caffe源码解读(12)-convert_imageset.cpp

$caffe$中允许输入的数据类型可以是$LMDB$或$LEVELDB$，$caffe$中提供了将图片转化为LMDB的工具，位于caffe_dir/tools/convert_imageset.cpp，下面对源码进行简单解析：
主要参考博文caffe，将数据转换为lmdb/leveldb,convert_imageset.cpp 解析

首先是一些参数的设置选项，包括shuffle、resize等

using namespace caffe;  // NOLINT(build/namespaces)
using std::pair;
using boost::scoped_ptr;
//参数选择
DEFINE_bool(gray, false,//将图像作为灰度图像处理，处理后为单通道的
    "When this option is on, treat images as grayscale ones");
DEFINE_bool(shuffle, false,//随机打乱图像及标签
    "Randomly shuffle the order of images and their labels");
DEFINE_string(backend, "lmdb",//数据格式默认为LMDB 
        "The backend {lmdb, leveldb} for storing the result");
DEFINE_int32(resize_width, 0, "Width images are resized to");//图像宽度重置
DEFINE_int32(resize_height, 0, "Height images are resized to");//图像高度重置
DEFINE_bool(check_size, false,//检查所有数据大小一致
    "When this option is on, check that all the datum have the same size");
DEFINE_bool(encoded, false,//是否将已处理图像保存
    "When this option is on, the encoded image will be save in datum");
DEFINE_string(encode_type, "",//图像保存的格式
    "Optional: What type should we encode the image as ('png','jpg',...).");

int main(int argc, char** argv) {
#ifdef USE_OPENCV
  ::google::InitGoogleLogging(argv[0]);//初始化日志
  // Print output to stderr (while still logging)
  FLAGS_alsologtostderr = 1;

#ifndef GFLAGS_GFLAGS_H_
  namespace gflags = google;
#endif

  gflags::SetUsageMessage("Convert a set of images to the leveldb/lmdb\n"
        "format used as input for Caffe.\n"
        "Usage:\n"
        "    convert_imageset [FLAGS] ROOTFOLDER/ LISTFILE DB_NAME\n"
        "The ImageNet dataset for the training demo is at\n"
        "    http://www.image-net.org/download-images\n");
  gflags::ParseCommandLineFlags(&argc, &argv, true);//调用解析命令行函数
//argc，传给main的参数个数
  if (argc < 4) {
    gflags::ShowUsageWithFlagsRestrict(argv[0], "tools/convert_imageset");
    return 1;
  }
　//获取参数信息
  const bool is_color = !FLAGS_gray;
  const bool check_size = FLAGS_check_size;
  const bool encoded = FLAGS_encoded;
  const string encode_type = FLAGS_encode_type;
　//argv[2]为图像的listfile
  std::ifstream infile(argv[2]);
  std::vector<std::pair<std::string, int> > lines;
  std::string line;
  size_t pos;
  int label;
  //存储文件名pos和标签label
  while (std::getline(infile, line)) {
    pos = line.find_last_of(' ');
    label = atoi(line.substr(pos + 1).c_str());
    lines.push_back(std::make_pair(line.substr(0, pos), label));//将每一行的pos和label组成pair数据对存储到lines
  }
  //乱序存储
  if (FLAGS_shuffle) {
    // 随机打乱数据对
    LOG(INFO) << "Shuffling data";
    shuffle(lines.begin(), lines.end());
  }
  LOG(INFO) << "A total of " << lines.size() << " images.";

  if (encode_type.size() && !encoded)
    LOG(INFO) << "encode_type specified, assuming encoded=true.";
　 //设置图像的长度和宽度
  int resize_height = std::max<int>(0, FLAGS_resize_height);
  int resize_width = std::max<int>(0, FLAGS_resize_width);

  // Create new DB
  //argv[3]为db存储位置
  scoped_ptr<db::DB> db(db::GetDB(FLAGS_backend));
  db->Open(argv[3], db::NEW);
  scoped_ptr<db::Transaction> txn(db->NewTransaction());

  // Storing to db
  //argv[1]为图像存储路径
  std::string root_folder(argv[1]);
  Datum datum;
  int count = 0;
  int data_size = 0;
  bool data_size_initialized = false;
　//将数据诸逐个化为lmdb/leveldb
  for (int line_id = 0; line_id < lines.size(); ++line_id) {
    bool status;
    std::string enc = encode_type;
    if (encoded && !enc.size()) {
      // Guess the encoding type from the file name
      string fn = lines[line_id].first;
      size_t p = fn.rfind('.');
      if ( p == fn.npos )
        LOG(WARNING) << "Failed to guess the encoding of '" << fn << "'";
      enc = fn.substr(p);
      std::transform(enc.begin(), enc.end(), enc.begin(), ::tolower);
    }
    //将图像数据读入datum
    status = ReadImageToDatum(root_folder + lines[line_id].first,
        lines[line_id].second, resize_height, resize_width, is_color,
        enc, &datum);
    if (status == false) continue;
    //检查图像尺寸
    if (check_size) {
      if (!data_size_initialized) {
        data_size = datum.channels() * datum.height() * datum.width();
        data_size_initialized = true;
      } else {
        const std::string& data = datum.data();
        CHECK_EQ(data.size(), data_size) << "Incorrect data field size "
            << data.size();
      }
    }
    // sequential
    string key_str = caffe::format_int(line_id, 8) + "_" + lines[line_id].first;

    // Put in db
    string out;
    CHECK(datum.SerializeToString(&out));//datum数据序列化到字符串中
    txn->Put(key_str, out);

    if (++count % 1000 == 0) {
      // Commit db
      txn->Commit();
      txn.reset(db->NewTransaction());
      LOG(INFO) << "Processed " << count << " files.";
    }
  }
  // write the last batch
  if (count % 1000 != 0) {
    txn->Commit();
    LOG(INFO) << "Processed " << count << " files.";
  }
#else
  LOG(FATAL) << "This tool requires OpenCV; compile with USE_OPENCV.";
#endif  // USE_OPENCV
  return 0;
}