【caffe I/O】数据变换器（图像的预处理部分） 代码注释

caffe.proto中TransformationParameter部分

// 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.
  //像素幅度缩放参数，默认不缩放
  optional float scale = 1 [default = 1];
  // Specify if we want to randomly mirror data.
  //图像随机镜像开关。默认false，不进行随机镜像操作
  optional bool mirror = 2 [default = false];
  // Specify if we would like to randomly crop an image.
  //图像随机切块的大小。默认不切块。
  optional uint32 crop_size = 3 [default = 0];
  // mean_file and mean_value cannot be specified at the same time
  //存储图像均值的文件
  optional string mean_file = 4;
  // if specified can be repeated once (would subtract it from all the channels)
  // or can be repeated the same number of times as channels
  // (would subtract them from the corresponding channel)
  //均值数值。无需读取文件。
  //如果均值数目和通道数一致，则每个通道分别减去对应均值；
  //如果没有均值只有一个，则每个通道减去相同的均值。
  repeated float mean_value = 5;
  // Force the decoded image to have 3 color channels.
  //强制为三通道三色图像输入 默认false
  optional bool force_color = 6 [default = false];
  // Force the decoded image to have 1 color channels.
  //强制为单通道灰度图像输入 默认false
  optional bool force_gray = 7 [default = false];
}

caffe.proto中Datum部分

 

//Datum用来从LMDB/LEVELDB 中读取数据，或将数据写入其中。和BlobProto有相似功能，只是
//BlobProto用于模型权值序列化反序列化，而Datum用于数据或特征图（feature map）提供序列化反序列化
message Datum {
  //数据维度信息：channels*height*width
  optional int32 channels = 1;
  optional int32 height = 2;
  optional int32 width = 3;
  // the actual image data, in bytes
  //图像数据，以字节类型存储
  optional bytes data = 4;
  //标签数据，统一用int32类型存储
  optional int32 label = 5;
  // Optionally, the datum could also hold float data.
  repeated float float_data = 6;
  // If true data contains an encoded image that need to be decoded
  optional bool encoded = 7 [default = false];//是否为编码数据，默认false
}

 

 

 

 include/caffe/data_transformer.hpp

#ifndef CAFFE_DATA_TRANSFORMER_HPP
#define CAFFE_DATA_TRANSFORMER_HPP

#include <vector>

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

namespace caffe {

/**
 * @brief Applies common transformations to the input data, such as
 * scaling, mirroring, substracting the image mean...
 */
template <typename Dtype>
class DataTransformer {
 public:
  explicit DataTransformer(const TransformationParameter& param, Phase phase);
  virtual ~DataTransformer() {}

  /**
   * @brief Initialize the Random number generations if needed by the
   *    transformation.
   */
  //初始化随机数种子函数
  void InitRand();

  /**
   * @brief Applies the transformation defined in the data layer's
   * transform_param block to the data.
   *
   * @param datum
   *    Datum containing the data to be transformed.
   * @param transformed_blob
   *    This is destination blob. It can be part of top blob's data if
   *    set_cpu_data() is used. See data_layer.cpp for an example.
   */
  //数据读取层中transform_param块所声明的变换应用到输入数据中。
  //以下为多个重载函数
  void Transform(const Datum& datum, Blob<Dtype>* transformed_blob);

  /**
   * @brief Applies the transformation defined in the data layer's
   * transform_param block to a vector of Datum.
   *
   * @param datum_vector
   *    A vector of Datum containing the data to be transformed.
   * @param transformed_blob
   *    This is destination blob. It can be part of top blob's data if
   *    set_cpu_data() is used. See memory_layer.cpp for an example.
   */
  void Transform(const vector<Datum> & datum_vector,
                Blob<Dtype>* transformed_blob);
//使用OPENCV
#ifdef USE_OPENCV
  /**
   * @brief Applies the transformation defined in the data layer's
   * transform_param block to a vector of Mat.
   *
   * @param mat_vector
   *    A vector of Mat containing the data to be transformed.
   * @param transformed_blob
   *    This is destination blob. It can be part of top blob's data if
   *    set_cpu_data() is used. See memory_layer.cpp for an example.
   */
  void Transform(const vector<cv::Mat> & mat_vector,
                Blob<Dtype>* transformed_blob);

  /**
   * @brief Applies the transformation defined in the data layer's
   * transform_param block to a cv::Mat
   *
   * @param cv_img
   *    cv::Mat containing the data to be transformed.
   * @param transformed_blob
   *    This is destination blob. It can be part of top blob's data if
   *    set_cpu_data() is used. See image_data_layer.cpp for an example.
   */
  void Transform(const cv::Mat& cv_img, Blob<Dtype>* transformed_blob);
#endif  // USE_OPENCV

  /**
   * @brief Applies the same transformation defined in the data layer's
   * transform_param block to all the num images in a input_blob.
   *
   * @param input_blob
   *    A Blob containing the data to be transformed. It applies the same
   *    transformation to all the num images in the blob.
   * @param transformed_blob
   *    This is destination blob, it will contain as many images as the
   *    input blob. It can be part of top blob's data.
   */
  void Transform(Blob<Dtype>* input_blob, Blob<Dtype>* transformed_blob);

  /**
   * @brief Infers the shape of transformed_blob will have when
   *    the transformation is applied to the data.
   *
   * @param datum
   *    Datum containing the data to be transformed.
   */
   //获取执行变换后输出Blob的形状
  vector<int> InferBlobShape(const Datum& datum);
  /**
   * @brief Infers the shape of transformed_blob will have when
   *    the transformation is applied to the data.
   *    It uses the first element to infer the shape of the blob.
   *
   * @param datum_vector
   *    A vector of Datum containing the data to be transformed.
   */
  vector<int> InferBlobShape(const vector<Datum> & datum_vector);
  /**
   * @brief Infers the shape of transformed_blob will have when
   *    the transformation is applied to the data.
   *    It uses the first element to infer the shape of the blob.
   *
   * @param mat_vector
   *    A vector of Mat containing the data to be transformed.
   */
#ifdef USE_OPENCV
  vector<int> InferBlobShape(const vector<cv::Mat> & mat_vector);
  /**
   * @brief Infers the shape of transformed_blob will have when
   *    the transformation is applied to the data.
   *
   * @param cv_img
   *    cv::Mat containing the data to be transformed.
   */
  vector<int> InferBlobShape(const cv::Mat& cv_img);
#endif  // USE_OPENCV

 protected:
   /**
   * @brief Generates a random integer from Uniform({0, 1, ..., n-1}).
   *
   * @param n
   *    The upperbound (exclusive) value of the random number.
   * @return
   *    A uniformly random integer value from ({0, 1, ..., n-1}).
   */
  //产生取值0到n-1的随机整数，服从均匀分布
  virtual int Rand(int n);

  
  void Transform(const Datum& datum, Dtype* transformed_data);
  // Tranformation parameters
  //变换参数，该数据结构由ProtoBuffer工具自动生成
  TransformationParameter param_;

  //随机数生成器。声明在include/caffe/common.hpp中
  shared_ptr<Caffe::RNG> rng_;
  Phase phase_;//当前运行阶段。TRAIN或TEST。阶段不同，变换会有差异
  Blob<Dtype> data_mean_;//均值图像，从均值文件中读取
  vector<Dtype> mean_values_;//均值数值，从param_中提取
};

}  // namespace caffe

#endif  // CAFFE_DATA_TRANSFORMER_HPP_

 src/caffe/data_transformer.cpp

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

#include <string>
#include <vector>

#include "caffe/data_transformer.hpp"
#include "caffe/util/io.hpp"
#include "caffe/util/math_functions.hpp"
#include "caffe/util/rng.hpp"

namespace caffe {

template<typename Dtype>
DataTransformer<Dtype>::DataTransformer(const TransformationParameter& param,
    Phase phase)
    : param_(param), phase_(phase) {//初始化
  // check if we want to use mean_file
  //查看是否使用均值文件
  if (param_.has_mean_file()) {
    //如果param_中指定了均值文件又指定了均值数值则报错，二选一
    CHECK_EQ(param_.mean_value_size(), 0) <<
      "Cannot specify mean_file and mean_value at the same time";
    const string& mean_file = param.mean_file();//获取均值文件名
    if (Caffe::root_solver()) {
      LOG(INFO) << "Loading mean file from: " << mean_file;
    }
    BlobProto blob_proto;//从均值文件中读取数据到blob_proto对象中
    ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);
    data_mean_.FromProto(blob_proto);//从blob_proto将均值反序列化到data_mean_内存中
  }
  // check if we want to use mean_value
  //查看是否使用均值数值
  if (param_.mean_value_size() > 0) {
    CHECK(param_.has_mean_file() == false) <<
      "Cannot specify mean_file and mean_value at the same time";
    for (int c = 0; c < param_.mean_value_size(); ++c) {
        //读取均值数值，不再读取均值文件
      mean_values_.push_back(param_.mean_value(c));
    }
  }
}
//若干重载变换函数
//该函数以Datum作为输入，结构体在caffe.proto中可见。输出为数据指针
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const Datum& datum,
                                       Dtype* transformed_data) {
  //获得datum数据字串、维度信息
  const string& data = datum.data();
  const int datum_channels = datum.channels();
  const int datum_height = datum.height();
  const int datum_width = datum.width();

  //从param_获得处理参数。如切块大小、幅度缩放、随机镜像、图像均值等
  const int crop_size = param_.crop_size();
  const Dtype scale = param_.scale();
  const bool do_mirror = param_.mirror() && Rand(2);
  const bool has_mean_file = param_.has_mean_file();
  const bool has_uint8 = data.size() > 0;
  const bool has_mean_values = mean_values_.size() > 0;

  CHECK_GT(datum_channels, 0);//保证输入通道数大于零
  CHECK_GE(datum_height, crop_size);//保证输入数据的宽和高大于切块尺寸
  CHECK_GE(datum_width, crop_size);

  //获得图像均值
  Dtype* mean = NULL;
  if (has_mean_file) {//若指定了图像均值文件
    //保证图像的均值文件的维度和输入图像数据的维度完全相同
    CHECK_EQ(datum_channels, data_mean_.channels());
    CHECK_EQ(datum_height, data_mean_.height());
    CHECK_EQ(datum_width, data_mean_.width());
    mean = data_mean_.mutable_cpu_data();//获得图像均值数据控制权
  }
  if (has_mean_values) {//未指定图像均值文件，直接给出均值数值
    //保证均值数据维数是1，或与输入图像数据的通道数相同
    CHECK(mean_values_.size() == 1 || mean_values_.size() == datum_channels) <<
     "Specify either 1 mean_value or as many as channels: " << datum_channels;
    if (datum_channels > 1 && mean_values_.size() == 1) {
      // Replicate the mean_value for simplicity
      //如果均值数据维度为1，且输入数据通道数大于1，则重复channels次
      for (int c = 1; c < datum_channels; ++c) {
        mean_values_.push_back(mean_values_[0]);
      }
    }
  }

  //输入图像的宽和高
  int height = datum_height;
  int width = datum_width;

  //开始图像切块
  int h_off = 0;
  int w_off = 0;
  if (crop_size) {//若不为0则进行切块，为0不切块
    height = crop_size;
    width = crop_size;
    // We only do random crop when we do training.
    // 在训练的时候随机crop图像块,这里需要自己实现Rand这个函数来确定是如何随机的
    if (phase_ == TRAIN) {
      h_off = Rand(datum_height - crop_size + 1);// 产生从0到datum_height - crop_size的随机数
      w_off = Rand(datum_width - crop_size + 1);//切块的width偏移量
    } else {//测试阶段只切取图像中心位置
      h_off = (datum_height - crop_size) / 2;
      w_off = (datum_width - crop_size) / 2;
    }
  }

  // 对数据进行变换，主要是将原来的像素值减去均值，然后乘以scale这么一个操作  
  // 如果需要crop则最终转换的Blob的大小即为crop*crop  
  // 如果不是，则最终的Blob大小即为datum_height*datum_width  
  Dtype datum_element;//存放输入图像的像素值
  int top_index, data_index;//分别存放输出index和输入index
  for (int c = 0; c < datum_channels; ++c) {
    for (int h = 0; h < height; ++h) {
      for (int w = 0; w < width; ++w) {
        data_index = (c * datum_height + h_off + h) * datum_width + w_off + w;
        if (do_mirror) {//若需要镜像操作，则输出index时设置width反向
          top_index = (c * height + h) * width + (width - 1 - w);
        } else {
          top_index = (c * height + h) * width + w;
        }
        if (has_uint8) {// Datum中如果是uint8存储图像数据则转换为float
          datum_element =
            static_cast<Dtype>(static_cast<uint8_t>(data[data_index]));
        } else {//否则为float
          datum_element = datum.float_data(data_index);
        }
        if (has_mean_file) {//若指定了均值文件
          transformed_data[top_index] =
            (datum_element - mean[data_index]) * scale;//去均值，幅度缩放
        } else {
          if (has_mean_values) {//若指定了均值数值
            transformed_data[top_index] =
              (datum_element - mean_values_[c]) * scale;//去均值，幅度缩放
          } else {
            transformed_data[top_index] = datum_element * scale;//不去均值，只幅度缩放
          }
        }
      }
    }
  }
}


//与上一个函数类似，只是输出变成blob
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const Datum& datum,
                                       Blob<Dtype>* transformed_blob) {
  // If datum is encoded, decode and transform the cv::image.
  if (datum.encoded()) {//  检查datum是否经过编码的图像，如果是则解码 
#ifdef USE_OPENCV
    // 先检查是不是两个属性都设置， 如果是则说明参数设置有误 
    CHECK(!(param_.force_color() && param_.force_gray()))
        << "cannot set both force_color and force_gray";
    cv::Mat cv_img;
    if (param_.force_color() || param_.force_gray()) {
    // If force_color then decode in color otherwise decode in gray.
    // 如果强制彩色或者强制灰度图像一个成立则使用DecodeDatumToCVMat解码 
      cv_img = DecodeDatumToCVMat(datum, param_.force_color());
    } else {// 否则使用DecodeDatumToCVMatNative解码
      cv_img = DecodeDatumToCVMatNative(datum);
    }
    // Transform the cv::image into blob.将cv::image 变换为 blob
    return Transform(cv_img, transformed_blob);
#else
    LOG(FATAL) << "Encoded datum requires OpenCV; compile with USE_OPENCV.";
#endif  // USE_OPENCV
  } else {// 如果没有编码则检查force_color和force_gray是否设置，如果设置则不合法，因为该选项只适合于编码后的数据 
    if (param_.force_color() || param_.force_gray()) {
      LOG(ERROR) << "force_color and force_gray only for encoded datum";
    }
  }

  const int crop_size = param_.crop_size();
  const int datum_channels = datum.channels();
  const int datum_height = datum.height();
  const int datum_width = datum.width();

  // Check dimensions.检查维度
  const int channels = transformed_blob->channels();
  const int height = transformed_blob->height();
  const int width = transformed_blob->width();
  const int num = transformed_blob->num();

  CHECK_EQ(channels, datum_channels);
  CHECK_LE(height, datum_height);
  CHECK_LE(width, datum_width);
  CHECK_GE(num, 1);

  if (crop_size) {
    CHECK_EQ(crop_size, height);
    CHECK_EQ(crop_size, width);
  } else {
    CHECK_EQ(datum_height, height);
    CHECK_EQ(datum_width, width);
  }
  // 参数变换完毕，调用现有函数
  Dtype* transformed_data = transformed_blob->mutable_cpu_data();
  Transform(datum, transformed_data);
}

//对一组datum数据进行变换
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const vector<Datum> & datum_vector,
                                       Blob<Dtype>* transformed_blob) {
  const int datum_num = datum_vector.size();
  const int num = transformed_blob->num();// 变换到的目标blob的形状
  const int channels = transformed_blob->channels();
  const int height = transformed_blob->height();
  const int width = transformed_blob->width();

  CHECK_GT(datum_num, 0) << "There is no datum to add";
  CHECK_LE(datum_num, num) <<
    "The size of datum_vector must be no greater than transformed_blob->num()";
  Blob<Dtype> uni_blob(1, channels, height, width);// 新建一个uni_blob,里面只有一个batch。临时Blob
  //依次对每一个datum进行变换，放入对应的Blob之中
  for (int item_id = 0; item_id < datum_num; ++item_id) {
    int offset = transformed_blob->offset(item_id);
    uni_blob.set_cpu_data(transformed_blob->mutable_cpu_data() + offset);
    Transform(datum_vector[item_id], &uni_blob);
  }
}

#ifdef USE_OPENCV
//对一组cv::Mat对象进行变换，放入Blob中
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const vector<cv::Mat> & mat_vector,
                                       Blob<Dtype>* transformed_blob) {
  // 获取mat的参数
  const int mat_num = mat_vector.size();
  const int num = transformed_blob->num();
  const int channels = transformed_blob->channels();
  const int height = transformed_blob->height();
  const int width = transformed_blob->width();

  CHECK_GT(mat_num, 0) << "There is no MAT to add";
  CHECK_EQ(mat_num, num) <<
    "The size of mat_vector must be equals to transformed_blob->num()";
  Blob<Dtype> uni_blob(1, channels, height, width);
  for (int item_id = 0; item_id < mat_num; ++item_id) {
    int offset = transformed_blob->offset(item_id);
    uni_blob.set_cpu_data(transformed_blob->mutable_cpu_data() + offset);
    Transform(mat_vector[item_id], &uni_blob);
  }
}
// 对一个cv::Mat对象进行变换，放入Blob中。
// 如果是图像的话，需要减去均值乘以scale，判断是不是需要做镜像处理  
// 逻辑与前面类似 
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const cv::Mat& cv_img,
                                       Blob<Dtype>* transformed_blob) {
  const int crop_size = param_.crop_size();
  const int img_channels = cv_img.channels();
  const int img_height = cv_img.rows;
  const int img_width = cv_img.cols;

  // Check dimensions.检查维度
  const int channels = transformed_blob->channels();
  const int height = transformed_blob->height();
  const int width = transformed_blob->width();
  const int num = transformed_blob->num();

  CHECK_EQ(channels, img_channels);
  CHECK_LE(height, img_height);
  CHECK_LE(width, img_width);
  CHECK_GE(num, 1);

  CHECK(cv_img.depth() == CV_8U) << "Image data type must be unsigned byte";

  const Dtype scale = param_.scale();
  const bool do_mirror = param_.mirror() && Rand(2);
  const bool has_mean_file = param_.has_mean_file();
  const bool has_mean_values = mean_values_.size() > 0;

  CHECK_GT(img_channels, 0);
  CHECK_GE(img_height, crop_size);
  CHECK_GE(img_width, crop_size);

  Dtype* mean = NULL;
  if (has_mean_file) {
    CHECK_EQ(img_channels, data_mean_.channels());
    CHECK_EQ(img_height, data_mean_.height());
    CHECK_EQ(img_width, data_mean_.width());
    mean = data_mean_.mutable_cpu_data();
  }
  if (has_mean_values) {
    CHECK(mean_values_.size() == 1 || mean_values_.size() == img_channels) <<
     "Specify either 1 mean_value or as many as channels: " << img_channels;
    if (img_channels > 1 && mean_values_.size() == 1) {
      // Replicate the mean_value for simplicity 复制均值便于操作
      for (int c = 1; c < img_channels; ++c) {
        mean_values_.push_back(mean_values_[0]);
      }
    }
  }

  int h_off = 0;
  int w_off = 0;
  cv::Mat cv_cropped_img = cv_img;
  if (crop_size) {
    CHECK_EQ(crop_size, height);
    CHECK_EQ(crop_size, width);
    // We only do random crop when we do training.只有训练阶段才随机切块
    if (phase_ == TRAIN) {
      h_off = Rand(img_height - crop_size + 1);
      w_off = Rand(img_width - crop_size + 1);
    } else {
      h_off = (img_height - crop_size) / 2;
      w_off = (img_width - crop_size) / 2;
    }
    cv::Rect roi(w_off, h_off, crop_size, crop_size);
    cv_cropped_img = cv_img(roi);
  } else {
    CHECK_EQ(img_height, height);
    CHECK_EQ(img_width, width);
  }

  CHECK(cv_cropped_img.data);

  Dtype* transformed_data = transformed_blob->mutable_cpu_data();
  int top_index;
  for (int h = 0; h < height; ++h) {
    const uchar* ptr = cv_cropped_img.ptr<uchar>(h);
    int img_index = 0;
    for (int w = 0; w < width; ++w) {
      for (int c = 0; c < img_channels; ++c) {
        if (do_mirror) {
          top_index = (c * height + h) * width + (width - 1 - w);
        } else {
          top_index = (c * height + h) * width + w;
        }
        // int top_index = (c * height + h) * width + w;
        Dtype pixel = static_cast<Dtype>(ptr[img_index++]);
        if (has_mean_file) {
          int mean_index = (c * img_height + h_off + h) * img_width + w_off + w;
          transformed_data[top_index] =
            (pixel - mean[mean_index]) * scale;
        } else {
          if (has_mean_values) {
            transformed_data[top_index] =
              (pixel - mean_values_[c]) * scale;
          } else {
            transformed_data[top_index] = pixel * scale;
          }
        }
      }
    }
  }
}
#endif  // USE_OPENCV

//输入输出都是Blob
template<typename Dtype>
void DataTransformer<Dtype>::Transform(Blob<Dtype>* input_blob,
                                       Blob<Dtype>* transformed_blob) {
  const int crop_size = param_.crop_size();
  const int input_num = input_blob->num();
  const int input_channels = input_blob->channels();
  const int input_height = input_blob->height();
  const int input_width = input_blob->width();

  if (transformed_blob->count() == 0) {
    // Initialize transformed_blob with the right shape.初始化变换后的Blob形状
    if (crop_size) {
      transformed_blob->Reshape(input_num, input_channels,
                                crop_size, crop_size);
    } else {
      transformed_blob->Reshape(input_num, input_channels,
                                input_height, input_width);
    }
  }

  const int num = transformed_blob->num();
  const int channels = transformed_blob->channels();
  const int height = transformed_blob->height();
  const int width = transformed_blob->width();
  const int size = transformed_blob->count();

  CHECK_LE(input_num, num);
  CHECK_EQ(input_channels, channels);
  CHECK_GE(input_height, height);
  CHECK_GE(input_width, width);


  const Dtype scale = param_.scale();
  const bool do_mirror = param_.mirror() && Rand(2);
  const bool has_mean_file = param_.has_mean_file();
  const bool has_mean_values = mean_values_.size() > 0;

  int h_off = 0;
  int w_off = 0;
  if (crop_size) {
    CHECK_EQ(crop_size, height);
    CHECK_EQ(crop_size, width);
    // We only do random crop when we do training.只有训练阶段随机切块
    if (phase_ == TRAIN) {
      h_off = Rand(input_height - crop_size + 1);
      w_off = Rand(input_width - crop_size + 1);
    } else {
      h_off = (input_height - crop_size) / 2;
      w_off = (input_width - crop_size) / 2;
    }
  } else {
    CHECK_EQ(input_height, height);
    CHECK_EQ(input_width, width);
  }

  Dtype* input_data = input_blob->mutable_cpu_data();
  if (has_mean_file) {
    CHECK_EQ(input_channels, data_mean_.channels());
    CHECK_EQ(input_height, data_mean_.height());
    CHECK_EQ(input_width, data_mean_.width());
    for (int n = 0; n < input_num; ++n) {
      int offset = input_blob->offset(n);
      /* 
       template <typename Dtype> 
       void caffe_sub(const int N, const Dtype* a, const Dtype* b, Dtype* y); 
       math_function中定义的caffe_sub目的是矩阵相减input_data（以offset开始的矩阵） = input_data（以offset开始的矩阵） - data_mean_ 
      */
      caffe_sub(data_mean_.count(), input_data + offset,
            data_mean_.cpu_data(), input_data + offset);
    }
  }

  if (has_mean_values) {
    CHECK(mean_values_.size() == 1 || mean_values_.size() == input_channels) <<
     "Specify either 1 mean_value or as many as channels: " << input_channels;
    if (mean_values_.size() == 1) {
      caffe_add_scalar(input_blob->count(), -(mean_values_[0]), input_data);
    } else {
      for (int n = 0; n < input_num; ++n) {
        for (int c = 0; c < input_channels; ++c) {
          int offset = input_blob->offset(n, c);
          // 给input_data[offset]地址开始的每一个元素加上一个-mean_values_[c] 
          caffe_add_scalar(input_height * input_width, -(mean_values_[c]),
            input_data + offset);
        }
      }
    }
  }
  // 如果什么均值都没有则直接复制 
  Dtype* transformed_data = transformed_blob->mutable_cpu_data();

  for (int n = 0; n < input_num; ++n) {
    int top_index_n = n * channels;
    int data_index_n = n * channels;
    for (int c = 0; c < channels; ++c) {
      int top_index_c = (top_index_n + c) * height;
      int data_index_c = (data_index_n + c) * input_height + h_off;
      for (int h = 0; h < height; ++h) {
        int top_index_h = (top_index_c + h) * width;
        int data_index_h = (data_index_c + h) * input_width + w_off;
        if (do_mirror) {
          int top_index_w = top_index_h + width - 1;
          for (int w = 0; w < width; ++w) {
            transformed_data[top_index_w-w] = input_data[data_index_h + w];
          }
        } else {
          for (int w = 0; w < width; ++w) {
            transformed_data[top_index_h + w] = input_data[data_index_h + w];
          }
        }
      }
    }
  }
  if (scale != Dtype(1)) {
    DLOG(INFO) << "Scale: " << scale;
    caffe_scal(size, scale, transformed_data);
  }
}

//获得数据变换输出尺寸
template<typename Dtype>
vector<int> DataTransformer<Dtype>::InferBlobShape(const Datum& datum) {
  if (datum.encoded()) {
#ifdef USE_OPENCV
// 如果使用OpenCV则可以用先转换为CVMat，然后推断blob的形状 
    CHECK(!(param_.force_color() && param_.force_gray()))
        << "cannot set both force_color and force_gray";
    cv::Mat cv_img;
    if (param_.force_color() || param_.force_gray()) {
    // If force_color then decode in color otherwise decode in gray.
      cv_img = DecodeDatumToCVMat(datum, param_.force_color());
    } else {
      cv_img = DecodeDatumToCVMatNative(datum);
    }
    // InferBlobShape using the cv::image.
    return InferBlobShape(cv_img);
#else
    LOG(FATAL) << "Encoded datum requires OpenCV; compile with USE_OPENCV.";
#endif  // USE_OPENCV
  }
  // 否则直接粗暴地从datum里面获取形状的数据 
  const int crop_size = param_.crop_size();
  const int datum_channels = datum.channels();
  const int datum_height = datum.height();
  const int datum_width = datum.width();
  // Check dimensions.检查维度
  CHECK_GT(datum_channels, 0);
  CHECK_GE(datum_height, crop_size);
  CHECK_GE(datum_width, crop_size);
  // Build BlobShape. 创建BlobShape对象
  vector<int> shape(4);
  shape[0] = 1;
  shape[1] = datum_channels;
  shape[2] = (crop_size)? crop_size: datum_height;
  shape[3] = (crop_size)? crop_size: datum_width;
  return shape;
}

template<typename Dtype>
vector<int> DataTransformer<Dtype>::InferBlobShape(
    const vector<Datum> & datum_vector) {
  const int num = datum_vector.size();
  CHECK_GT(num, 0) << "There is no datum to in the vector";
  // Use first datum in the vector to InferBlobShape.使用第一个推断
  vector<int> shape = InferBlobShape(datum_vector[0]);
  // Adjust num to the size of the vector.
  shape[0] = num;
  return shape;
}

#ifdef USE_OPENCV
// 如果使用OpenCV  
// 使用CVMat中的信息来推断形状 
template<typename Dtype>
vector<int> DataTransformer<Dtype>::InferBlobShape(const cv::Mat& cv_img) {
  const int crop_size = param_.crop_size();
  const int img_channels = cv_img.channels();
  const int img_height = cv_img.rows;
  const int img_width = cv_img.cols;
  // Check dimensions.
  CHECK_GT(img_channels, 0);
  CHECK_GE(img_height, crop_size);
  CHECK_GE(img_width, crop_size);
  // Build BlobShape.
  vector<int> shape(4);
  shape[0] = 1;
  shape[1] = img_channels;
  shape[2] = (crop_size)? crop_size: img_height;
  shape[3] = (crop_size)? crop_size: img_width;
  return shape;
}

template<typename Dtype>
vector<int> DataTransformer<Dtype>::InferBlobShape(
    const vector<cv::Mat> & mat_vector) {
  const int num = mat_vector.size();
  CHECK_GT(num, 0) << "There is no cv_img to in the vector";
  // Use first cv_img in the vector to InferBlobShape.
  vector<int> shape = InferBlobShape(mat_vector[0]);
  // Adjust num to the size of the vector.
  shape[0] = num;
  return shape;
}
#endif  // USE_OPENCV

// 初始化随机数种子  
template <typename Dtype>
void DataTransformer<Dtype>::InitRand() {
  // 要么需要镜像要么训练阶段和需要crop同时满足的情况下才初始化随机数种子
  const bool needs_rand = param_.mirror() ||
      (phase_ == TRAIN && param_.crop_size());
  if (needs_rand) {
    const unsigned int rng_seed = caffe_rng_rand();// 获得随机数种子（通过熵池或者时间生成种子）
    rng_.reset(new Caffe::RNG(rng_seed));//初始化随机数种子并实例化随机数生成器 
  } else {
    rng_.reset();//否则随机数生成器设置为空  
  }
}

// 产生从0到n的随机数
template <typename Dtype>
int DataTransformer<Dtype>::Rand(int n) {
  CHECK(rng_);
  CHECK_GT(n, 0);
  caffe::rng_t* rng =
      static_cast<caffe::rng_t*>(rng_->generator());
  return ((*rng)() % n);
}

INSTANTIATE_CLASS(DataTransformer);
/* 
初始化类的宏定义
#define INSTANTIATE_CLASS(classname) \ 
  char gInstantiationGuard##classname; \ 
  template class classname<float>; \ 
  template class classname<double> 
*/  
}  // namespace caffe

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

摘抄参考赵永科《21天实战caffe》

同时参考http://blog.csdn.net/langb2014/article/details/51050213