Caffe代碼梳理

• src/caffe/proto/caffe.proto          了解基本數據結構內存對象和磁盤文件的一一映射，主要由ProtoBuffer工具完成；
• include頭文件                                理解整個框架，從基類向派生類順藤摸瓜；
• .cpp和.cu文件                                caffe框架不需要大改，只需要按需求派生出新的類實現即可；
• 編寫各類工具集成到caffe內部         如tools下的工具；

message ReLUParameter {

  optional float negative_slope = 1 [default = 0];
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 2 [default = DEFAULT];
}

#ifndef CAFFE_RELU_LAYER_HPP_
#define CAFFE_RELU_LAYER_HPP_

#include <vector>

#include "caffe/blob.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"

#include "caffe/layers/neuron_layer.hpp"

namespace caffe {

/**
 * @brief Rectified Linear Unit non-linearity @f$ y = \max(0, x) @f$.
 *        The simple max is fast to compute, and the function does not saturate.
 */
template <typename Dtype>
class ReLULayer : public NeuronLayer<Dtype> {      //派生于NeuronLayer，實現Relu**函數的計算
 public:
  /**
   * @param param provides ReLUParameter relu_param,
   *     with ReLULayer options:
   *   - negative_slope (\b optional, default 0).
   *     the value @f$ \nu @f$ by which negative values are multiplied.
   */
  //顯示構造函數
  explicit ReLULayer(const LayerParameter& param)
      : NeuronLayer<Dtype>(param) {}
//返回類名字符串
  virtual inline const char* type() const { return "ReLU"; }

 protected:
  //前向傳播函數
  virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);
  virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);

  //反向傳播函數
  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
};

}  // namespace caffe

#endif  // CAFFE_RELU_LAYER_HPP_

#include <algorithm>
#include <vector>

#include "caffe/layers/relu_layer.hpp"

namespace caffe {

template <typename Dtype>
void ReLULayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
    const vector<Blob<Dtype>*>& top) {
  const Dtype* bottom_data = bottom[0]->cpu_data();
  Dtype* top_data = top[0]->mutable_cpu_data();
  const int count = bottom[0]->count();
  Dtype negative_slope = this->layer_param_.relu_param().negative_slope();
  for (int i = 0; i < count; ++i) {
    top_data[i] = std::max(bottom_data[i], Dtype(0))
        + negative_slope * std::min(bottom_data[i], Dtype(0));
  }
}

template <typename Dtype>
void ReLULayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
    const vector<bool>& propagate_down,
    const vector<Blob<Dtype>*>& bottom) {
  if (propagate_down[0]) {
    const Dtype* bottom_data = bottom[0]->cpu_data();
    const Dtype* top_diff = top[0]->cpu_diff();
    Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
    const int count = bottom[0]->count();
    Dtype negative_slope = this->layer_param_.relu_param().negative_slope();
    for (int i = 0; i < count; ++i) {
      bottom_diff[i] = top_diff[i] * ((bottom_data[i] > 0)
          + negative_slope * (bottom_data[i] <= 0));
    }
  }
}


#ifdef CPU_ONLY
STUB_GPU(ReLULayer);
#endif

INSTANTIATE_CLASS(ReLULayer);

}  // namespace caffe