Caffe源码解读：Layer类

Layer类简介

• 至少有一个输入，输出Blob。
• 部分Layer带有权值和偏置项（如：激活层没有权值项）
• 前向传播对输入Blob处理，得到输出Blob。反向传播对输出的diff进行处理，得到输入的diff

ProtoBuffer描述

打开./caffe/src/caffe/caffe.proto文件，找到LayerParameter，查看对应的数据结构描述如下（根据这个数据结构描述，相当于约定，就可以自动生成对应的.hpp文件）:

// 注意
// 定义了自己的层的话，一定要更新下一个可用ID
// 下一个ID是147，最近更新:recurrent_param
message LayerParameter {
  optional string name = 1; // 可选参数，层的名字，string类型，下面类似
  optional string type = 2; // 层的类型
  repeated string bottom = 3; // 输入Blob对应的名字
  repeated string top = 4; // 输出Blob的名字

  // Train/Test阶段
  optional Phase phase = 10;

  // 每一层损失函数的权重，通常为0或者1，0表示不参与损失函数计算，1表示参与
  repeated float loss_weight = 5;

  // 具体的训练参数（比如相对于全局学习速率的缩放因子，权值衰减因子，这样就可以针对每一层设置不同的学习速率了）以及用于权值共享的名称（只有在需要权值共享的时候才需要名词）和其他设置，ParamSpec类型（这个类型的数据结构描述同样可以在当前文件中看到）
  repeated ParamSpec param = 6;

  // 该层的数值参数，BlobProto类型
  repeated BlobProto blobs = 7;

  // 是否需要对Bottom Blob进行反向传播，如果未指定，caffe会自动推断。该字段的维度数目应等于Bottom Blob的个数。即每层Bottom Blob都要指明是否需要反向传播
  repeated bool propagate_down = 11;

  // 根据当前网络状态规则，确定该层是否包含在网络中，如果没有指定任何规则，则一直被包含在网络中
  repeated NetStateRule include = 8;
  repeated NetStateRule exclude = 9;

  // 数据预处理参数
  optional TransformationParameter transform_param = 100;

  // 所有损失层共享的参数
  optional LossParameter loss_param = 101;

 // 不同层类型的参数
  // 注意，一些层实现可能有多种计算引擎（比如：caffe实现，以及cudnn实现），这些层包括一个引擎类型和一个引擎参数实现，默认引擎是在编译阶段的makefile里面设置的
  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;
}

Layer之间的继承关系

在看头文件声明之前，先看一下各个Layer之间的继承关系：

Layer类的派生类

Neuron Layers类继承关系

Vision Layers类继承关系

Common Layers类继承关系

Data Layers类继承关系

Loss Layers类继承关系

头文件声明

找到./include/caffe/layer.hpp文件：

#ifndef CAFFE_LAYER_H_
#define CAFFE_LAYER_H_

#include 
#include 
#include 

#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 
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)
    : 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_.resize(layer_param_.blobs_size());
        for (int i = 0; i < layer_param_.blobs_size(); ++i) {
          blobs_[i].reset(new Blob());
          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.
   */
  void SetUp(const vector*>& bottom,
      const vector*>& top) {
    InitMutex();
    CheckBlobCounts(bottom, top);
    LayerSetUp(bottom, top);
    Reshape(bottom, top);
    SetLossWeights(top);
  }

  /**
   * @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 layer_param_.
   * Setting up the shapes of top blobs and internal buffers should be done in
   * Reshape, which will be called before the forward pass to
   * adjust the top blob sizes.
   */
  virtual void LayerSetUp(const vector*>& bottom,
      const vector*>& 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.
   */
  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.
   */
  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.
   */
  inline void SetShared(bool is_shared) {
    CHECK(ShareInParallel() || !is_shared)
        << type() << "Layer does not support sharing.";
    is_shared_ = is_shared;
  }

  /**
   * @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.
   */
  virtual void Reshape(const vector*>& bottom,
      const vector*>& 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
   * \return 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.
   */
  inline Dtype Forward(const vector*>& bottom,
      const vector*>& 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.
   */
  inline void Backward(const vector*>& top,
      const vector& propagate_down,
      const vector*>& bottom);

  /**
   * @brief Returns the vector of learnable parameter blobs.
   */
  vector > >& 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.
   */
  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.
   */
  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.
   */
  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.
   */
  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().
   */
  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).
   */
  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.
   */
  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.
   */
  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_;
  /** The phase: TRAIN or TEST */
  Phase phase_;
  /** The vector that stores the learnable parameters as a set of blobs. */
  vector > > blobs_;
  /** Vector indicating whether to compute the diff of each param blob. */
  vector param_propagate_down_;

  /** The vector that indicates whether each top blob has a non-zero weight in
   *  the objective function. */
  vector loss_;

  /** @brief Using the CPU device, compute the layer output. */
  virtual void Forward_cpu(const vector*>& bottom,
      const vector*>& top) = 0;
  /**
   * @brief Using the GPU device, compute the layer output.
   *        Fall back to Forward_cpu() if unavailable.
   */
  virtual void Forward_gpu(const vector*>& bottom,
      const vector*>& 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*>& top,
      const vector& propagate_down,
      const vector*>& 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*>& top,
      const vector& propagate_down,
      const vector*>& 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.
   */
  virtual void CheckBlobCounts(const vector*>& bottom,
                               const vector*>& 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.
   */
  inline void SetLossWeights(const vector*>& 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);
      }
    }
  }

 private:
  /** Whether this layer is actually shared by other nets*/
  bool is_shared_;

  /** The mutex for sequential forward if this layer is shared */
  shared_ptr forward_mutex_;

  /** Initialize forward_mutex_ */
  void InitMutex();
  /** Lock forward_mutex_ if this layer is shared */
  void Lock();
  /** Unlock forward_mutex_ if this layer is shared */
  void Unlock();

  DISABLE_COPY_AND_ASSIGN(Layer);
};  // class Layer

// Forward and backward wrappers. You should implement the cpu and
// gpu specific implementations instead, and should not change these
// functions.
template 
inline Dtype Layer::Forward(const vector*>& bottom,
    const vector*>& top) {
  // Lock during forward to ensure sequential forward
  Lock();
  Dtype loss = 0;
  Reshape(bottom, top);
  switch (Caffe::mode()) {
  case Caffe::CPU:
    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:
    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 
inline void Layer::Backward(const vector*>& top,
    const vector& propagate_down,
    const vector*>& 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.";
  }
}

// Serialize LayerParameter to protocol buffer
template 
void Layer::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

#endif  // CAFFE_LAYER_H_

参考资料：

• 《21天实战Caffe》