A script converting numpy array into leveldb is the easiest solution.
Both @Yangqing' pyleveldb and Russell Power's py-leveldb are good enough for this task.
The conversion can be done in two steps.

// 1. Convert the original data format into datum
bool ReadImageToDatum(const string& filename, const int label,
    const int height, const int width, Datum* datum) {
  cv::Mat cv_img;
  if (height > 0 && width > 0) {
    cv::Mat cv_img_origin = cv::imread(filename, CV_LOAD_IMAGE_COLOR);
    cv::resize(cv_img_origin, cv_img, cv::Size(height, width));
  } else {
    cv_img = cv::imread(filename, CV_LOAD_IMAGE_COLOR);
  }
  if (!cv_img.data) {
    LOG(ERROR) << "Could not open or find file " << filename;
    return false;
  }
  if (height > 0 && width > 0) {

  }
  datum->set_channels(3);
  datum->set_height(cv_img.rows);
  datum->set_width(cv_img.cols);
  datum->set_label(label);
  datum->clear_data();
  datum->clear_float_data();
  string* datum_string = datum->mutable_data();
  for (int c = 0; c < 3; ++c) {
    for (int h = 0; h < cv_img.rows; ++h) {
      for (int w = 0; w < cv_img.cols; ++w) {
        datum_string->push_back(static_cast<char>(cv_img.at<cv::Vec3b>(h, w)[c]));
      }
    }
  }
  return true;
}

// 2. Save the datum
leveldb::WriteBatch* batch = new leveldb::WriteBatch();
datum.SerializeToString(&value);
batch->Put(string(key_cstr), value);

Training a network in python #135

Description

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions