExactNumTopBlobs() or
   * MinTopBlobs().
   */
   //返回是否允许匿名Top Blob，即由该层自动创建。
   //如果为真，Net::Init 会创建足够多的匿名Top Blob来满足 ExactNumTopBlobs() or MinTopBlobs()需求
  virtual inline bool AutoTopBlobs() const { return false; }

  /**
   * @brief Return whether to allow force_backward for a given bottom blob
   *        index.
   *
   * If AllowForceBackward(i) == false, we will ignore the force_backward
   * setting and backpropagate to blob i only if it needs gradient information
   * (as is done when force_backward == false).
   */
   //是否允许强制反向传播。如果AllowForceBackward(i) == false，忽略force_backward设定
  virtual inline bool AllowForceBackward(const int bottom_index) const {
    return true;
  }

  /**
   * @brief Specifies whether the layer should compute gradients w.r.t. a
   *        parameter at a particular index given by param_id.
   *
   * You can safely ignore false values and always compute gradients
   * for all parameters, but possibly with wasteful computation.
   */
   //该Layer是否计算相对权值或偏置项的梯度，具体相对谁由param_id指定
  inline bool param_propagate_down(const int param_id) {
    return (param_propagate_down_.size() > param_id) ?
        param_propagate_down_[param_id] : false;
  }
  /**
   * @brief Sets whether the layer should compute gradients w.r.t. a
   *        parameter at a particular index given by param_id.
   */
   //设置该Layer是否计算相对权值或偏置项的梯度，具体相对谁由param_id指定
  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;
  }


 protected:
  /** The protobuf that stores the layer parameters */
  LayerParameter layer_param_;//保存Layer参数的ProtoBuffer对象
  /** The phase: TRAIN or TEST */
  Phase phase_;//Layer当前所属阶段，可选TRAIN或TEST
  /** The vector that stores the learnable parameters as a set of blobs. */
  vector<shared_ptr<Blob<Dtype> > > blobs_;//Layer内部权值偏置项，由Blob组织
  /** Vector indicating whether to compute the diff of each param blob. */
  vector<bool> param_propagate_down_;//标志位，是否计算对应的参数的误差梯度

  /** The vector that indicates whether each top blob has a non-zero weight in
   *  the objective function. */
  vector<Dtype> loss_;//标志位，在目标函数中是否每个Top Blob都有非零权值

  //以下四个函数会在派生类中经常看到
  
  /** @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);
  }

  /**
   * Called by the parent Layer's SetUp to check that the number of bottom
   * and top Blobs provided as input match the expected numbers specified by
   * the {ExactNum,Min,Max}{Bottom,Top}Blobs() functions.
   */
   //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.";
    }
  }

  /**
   * Called by SetUp to initialize the weights associated with any top blobs in
   * the loss function. Store non-zero loss weights in the diff blob.
   */
   //该函数在Layer的Setup函数中调用，主要目的是初始化与TopBlob相关的loss权重，放到top blob的diff域
   //实际由Forward（）计算loss
   //loss_weight==0 表示当前层不参与loss计算，大部分layer属于这一类
   //loss_weight==1 表示当前层参与loss计算，损失层（LossLayer）属于这一类
  inline void SetLossWeights(const vector<Blob<Dtype>*>& top) {
    //从ProtoBuffer对象中获得Layer参数，这里需要loss_weight参数
    const int num_loss_weights = layer_param_.loss_weight_size();
    if (num_loss_weights) {//如果ProtoBuffer中至少有一个loss_weight 参数
      //loss_weight个数应该与TopBlob相同，或者不要Loss_weigth参数
      CHECK_EQ(top.size(), num_loss_weights) << "loss_weight must be "
          "unspecified or specified once per top blob.";
      //遍历每一个Top Blob
      for (int top_id = 0; top_id < top.size(); ++top_id) {
        //从ProtoBuffer对象中获得loss_weight参数（0或者1）
        const Dtype loss_weight = layer_param_.loss_weight(top_id);
        if (loss_weight == Dtype(0)) { continue; }//为0，跳过
        this->set_loss(top_id, loss_weight);//不为0，进行网络的相关设置
        const int count = top[top_id]->count();//本地记录loss_weight的值
        Dtype* loss_multiplier = top[top_id]->mutable_cpu_diff();
        //将loss_weight写入TopBlob的diff中，传递到需要使用的地方，实现远程同步
        caffe_set(count, loss_weight, loss_multiplier);
      }
    }
  }

 private:
  DISABLE_COPY_AND_ASSIGN(Layer);//禁用拷贝构造函数和赋值运算函数
};  // class Layer

// Forward and backward wrappers. You should implement the cpu and
// gpu specific implementations instead, and should not change these
// functions.
//前向传播函数、后向传播函数的包装，不需要修改这两个函数
//使用时只需要在派生类中改写Forward_cpu等
template <typename Dtype>
inline Dtype Layer<Dtype>::Forward(const vector<Blob<Dtype>*>& bottom,
    const vector<Blob<Dtype>*>& top) {
  Dtype loss = 0;
  Reshape(bottom, top);
  switch (Caffe::mode()) {//判断计算设备
  case Caffe::CPU://在CPU上执行Forward计算
    Forward_cpu(bottom, top);//调用CPU版本的Forward
    //如果需要计算loss还需要进一步操作
    for (int top_id = 0; top_id < top.size(); ++top_id) {
      if (!this->loss(top_id)) { continue; }
      const int count = top[top_id]->count();
      //若为损失层，则已经通过Forward函数计算出全局损失函数，放在Top Blob data中
      const Dtype* data = top[top_id]->cpu_data();
      //若loss_weight不为0，则已经在SetLossWeight中将loss权重放在Top Blob diff 中
      const Dtype* loss_weights = top[top_id]->cpu_diff();
      loss += caffe_cpu_dot(count, data, loss_weights);//加权loss之和，得到标量loss
    }
    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.";
  }
  return loss;
}
//反向传播函数，直接调用对应设备函数
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.";
  }
}
//将层配置参数序列化为ProtoBuffer
// 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);
  }//权值偏置项也会保存
}

}  // namespace caffe

#endif  // CAFFE_LAYER_H_

 待更新

摘抄参考赵永科《深度学习 21天实战caffe》