caffe之Data_Layer层代码解析

一、 caffe的数据输入层， 根据不同的输入方式有不同的层， 因为本人最早接触的是通过lmdb数据库输入数据，而lmdb对应这DataLayer层， 其实还有一个常用的就是ImageDataLayer层， 这个层 可以直接输入图片的路径， 而不需转换。

    上面这张图， 反应输入层的继承关系和不同层次关系， 可见： DataLayer层 继承自BasePrefetchingDataLayer层，继承BaseDataLayer层，继承Layer层。

   DataLayer.hpp：  其实这个层只做了一件事情， 那就是reshape之后，从lmdb数据库中读取数据， 然后将读到的数据指针输出给top， 如果有标签，也会输出标签。

   ImageDataLayer.cpp： 这个层也只做了一件事情， 那就是reshape之后，从文件列表中读取数据， 然后将读到的数据指针输出给top， 如果有标签，也会输出标签

如果只是使用， 那么参考我的另一篇微博 http://blog.youkuaiyun.com/ming5432ming/article/details/78458916 ， 没有必要往下看。   

     如想了解下具体实现，请往下走。

二、 下面是DataLayer.hpp

      先说结论：  其实这个层只做了一件事情， 那就是reshape之后，从lmdb数据库中读取数据， 然后将读到的数据指针输出给top， 如果有标签，也会输出标签。

 

#ifndef CAFFE_DATA_LAYER_HPP_
#define CAFFE_DATA_LAYER_HPP_

#include <vector>

#include "caffe/blob.hpp"
#include "caffe/data_transformer.hpp"
#include "caffe/internal_thread.hpp"
#include "caffe/layer.hpp"
#include "caffe/layers/base_data_layer.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/util/db.hpp"

namespace caffe {

template <typename Dtype>
class DataLayer : public BasePrefetchingDataLayer<Dtype> {
 public:
  explicit DataLayer(const LayerParameter& param);
  virtual ~DataLayer();
  virtual void DataLayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);
  virtual inline const char* type() const { return "Data"; }     //名字是Data， 这个对应这prototxt文件中的type变量。
  virtual inline int ExactNumBottomBlobs() const { return 0; }     //data层没有输入bottom层
  virtual inline int MinTopBlobs() const { return 1; }
  virtual inline int MaxTopBlobs() const { return 2; }

 protected:
  void Next();
  bool Skip();
  virtual void load_batch(Batch<Dtype>* batch);

  shared_ptr<db::DB> db_;             //lmdb数据库操作的指针。
  shared_ptr<db::Cursor> cursor_;
  uint64_t offset_;
};

}  // namespace caffe

#endif  // CAFFE_DATA_LAYER_HPP_

下面是DataLayer.cpp

#ifdef USE_OPENCV
#include <opencv2/core/core.hpp>
#endif  // USE_OPENCV
#include <stdint.h>

#include <vector>

#include "caffe/data_transformer.hpp"
#include "caffe/layers/data_layer.hpp"
#include "caffe/util/benchmark.hpp"

namespace caffe {

template <typename Dtype>
DataLayer<Dtype>::DataLayer(const LayerParameter& param)  // 打开数据库
  : BasePrefetchingDataLayer<Dtype>(param),
    offset_() {
  db_.reset(db::GetDB(param.data_param().backend()));
  db_->Open(param.data_param().source(), db::READ);
  cursor_.reset(db_->NewCursor());
}

template <typename Dtype>
DataLayer<Dtype>::~DataLayer() {
  this->StopInternalThread();
}

template <typename Dtype>
void DataLayer<Dtype>::DataLayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  const int batch_size = this->layer_param_.data_param().batch_size();  //从配置文件中读取批处理大小；
  // Read a data point, and use it to initialize the top blob.
  Datum datum;
  datum.ParseFromString(cursor_->value());               //读取一个数据，并存放在datum中， datum是在caffe.proto中定义的数据结构。 里面包括channel、height、和width

  // Use data_transformer to infer the expected blob shape from datum.
  vector<int> top_shape = this->data_transformer_->InferBlobShape(datum);   //用读到的数据初始化top_shape结构。
  this->transformed_data_.Reshape(top_shape);
  // Reshape top[0] and prefetch_data according to the batch_size.
  top_shape[0] = batch_size;         //因为datum中没有批处理的信息，所以在这补充。
  top[0]->Reshape(top_shape);
  for (int i = 0; i < this->prefetch_.size(); ++i) {
    this->prefetch_[i]->data_.Reshape(top_shape);    //reshape每一个险种中的prefetch_
  }
  LOG_IF(INFO, Caffe::root_solver())
      << "output data size: " << top[0]->num() << ","
      << top[0]->channels() << "," << top[0]->height() << ","
      << top[0]->width();
  // label
  if (this->output_labels_) {
    vector<int> label_shape(1, batch_size);    //如果有标签，则输出标签结构。
    top[1]->Reshape(label_shape);
    for (int i = 0; i < this->prefetch_.size(); ++i) {
      this->prefetch_[i]->label_.Reshape(label_shape);
    }
  }
}

template <typename Dtype>
bool DataLayer<Dtype>::Skip() {
  int size = Caffe::solver_count();
  int rank = Caffe::solver_rank();
  bool keep = (offset_ % size) == rank ||
              // In test mode, only rank 0 runs, so avoid skipping
              this->layer_param_.phase() == TEST;
  return !keep;
}

template<typename Dtype>
void DataLayer<Dtype>::Next() {
  cursor_->Next();
  if (!cursor_->valid()) {         //如果数据库结束，则从头开始读取。
    LOG_IF(INFO, Caffe::root_solver())
        << "Restarting data prefetching from start.";
    cursor_->SeekToFirst();            
  }
  offset_++;
}

// This function is called on prefetch thread
template<typename Dtype>
void DataLayer<Dtype>::load_batch(Batch<Dtype>* batch) {      //每一个线程都会执行这个函数。
  CPUTimer batch_timer;
  batch_timer.Start();
  double read_time = 0;
  double trans_time = 0;
  CPUTimer timer;
  CHECK(batch->data_.count());
  CHECK(this->transformed_data_.count());
  const int batch_size = this->layer_param_.data_param().batch_size();  

  Datum datum;
  for (int item_id = 0; item_id < batch_size; ++item_id) {
    timer.Start();
    while (Skip()) {
      Next();
    }
    datum.ParseFromString(cursor_->value());      //读取一个数据；
    read_time += timer.MicroSeconds();

    if (item_id == 0) {
      // Reshape according to the first datum of each batch
      // on single input batches allows for inputs of varying dimension.
      // Use data_transformer to infer the expected blob shape from datum.
      vector<int> top_shape = this->data_transformer_->InferBlobShape(datum);
      this->transformed_data_.Reshape(top_shape);
      // Reshape batch according to the batch_size.
      top_shape[0] = batch_size;
      batch->data_.Reshape(top_shape);      //批处理batch的  reshape
    }

    // Apply data transformations (mirror, scale, crop...)
    timer.Start();
    int offset = batch->data_.offset(item_id);      //在一个批次中的偏移量；
    Dtype* top_data = batch->data_.mutable_cpu_data();    //读取cpu的指针，并赋值给top_data；
    this->transformed_data_.set_cpu_data(top_data + offset);
    this->data_transformer_->Transform(datum, &(this->transformed_data_));   //设置cpu的data指针。
    // Copy label.
    if (this->output_labels_) {     //设置label数据。
      Dtype* top_label = batch->label_.mutable_cpu_data();
      top_label[item_id] = datum.label();
    }
    trans_time += timer.MicroSeconds();
    Next();
  }
  timer.Stop();
  batch_timer.Stop();
  DLOG(INFO) << "Prefetch batch: " << batch_timer.MilliSeconds() << " ms.";
  DLOG(INFO) << "     Read time: " << read_time / 1000 << " ms.";
  DLOG(INFO) << "Transform time: " << trans_time / 1000 << " ms.";
}

INSTANTIATE_CLASS(DataLayer);
REGISTER_LAYER_CLASS(Data);

}  // namespace caffe

总结： 其实这个层只做了一件事情， 那就是reshape之后，从数据库中读取数据， 然后将读到的数据指针输出给top。






三、 既然到了这，顺便说一下ImageDataLayer层。
下面是ImageDataLayer.hpp
 
#ifndef CAFFE_IMAGE_DATA_LAYER_HPP_
#define CAFFE_IMAGE_DATA_LAYER_HPP_

#include <string>
#include <utility>
#include <vector>

#include "caffe/blob.hpp"
#include "caffe/data_transformer.hpp"
#include "caffe/internal_thread.hpp"
#include "caffe/layer.hpp"
#include "caffe/layers/base_data_layer.hpp"
#include "caffe/proto/caffe.pb.h"

namespace caffe {

/**
 * @brief Provides data to the Net from image files.
 *
 * TODO(dox): thorough documentation for Forward and proto params.
 */
template <typename Dtype>
class ImageDataLayer : public BasePrefetchingDataLayer<Dtype> {
 public:
  explicit ImageDataLayer(const LayerParameter& param)
      : BasePrefetchingDataLayer<Dtype>(param) {}
  virtual ~ImageDataLayer();
  virtual void DataLayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);

  virtual inline const char* type() const { return "ImageData"; }   //这是prototxt中 的type
  virtual inline int ExactNumBottomBlobs() const { return 0; }
  virtual inline int ExactNumTopBlobs() const { return 2; }

 protected:
  shared_ptr<Caffe::RNG> prefetch_rng_;
  virtual void ShuffleImages();
  virtual void load_batch(Batch<Dtype>* batch);

  vector<std::pair<std::string, int> > lines_;
  int lines_id_;
};


}  // namespace caffe

#endif  // CAFFE_IMAGE_DATA_LAYER_HPP_

下面是ImageDataLayer.cpp

#ifdef USE_OPENCV
#include <opencv2/core/core.hpp>

#include <fstream>  // NOLINT(readability/streams)
#include <iostream>  // NOLINT(readability/streams)
#include <string>
#include <utility>
#include <vector>

#include "caffe/data_transformer.hpp"
#include "caffe/layers/base_data_layer.hpp"
#include "caffe/layers/image_data_layer.hpp"
#include "caffe/util/benchmark.hpp"
#include "caffe/util/io.hpp"
#include "caffe/util/math_functions.hpp"
#include "caffe/util/rng.hpp"

namespace caffe {

template <typename Dtype>
ImageDataLayer<Dtype>::~ImageDataLayer<Dtype>() {
  this->StopInternalThread();
}

template <typename Dtype>
void ImageDataLayer<Dtype>::DataLayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  const int new_height = this->layer_param_.image_data_param().new_height();   //从网络文件中读取参数；
  const int new_width  = this->layer_param_.image_data_param().new_width();
  const bool is_color  = this->layer_param_.image_data_param().is_color();
  string root_folder = this->layer_param_.image_data_param().root_folder();

  CHECK((new_height == 0 && new_width == 0) ||
      (new_height > 0 && new_width > 0)) << "Current implementation requires "
      "new_height and new_width to be set at the same time.";
  // Read the file with filenames and labels
  const string& source = this->layer_param_.image_data_param().source();
  LOG(INFO) << "Opening file " << source;
  std::ifstream infile(source.c_str());               // 打开网络文件中的文件列表。
  string line;
  size_t pos;
  int label;
  while (std::getline(infile, line)) {
    pos = line.find_last_of(' ');                        //图片路径与标签用空格隔开
    label = atoi(line.substr(pos + 1).c_str());
    lines_.push_back(std::make_pair(line.substr(0, pos), label));  //读出一行的图片路径和标签
  }

  CHECK(!lines_.empty()) << "File is empty";

  if (this->layer_param_.image_data_param().shuffle()) {
    // randomly shuffle data
    LOG(INFO) << "Shuffling data";
    const unsigned int prefetch_rng_seed = caffe_rng_rand();
    prefetch_rng_.reset(new Caffe::RNG(prefetch_rng_seed));
    ShuffleImages();
  } else {
    if (this->phase_ == TRAIN && Caffe::solver_rank() > 0 &&
        this->layer_param_.image_data_param().rand_skip() == 0) {
      LOG(WARNING) << "Shuffling or skipping recommended for multi-GPU";
    }
  }
  LOG(INFO) << "A total of " << lines_.size() << " images.";

  lines_id_ = 0;
  // Check if we would need to randomly skip a few data points
  if (this->layer_param_.image_data_param().rand_skip()) {
    unsigned int skip = caffe_rng_rand() %
        this->layer_param_.image_data_param().rand_skip();
    LOG(INFO) << "Skipping first " << skip << " data points.";
    CHECK_GT(lines_.size(), skip) << "Not enough points to skip";
    lines_id_ = skip;
  }
  // Read an image, and use it to initialize the top blob.
  cv::Mat cv_img = ReadImageToCVMat(root_folder + lines_[lines_id_].first,    //读取图片数据
                                    new_height, new_width, is_color);
  CHECK(cv_img.data) << "Could not load " << lines_[lines_id_].first;
  // Use data_transformer to infer the expected blob shape from a cv_image.
  vector<int> top_shape = this->data_transformer_->InferBlobShape(cv_img);
  this->transformed_data_.Reshape(top_shape);
  // Reshape prefetch_data and top[0] according to the batch_size.
  const int batch_size = this->layer_param_.image_data_param().batch_size();
  CHECK_GT(batch_size, 0) << "Positive batch size required";
  top_shape[0] = batch_size;
  for (int i = 0; i < this->prefetch_.size(); ++i) {
    this->prefetch_[i]->data_.Reshape(top_shape);                   //reshape  prefetch参数的结构
  }
  top[0]->Reshape(top_shape);

  LOG(INFO) << "output data size: " << top[0]->num() << ","
      << top[0]->channels() << "," << top[0]->height() << ","
      << top[0]->width();
  // label
  vector<int> label_shape(1, batch_size);            //标签的reshape
  top[1]->Reshape(label_shape);
  for (int i = 0; i < this->prefetch_.size(); ++i) {
    this->prefetch_[i]->label_.Reshape(label_shape);
  }
}

template <typename Dtype>
void ImageDataLayer<Dtype>::ShuffleImages() {
  caffe::rng_t* prefetch_rng =
      static_cast<caffe::rng_t*>(prefetch_rng_->generator());
  shuffle(lines_.begin(), lines_.end(), prefetch_rng);
}

// This function is called on prefetch thread
template <typename Dtype>
void ImageDataLayer<Dtype>::load_batch(Batch<Dtype>* batch) {
  CPUTimer batch_timer;
  batch_timer.Start();
  double read_time = 0;
  double trans_time = 0;
  CPUTimer timer;
  CHECK(batch->data_.count());
  CHECK(this->transformed_data_.count());
  ImageDataParameter image_data_param = this->layer_param_.image_data_param();
  const int batch_size = image_data_param.batch_size();
  const int new_height = image_data_param.new_height();
  const int new_width = image_data_param.new_width();
  const bool is_color = image_data_param.is_color();
  string root_folder = image_data_param.root_folder();

  // Reshape according to the first image of each batch
  // on single input batches allows for inputs of varying dimension.
  cv::Mat cv_img = ReadImageToCVMat(root_folder + lines_[lines_id_].first,
      new_height, new_width, is_color);
  CHECK(cv_img.data) << "Could not load " << lines_[lines_id_].first;
  // Use data_transformer to infer the expected blob shape from a cv_img.
  vector<int> top_shape = this->data_transformer_->InferBlobShape(cv_img);
  this->transformed_data_.Reshape(top_shape);
  // Reshape batch according to the batch_size.
  top_shape[0] = batch_size;
  batch->data_.Reshape(top_shape);

  Dtype* prefetch_data = batch->data_.mutable_cpu_data();
  Dtype* prefetch_label = batch->label_.mutable_cpu_data();

  // datum scales
  const int lines_size = lines_.size();
  for (int item_id = 0; item_id < batch_size; ++item_id) {
    // get a blob
    timer.Start();
    CHECK_GT(lines_size, lines_id_);
    cv::Mat cv_img = ReadImageToCVMat(root_folder + lines_[lines_id_].first,
        new_height, new_width, is_color);
    CHECK(cv_img.data) << "Could not load " << lines_[lines_id_].first;
    read_time += timer.MicroSeconds();
    timer.Start();
    // Apply transformations (mirror, crop...) to the image
    int offset = batch->data_.offset(item_id);
    this->transformed_data_.set_cpu_data(prefetch_data + offset);
    this->data_transformer_->Transform(cv_img, &(this->transformed_data_));
    trans_time += timer.MicroSeconds();

    prefetch_label[item_id] = lines_[lines_id_].second;
    // go to the next iter
    lines_id_++;
    if (lines_id_ >= lines_size) {
      // We have reached the end. Restart from the first.
      DLOG(INFO) << "Restarting data prefetching from start.";
      lines_id_ = 0;
      if (this->layer_param_.image_data_param().shuffle()) {
        ShuffleImages();
      }
    }
  }
  batch_timer.Stop();
  DLOG(INFO) << "Prefetch batch: " << batch_timer.MilliSeconds() << " ms.";
  DLOG(INFO) << "     Read time: " << read_time / 1000 << " ms.";
  DLOG(INFO) << "Transform time: " << trans_time / 1000 << " ms.";
}

INSTANTIATE_CLASS(ImageDataLayer);
REGISTER_LAYER_CLASS(ImageData);

}  // namespace caffe
#endif  // USE_OPENCV

总结：  会发现这个cpp的机构和Data_layer.cpp是类似的， 作用就是从文件列表中读取文件，并送给top结构。