create_data.sh->creata_annoset.py->convert_annoset.cpp

// This program converts a set of images and annotations to a lmdb/leveldb by
// storing them as AnnotatedDatum proto buffers.
// Usage:
//   convert_annoset [FLAGS] ROOTFOLDER/ LISTFILE DB_NAME
//
// where ROOTFOLDER is the root folder that holds all the images and
// annotations, and LISTFILE should be a list of files as well as their labels
// or label files.
// For classification task, the file should be in the format as
//   imgfolder1/img1.JPEG 7
//   ....
// For detection task, the file should be in the format as
//   imgfolder1/img1.JPEG annofolder1/anno1.xml

这个classification测试可以跑通
detecction要用xml暂时跑不通，因为：
输出结构和他定义的不一致

pretrain####

在imagenet上pretrain,应该用 imgfolder1/img1.JPEG 7

2101538450.jpg

fine-tuning####

在自己的数据集上fine-tuning，应该用annofolder1/anno1.xml

 if (anno_type == "classification") {
      label = boost::get<int>(lines[line_id].second);
      status = ReadImageToDatum(filename, label, resize_height, resize_width,
          min_dim, max_dim, is_color, enc, datum);
    } else if (anno_type == "detection") {
      labelname = root_folder + boost::get<std::string>(lines[line_id].second);
      status = ReadRichImageToAnnotatedDatum(filename, labelname, resize_height,
          resize_width, min_dim, max_dim, is_color, enc, type, label_type,
          name_to_label, &anno_datum);
      anno_datum.set_type(AnnotatedDatum_AnnotationType_BBOX);
    }
    if (status == false) {
      LOG(WARNING) << "Failed to read " << lines[line_id].first;
      continue;
    }
    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;

具体怎么对应网络结构，待续。。。