caffe源码：Layer

caffe.proto

enum Phase {
   TRAIN = 0;
   TEST = 1;
}

message NetState {
  optional Phase phase = 1 [default = TEST];
  optional int32 level = 2 [default = 0];
  repeated string stage = 3;
}

message NetStateRule {
  // Set phase to require the NetState have a particular phase (TRAIN or TEST)
  // to meet this rule.
  optional Phase phase = 1;

  // Set the minimum and/or maximum levels in which the layer should be used.
  // Leave undefined to meet the rule regardless of level.
  optional int32 min_level = 2;
  optional int32 max_level = 3;

  // Customizable sets of stages to include or exclude.
  // The net must have ALL of the specified stages and NONE of the specified
  // "not_stage"s to meet the rule.
  // (Use multiple NetStateRules to specify conjunctions of stages.)
  repeated string stage = 4;
  repeated string not_stage = 5;
}

// Specifies training parameters (multipliers on global learning constants,
// and the name and other settings used for weight sharing).
message ParamSpec {
  // The names of the parameter blobs -- useful for sharing parameters among
  // layers, but never required otherwise.  To share a parameter between two
  // layers, give it a (non-empty) name.
  optional string name = 1;

  // Whether to require shared weights to have the same shape, or just the same
  // count -- defaults to STRICT if unspecified.
  optional DimCheckMode share_mode = 2;
  enum DimCheckMode {
    // STRICT (default) requires that num, channels, height, width each match.
    STRICT = 0;
    // PERMISSIVE requires only the count (num*channels*height*width) to match.
    PERMISSIVE = 1;
  }

  // The multiplier on the global learning rate for this parameter.
  optional float lr_mult = 3 [default = 1.0];

  // The multiplier on the global weight decay for this parameter.
  optional float decay_mult = 4 [default = 1.0];
}

// NOTE
// Update the next available ID when you add a new LayerParameter field.
//
// LayerParameter next available layer-specific ID: 147 (last added: recurrent_param) : 
//注意此行ID，下次加自己的layer的参数ID就顺着这个数字继续往下加！
//或者另开个数字：如200，只要此message里ID不重复就行。
message LayerParameter {
  optional string name = 1; // the layer name
  optional string type = 2; // the layer type
  repeated string bottom = 3; // the name of each bottom blob
  repeated string top = 4; // the name of each top blob

  // The train / test phase for computation.
  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.
  repeated float loss_weight = 5;

  // Specifies training parameters (multipliers on global learning constants,
  // and the name and other settings used for weight sharing).
  repeated ParamSpec param = 6;

  // The blobs containing the numeric parameters of the layer.
  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.
  //
  // 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.
  repeated NetStateRule include = 8;
  repeated NetStateRule exclude = 9;

  // Parameters for data pre-processing.
  optional TransformationParameter transform_param = 100;

  // Parameters shared by loss layers.
  optional LossParameter loss_param = 101;

  // Yolo detection loss layer
  optional DetectionLossParameter detection_loss_param = 200;
  // Yolo detection evaluation layer
  optional EvalDetectionParameter eval_detection_param = 201;

  // Layer type-specific parameters.
  //
  // 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;
}

// Message that stores parameters used to apply transformation
// to the data layer's data
message TransformationParameter {
  // For data pre-processing, we can do simple scaling and subtracting the
  // data mean, if provided. Note that the mean subtraction is always carried
  // out before scaling.
  optional float scale = 1 [default = 1];
  // Specify if we want to randomly mirror data.
  optional bool mirror = 2 [default = false];
  // Specify if we would like to randomly crop an image.
  optional uint32 crop_size = 3 [default = 0];
  // mean_file and mean_value cannot be specified at the same time
  optional string mean_file = 4;
  // if specified can be repeated once (would substract it from all the channels)
  // or can be repeated the same number of times as channels
  // (would subtract them from the corresponding channel)
  repeated float mean_value = 5;
  // Force the decoded image to have 3 color channels.
  optional bool force_color = 6 [default = false];
  // Force the decoded image to have 1 color channels.
  optional bool force_gray = 7 [default = false];
}

// Message that stores parameters shared by loss layers
message LossParameter {
  // If specified, ignore instances with the given label.
  optional int32 ignore_label = 1;
  // How to normalize the loss for loss layers that aggregate across batches,
  // spatial dimensions, or other dimensions.  Currently only implemented in
  // SoftmaxWithLoss layer.
  enum NormalizationMode {
    // Divide by the number of examples in the batch times spatial dimensions.
    // Outputs that receive the ignore label will NOT be ignored in computing
    // the normalization factor.
    FULL = 0;
    // Divide by the total number of output locations that do not take the
    // ignore_label.  If ignore_label is not set, this behaves like FULL.
    VALID = 1;
    // Divide by the batch size.
    BATCH_SIZE = 2;
    // Do not normalize the loss.
    NONE = 3;
  }
  optional NormalizationMode normalization = 3 [default = VALID];
  // Deprecated.  Ignored if normalization is specified.  If normalization
  // is not specified, then setting this to false will be equivalent to
  // normalization = BATCH_SIZE to be consistent with previous behavior.
  optional bool normalize = 2;
}

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.
   */
  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<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.
   */
  void SetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& 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 <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.
   */
  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.
   */
  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<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
   * \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<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.
   */
  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_;
  }



  /**
   * @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<shared_ptr<Blob<Dtype> > > blobs_;
  /** Vector indicating whether to compute the diff of each param blob. */
  vector<bool> param_propagate_down_;

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


  /** @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.
   */
  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.
   */
  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);
      }
    }
  }



 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<boost::mutex> 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 <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:
    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 <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.";
  }
}




// 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

#endif  // CAFFE_LAYER_H_

layer.cpp

#include <boost/thread.hpp>
#include "caffe/layer.hpp"

namespace caffe {

template <typename Dtype>
void Layer<Dtype>::InitMutex()
{
  forward_mutex_.reset(new boost::mutex());
}


template <typename Dtype>
void Layer<Dtype>::Lock()
{
  if (IsShared())
  {
    forward_mutex_->lock();
  }
}


template <typename Dtype>
void Layer<Dtype>::Unlock()
{
  if (IsShared())
  {
    forward_mutex_->unlock();
  }
}



INSTANTIATE_CLASS(Layer);

}  // namespace caffe