caffe源碼解讀(7)－data_transformer.cpp

DataTransformer類主要負責對數據進行預處理，比如減去均值、進行crop，鏡像mirror，強制設置爲彩色圖像force_color，強制設置爲灰度圖像force_gray以及像素值的縮放scale，此外該類還將Datum、const vector、cv::Mat&、vector 、Blob*類型的數據變換到目標大小的blob，負責對上述類型的數據推斷其shape。

一.數據結構描述

(1)caffe.proto層參數定義

message TransformationParameter {
  //數據預處理操作：scale、mirror、crop、mean等
  optional float scale = 1 [default = 1];//像素幅度縮放參數
  optional bool mirror = 2 [default = false];//圖像隨機鏡像開關
  optional uint32 crop_size = 3 [default = 0];//隨機切塊
  optional string mean_file = 4;//存取圖像均值的文件
  repeated float mean_value = 5;//均值數值，無需讀取文件。若數目與圖像通道數目相等，則每個通道減去對應均值；如果值給出一個值，每個圖像通道均減去同一個值。
  optional bool force_color = 6 [default = false];//強制爲３通道彩色圖像輸入
  optional bool force_gray = 7 [default = false];//強制爲單通道灰度圖像輸入
}

二.數據變換器聲明

數據變換器聲明頭文件位於include/caffe/caffe_transformer.hpp中，文件內容如下：

#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 {
//DataTransformer類聲明
template <typename Dtype>
class DataTransformer {
 public:
 　//顯式構造函數
  explicit DataTransformer(const TransformationParameter& param, Phase phase);
  virtual ~DataTransformer() {}
  //初始化隨機數種子函數
  void InitRand();
  //以數據讀取層中transform_param塊所聲明的變換應用到輸入數據中
  //函數重載，以適應多種輸入數據源
  void Transform(const Datum& datum, Blob<Dtype>* transformed_blob);
  void Transform(const vector<Datum> & datum_vector,
                Blob<Dtype>* transformed_blob);
  void Transform(const vector<cv::Mat> & mat_vector,
                Blob<Dtype>* transformed_blob);
  void Transform(const cv::Mat& cv_img, Blob<Dtype>* transformed_blob);
  void Transform(Blob<Dtype>* input_blob, Blob<Dtype>* transformed_blob);
  //獲取執行transform後的輸出Blob的形狀
  vector<int> InferBlobShape(const Datum& datum);
  vector<int> InferBlobShape(const vector<Datum> & datum_vector);
  vector<int> InferBlobShape(const vector<cv::Mat> & mat_vector);
  vector<int> InferBlobShape(const cv::Mat& cv_img);

 protected:
 //產生取值｛０，１，...,n-1｝的隨機整數，服從均勻分佈
  virtual int Rand(int n);
  void Transform(const Datum& datum, Dtype* transformed_data);
  // Tranformation parameters
  //變換參數
  TransformationParameter param_;
  //隨機數聲明器，聲明在include/caffe/common.hpp中
  shared_ptr<Caffe::RNG> rng_;
  Phase phase_;
  //均值圖像，用於從均值文件中讀取
  Blob<Dtype> data_mean_;
  //均值數值，用於從param_中提取
  vector<Dtype> mean_values_;
};
}  // namespace caffe
#endif  // CAFFE_DATA_TRANSFORMER_HPP_

三.數據變換器實現

數據變換器的實現文件位於src/caffe/caffe_transformer.cpp中，文件內容如下：

template<typename Dtype>
//構造函數
DataTransformer<Dtype>::DataTransformer(const TransformationParameter& param,
    Phase phase)
    : param_(param), phase_(phase) {//初始化param和phase
  // 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_中既使用了均值文件mean_file又指定了均值數值mean_value則報錯，只能二選一
    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();//獲取均值文件名
    if (Caffe::root_solver()) {
      LOG(INFO) << "Loading mean file from: " << mean_file;
    }
    //從均值文件讀取數據到blob_proto對象中
    BlobProto blob_proto;
    ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);
    //從blob_proto將均值反序列化到data_mean_內存中
    data_mean_.FromProto(blob_proto);
  }
  // check if we want to use mean_value
  //查看是否使用均值數值
  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) {
      mean_values_.push_back(param_.mean_value(c));//從param_中讀取均值數值
    }
  }
}

下面函數使用了Datum作爲輸入，這個結構體的參數定義在caffe.proto中。
Datum是用來從LMDB/LEVELDB中讀取數據，或將數據寫入LMDB/LEVELDB。

message Datum {
　//數據維度信息，channel*height*width
  optional int32 channels = 1;
  optional int32 height = 2;
  optional int32 width = 3;
  //圖像數據，以字節類型存儲
  optional bytes data = 4;
  //標籤數據，統一以int32類型存儲
  optional int32 label = 5;
  //可選，圖像數據也可以float類型存儲
  repeated float float_data = 6;
  //是否爲編碼數據
  optional bool encoded = 7 [default = false];
}

//下面函數輸入爲Datum，輸出爲數據指針
template<typename Dtype>
void DataTransformer<Dtype>::Transform(const Datum& datum,
                                       Dtype* transformed_data) {
  //獲得datum數據字串、維度信息                                 
  const string& data = datum.data();
  const int datum_channels = datum.channels();
  const int datum_height = datum.height();
  const int datum_width = datum.width();
　//從param_獲取處理參數
  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;
　//保證輸入通道數大於０
　//保證輸入數據寬和高大於切塊大小
  CHECK_GT(datum_channels, 0);
  CHECK_GE(datum_height, crop_size);
  CHECK_GE(datum_width, crop_size);

  Dtype* mean = NULL;
  if (has_mean_file) {
  　//若指定了圖像均值文件
  　//需要保證輸入圖像數據的維度和圖像均值的維度完全相同
    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();
  }
  if (has_mean_values) {
  //若給出均值數值
  //保證給出的均值數值爲１，或者是和輸入圖像的通道數目一致
    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) {
    //如果通道數目大於１，只給出１個均值數值，則重複該值channel次，
    //即用每個通道數都減去該均值數值來進行去均值操作
    // Replicate the mean_value for simplicity
      for (int c = 1; c < datum_channels; ++c) {
        mean_values_.push_back(mean_values_[0]);
      }
    }
  }
  //輸入圖像的寬和高
  int height = datum_height;
  int width = datum_width;

  int h_off = 0;
  int w_off = 0;
  if (crop_size) {//crop_size不爲０,則進行crop,若爲０，則不進行crop
    height = crop_size;
    width = crop_size;
    // We only do random crop when we do training.
    if (phase_ == TRAIN) {//訓練階段隨機切塊
      h_off = Rand(datum_height - crop_size + 1);//切塊的height偏移量
      w_off = Rand(datum_width - crop_size + 1);//切塊的width偏移量
    } else {//測試階段只切取圖像中心位置　　
      h_off = (datum_height - crop_size) / 2;
      w_off = (datum_width - crop_size) / 2;
    }
  }

  Dtype datum_element;//存放輸入圖像的像素值
  int top_index, data_index;//分別存放輸出index和輸入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) {//若需要做鏡像，則對輸出index設置width反向
          top_index = (c * height + h) * width + (width - 1 - w);
        } else {
          top_index = (c * height + h) * width + w;
        }
        if (has_uint8) {//若datum中使用uint8存儲圖像數據,需要轉換爲float
          datum_element =
            static_cast<Dtype>(static_cast<uint8_t>(data[data_index]));
        } else {
          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;//執行去均值、幅度縮放
        } else {
          if (has_mean_values) {//若指定了均值數值
            transformed_data[top_index] =
              (datum_element - mean_values_[c]) * scale;//執行去均值、幅度縮放
          } else {
            transformed_data[top_index] = datum_element * scale;//不去均值、只做幅度縮放
          }
        }
      }
    }
  }
}


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()) {//如果datum是經過編碼的圖像，則先解碼
#ifdef USE_OPENCV
　　　//只能強制設置灰度或彩色圖像二選一
    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);
    }
    // Transform the cv::image into blob.
    //將cv_image變換爲blob
    return Transform(cv_img, transformed_blob);
#else
    LOG(FATAL) << "Encoded datum requires OpenCV; compile with USE_OPENCV.";
#endif  // USE_OPENCV
  } else {
    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.
  //檢查維度
  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);
  }

  Dtype* transformed_data = transformed_blob->mutable_cpu_data();
  Transform(datum, transformed_data);//參數變換完畢，調用現有參數
}
//對一組datum進行變換
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();
  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);
  //依次對每個datum進行變換，放入對應的blob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
template<typename Dtype>
//對一組輸入cv::Mat對象進行變換，放入Blob中
void DataTransformer<Dtype>::Transform(const vector<cv::Mat> & mat_vector,
                                       Blob<Dtype>* transformed_blob) {
  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);
  }
}

template<typename Dtype>
//對一個cv::Mat對象進行變換
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.
  //檢查維度
  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
      for (int c = 1; c < img_channels; ++c) {
        mean_values_.push_back(mean_values_[0]);
      }
    }
  }

  int h_off = 0;
  int w_off = 0;
  //用OpenCV實現圖像切塊
  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.
    //只有訓練階段纔會做隨機切塊
    if (phase_ == TRAIN) {
      h_off = Rand(img_height - crop_size + 1);
      w_off = Rand(img_width - crop_size + 1);
    } else {//測試階段做中心切塊
      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

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.
    //初始變換後的blob形狀
    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.
    //只有訓練階段纔會做隨機切塊
    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);
      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);
          caffe_add_scalar(input_height * input_width, -(mean_values_[c]),
            input_data + offset);
        }
      }
    }
  }

  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);
  }
}

template<typename Dtype>
vector<int> DataTransformer<Dtype>::InferBlobShape(const Datum& datum) {
  if (datum.encoded()) {
#ifdef USE_OPENCV
    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
  }
  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.
  CHECK_GT(datum_channels, 0);
  CHECK_GE(datum_height, crop_size);
  CHECK_GE(datum_width, crop_size);
  // Build BlobShape.
  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.
  vector<int> shape = InferBlobShape(datum_vector[0]);
  // Adjust num to the size of the vector.
  shape[0] = num;
  return shape;
}

#ifdef USE_OPENCV
template<typename Dtype>
//獲得數據變換輸出Blob尺寸
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.
  //檢查維度
  CHECK_GT(img_channels, 0);
  CHECK_GE(img_height, crop_size);
  CHECK_GE(img_width, crop_size);
  // Build BlobShape.
  //創建BlobShape對象
  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

template <typename Dtype>
//初始化隨機數種子
//如果在初始化參數中要求對輸入進行隨機鏡像操作或者在訓練階段需要做隨機切塊操作
//那麼需要初始化隨機數種子
void DataTransformer<Dtype>::InitRand() {
  const bool needs_rand = param_.mirror() ||
      (phase_ == TRAIN && param_.crop_size());
  if (needs_rand) {
    const unsigned int rng_seed = caffe_rng_rand();
    rng_.reset(new Caffe::RNG(rng_seed));
  } else {
    rng_.reset();
  }
}

template <typename Dtype>
//生成0~n-1之間的隨機數
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);

}  // namespace caffe