Python object_detection.utils.dataset_util.recursive_parse_xml_to_dict() Examples

The following are 30 code examples of object_detection.utils.dataset_util.recursive_parse_xml_to_dict(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module object_detection.utils.dataset_util , or try the search function .
Example #1
Source File: check_imagenet_data.py    From MBMD with MIT License 5 votes vote down vote up
def main(_):
    data_dir = FLAGS.data_dir

    #writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

    label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

    # logging.info('Reading from Imagenet dataset.')
    examples_list = dataset_util.read_examples_list(FLAGS.data_list_path)
    for idx, example in enumerate(examples_list):
        if idx % 100 == 0:
            print('On image %d of %d'%(idx, len(examples_list)))
            # logging.info('On image %d of %d', idx, len(examples_list))
        path = os.path.join(FLAGS.annotations_dir, example + '.xml')
        with tf.gfile.GFile(path, 'r') as fid:
            xml_str = fid.read()
        xml = etree.fromstring(xml_str)
        data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']
        if not data.has_key('object'):
            continue
        dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
    #    if tf_example is not None:
    #        writer.write(tf_example.SerializeToString())

    #writer.close() 
Example #2
Source File: create_pascal_tf_record.py    From BMW-TensorFlow-Training-GUI with Apache License 2.0 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #3
Source File: create_pascal_tf_record.py    From container_detection with GNU General Public License v3.0 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['cont_train', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',  FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)

      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #4
Source File: build2_tf_record.py    From train_ssd_mobilenet with MIT License 5 votes vote down vote up
def create_tf_record(output_record_file,
                     label_map_dict,
                     jpegfilenames):
    '''Creates a TFRecord file from examples.

    Args:
        output_record_file: Path to where output file is saved.
        label_map_dict: The label map dictionary.
        jpegfilenames: Examples to parse and save to tf record.
    '''
    writer = tf.python_io.TFRecordWriter(output_record_file)
    for idx, example in enumerate(jpegfilenames):
        if idx % 100 == 0:
            logging.info('On image %d of %d', idx, len(jpegfilenames))
        xmlfile = os.path.join(ANNOTATIONS_DIR, example + '.xml')

        if not os.path.exists(xmlfile):
            logging.warning('Could not find %s, ignoring example.', xmlfile)
            continue
        with tf.gfile.GFile(xmlfile, 'r') as fid:
            xml_str = fid.read()
        xml = etree.fromstring(xml_str)
        data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

        tf_example = dict_to_tf_example(data, label_map_dict)
        writer.write(tf_example.SerializeToString())

    writer.close() 
Example #5
Source File: create_pascal_tf_record.py    From moveo_ros with MIT License 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #6
Source File: create_pet_tf_record.py    From moveo_ros with MIT License 5 votes vote down vote up
def create_tf_record(output_filename,
                     label_map_dict,
                     annotations_dir,
                     image_dir,
                     examples):
  """Creates a TFRecord file from examples.

  Args:
    output_filename: Path to where output file is saved.
    label_map_dict: The label map dictionary.
    annotations_dir: Directory where annotation files are stored.
    image_dir: Directory where image files are stored.
    examples: Examples to parse and save to tf record.
  """
  writer = tf.python_io.TFRecordWriter(output_filename)
  for idx, example in enumerate(examples):
    if idx % 100 == 0:
      logging.info('On image %d of %d', idx, len(examples))
    path = os.path.join(annotations_dir, 'xmls', example + '.xml')

    if not os.path.exists(path):
      logging.warning('Could not find %s, ignoring example.', path)
      continue
    with tf.gfile.GFile(path, 'r') as fid:
      xml_str = fid.read()
    xml = etree.fromstring(xml_str)
    data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

    tf_example = dict_to_tf_example(data, label_map_dict, image_dir)
    writer.write(tf_example.SerializeToString())

  writer.close()


# TODO: Add test for pet/PASCAL main files. 
Example #7
Source File: create_knots_tf_record.py    From active-learning-detect with MIT License 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  print("Getting data for {} set".format(FLAGS.set))

  data_dir = FLAGS.data_dir

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  if FLAGS.set == 'trainval':
    examples_list_knot1 = get_examples_list(data_dir, 'knot_', 'train')
    examples_list_knot2 = get_examples_list(data_dir, 'knot_', 'val')
  #print(len(examples_list_knot1), len(examples_list_knot2), len(examples_list_defect1), len(examples_list_defect2))
    examples_list = examples_list_knot1 +  examples_list_knot2 # + examples_list_defect1 + examples_list_defect2
  else:
    examples_list = get_examples_list(data_dir, 'knot_', FLAGS.set)

  print("About to parse {}  examples".format(len(examples_list)))

  annotations_dir = os.path.join(data_dir, FLAGS.annotations_dir)
  for idx, example in enumerate(examples_list):
    if idx % 10 == 0:
      logging.info('On image %d of %d', idx, len(examples_list))
      print('On image {0} of {1}'.format(idx, len(examples_list)))
    path = os.path.join(annotations_dir, example + '.xml')
    with tf.gfile.GFile(path, 'r') as fid:
      xml_str = fid.read()
    xml = etree.fromstring(xml_str)
    data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

    tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                    FLAGS.ignore_difficult_instances)
    writer.write(tf_example.SerializeToString())

  writer.close() 
Example #8
Source File: create_pascal_tf_record.py    From hands-detection with MIT License 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #9
Source File: create_pet_tf_record.py    From hands-detection with MIT License 5 votes vote down vote up
def create_tf_record(output_filename,
                     label_map_dict,
                     annotations_dir,
                     image_dir,
                     examples):
  """Creates a TFRecord file from examples.

  Args:
    output_filename: Path to where output file is saved.
    label_map_dict: The label map dictionary.
    annotations_dir: Directory where annotation files are stored.
    image_dir: Directory where image files are stored.
    examples: Examples to parse and save to tf record.
  """
  writer = tf.python_io.TFRecordWriter(output_filename)
  for idx, example in enumerate(examples):
    if idx % 100 == 0:
      logging.info('On image %d of %d', idx, len(examples))
    path = os.path.join(annotations_dir, 'xmls', example + '.xml')

    if not os.path.exists(path):
      logging.warning('Could not find %s, ignoring example.', path)
      continue
    with tf.gfile.GFile(path, 'r') as fid:
      xml_str = fid.read()
    xml = etree.fromstring(xml_str)
    data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

    tf_example = dict_to_tf_example(data, label_map_dict, image_dir)
    writer.write(tf_example.SerializeToString())

  writer.close()


# TODO: Add test for pet/PASCAL main files. 
Example #10
Source File: create_pascal_tf_record.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #11
Source File: create_pet_tf_record.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up
def create_tf_record(output_filename,
                     label_map_dict,
                     annotations_dir,
                     image_dir,
                     examples):
  """Creates a TFRecord file from examples.

  Args:
    output_filename: Path to where output file is saved.
    label_map_dict: The label map dictionary.
    annotations_dir: Directory where annotation files are stored.
    image_dir: Directory where image files are stored.
    examples: Examples to parse and save to tf record.
  """
  writer = tf.python_io.TFRecordWriter(output_filename)
  for idx, example in enumerate(examples):
    if idx % 100 == 0:
      logging.info('On image %d of %d', idx, len(examples))
    path = os.path.join(annotations_dir, 'xmls', example + '.xml')

    if not os.path.exists(path):
      logging.warning('Could not find %s, ignoring example.', path)
      continue
    with tf.gfile.GFile(path, 'r') as fid:
      xml_str = fid.read()
    xml = etree.fromstring(xml_str)
    data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

    tf_example = dict_to_tf_example(data, label_map_dict, image_dir)
    writer.write(tf_example.SerializeToString())

  writer.close()


# TODO: Add test for pet/PASCAL main files. 
Example #12
Source File: create_dataset.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up
def xml_to_dict(path):
    with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
    xml = etree.fromstring(xml_str)
    return dataset_util.recursive_parse_xml_to_dict(xml)['annotation'] 
Example #13
Source File: create_imagenet_tf_record.py    From MBMD with MIT License 5 votes vote down vote up
def main(_):
    data_dir = FLAGS.data_dir

    writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

    label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

    # logging.info('Reading from Imagenet dataset.')
    examples_list = dataset_util.read_examples_list(FLAGS.data_list_path)
    for idx, example in enumerate(examples_list):
        if idx % 100 == 0:
            print('On image %d of %d'%(idx, len(examples_list)))
            # logging.info('On image %d of %d', idx, len(examples_list))
        path = os.path.join(FLAGS.annotations_dir, example + '.xml')
        with tf.gfile.GFile(path, 'r') as fid:
            xml_str = fid.read()
        xml = etree.fromstring(xml_str)
        data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']
        if not data.has_key('object'):
            continue
        tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
        if tf_example is not None:
            writer.write(tf_example.SerializeToString())

    writer.close() 
Example #14
Source File: create_pet_tf_record.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up
def create_tf_record(output_filename,
                     label_map_dict,
                     annotations_dir,
                     image_dir,
                     examples):
  """Creates a TFRecord file from examples.

  Args:
    output_filename: Path to where output file is saved.
    label_map_dict: The label map dictionary.
    annotations_dir: Directory where annotation files are stored.
    image_dir: Directory where image files are stored.
    examples: Examples to parse and save to tf record.
  """
  writer = tf.python_io.TFRecordWriter(output_filename)
  for idx, example in enumerate(examples):
    if idx % 100 == 0:
      logging.info('On image %d of %d', idx, len(examples))
    path = os.path.join(annotations_dir, 'xmls', example + '.xml')

    if not os.path.exists(path):
      logging.warning('Could not find %s, ignoring example.', path)
      continue
    with tf.gfile.GFile(path, 'r') as fid:
      xml_str = fid.read()
    xml = etree.fromstring(xml_str)
    data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

    tf_example = dict_to_tf_example(data, label_map_dict, image_dir)
    writer.write(tf_example.SerializeToString())

  writer.close()


# TODO: Add test for pet/PASCAL main files. 
Example #15
Source File: create_pascal_tf_record.py    From MBMD with MIT License 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #16
Source File: create_pet_tf_record.py    From MBMD with MIT License 5 votes vote down vote up
def create_tf_record(output_filename,
                     label_map_dict,
                     annotations_dir,
                     image_dir,
                     examples):
  """Creates a TFRecord file from examples.

  Args:
    output_filename: Path to where output file is saved.
    label_map_dict: The label map dictionary.
    annotations_dir: Directory where annotation files are stored.
    image_dir: Directory where image files are stored.
    examples: Examples to parse and save to tf record.
  """
  writer = tf.python_io.TFRecordWriter(output_filename)
  for idx, example in enumerate(examples):
    if idx % 100 == 0:
      logging.info('On image %d of %d', idx, len(examples))
    path = os.path.join(annotations_dir, 'xmls', example + '.xml')

    if not os.path.exists(path):
      logging.warning('Could not find %s, ignoring example.', path)
      continue
    with tf.gfile.GFile(path, 'r') as fid:
      xml_str = fid.read()
    xml = etree.fromstring(xml_str)
    data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

    tf_example = dict_to_tf_example(data, label_map_dict, image_dir)
    writer.write(tf_example.SerializeToString())

  writer.close()


# TODO: Add test for pet/PASCAL main files. 
Example #17
Source File: create_pascal_tf_record.py    From Elphas with Apache License 2.0 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #18
Source File: create_pascal_tf_record.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #19
Source File: create_pet_tf_record.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up
def create_tf_record(output_filename,
                     label_map_dict,
                     annotations_dir,
                     image_dir,
                     examples):
  """Creates a TFRecord file from examples.

  Args:
    output_filename: Path to where output file is saved.
    label_map_dict: The label map dictionary.
    annotations_dir: Directory where annotation files are stored.
    image_dir: Directory where image files are stored.
    examples: Examples to parse and save to tf record.
  """
  writer = tf.python_io.TFRecordWriter(output_filename)
  for idx, example in enumerate(examples):
    if idx % 100 == 0:
      logging.info('On image %d of %d', idx, len(examples))
    path = os.path.join(annotations_dir, 'xmls', example + '.xml')

    if not os.path.exists(path):
      logging.warning('Could not find %s, ignoring example.', path)
      continue
    with tf.gfile.GFile(path, 'r') as fid:
      xml_str = fid.read()
    xml = etree.fromstring(xml_str)
    data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

    tf_example = dict_to_tf_example(data, label_map_dict, image_dir)
    writer.write(tf_example.SerializeToString())

  writer.close()


# TODO: Add test for pet/PASCAL main files. 
Example #20
Source File: create_pascal_tf_record.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #21
Source File: create_pascal_tf_record.py    From MAX-Object-Detector with Apache License 2.0 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #22
Source File: create_pascal_tf_record.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #23
Source File: create_pascal_tf_record.py    From models with Apache License 2.0 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #24
Source File: create_pet_tf_record.py    From mtl-ssl with Apache License 2.0 5 votes vote down vote up
def create_tf_record(output_filename,
                     label_map_dict,
                     annotations_dir,
                     image_dir,
                     examples):
  """Creates a TFRecord file from examples.

  Args:
    output_filename: Path to where output file is saved.
    label_map_dict: The label map dictionary.
    annotations_dir: Directory where annotation files are stored.
    image_dir: Directory where image files are stored.
    examples: Examples to parse and save to tf record.
  """
  writer = tf.python_io.TFRecordWriter(output_filename)
  for idx, example in enumerate(examples):
    if idx % 100 == 0:
      logging.info('On image %d of %d', idx, len(examples))
    path = os.path.join(annotations_dir, 'xmls', example + '.xml')

    if not os.path.exists(path):
      logging.warning('Could not find %s, ignoring example.', path)
      continue
    with tf.gfile.GFile(path, 'r') as fid:
      xml_str = fid.read()
    xml = etree.fromstring(xml_str)
    data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

    tf_example = dict_to_tf_example(data, label_map_dict, image_dir)
    writer.write(tf_example.SerializeToString())

  writer.close()


# TODO: Add test for pet/PASCAL main files. 
Example #25
Source File: create_pascal_tf_record.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #26
Source File: create_pascal_tf_record.py    From ros_tensorflow with Apache License 2.0 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #27
Source File: create_pascal_tf_record.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #28
Source File: create_pascal_tf_record.py    From object_detector_app with MIT License 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close() 
Example #29
Source File: create_pet_tf_record.py    From object_detector_app with MIT License 5 votes vote down vote up
def create_tf_record(output_filename,
                     label_map_dict,
                     annotations_dir,
                     image_dir,
                     examples):
  """Creates a TFRecord file from examples.

  Args:
    output_filename: Path to where output file is saved.
    label_map_dict: The label map dictionary.
    annotations_dir: Directory where annotation files are stored.
    image_dir: Directory where image files are stored.
    examples: Examples to parse and save to tf record.
  """
  writer = tf.python_io.TFRecordWriter(output_filename)
  for idx, example in enumerate(examples):
    if idx % 100 == 0:
      logging.info('On image %d of %d', idx, len(examples))
    path = os.path.join(annotations_dir, 'xmls', example + '.xml')

    if not os.path.exists(path):
      logging.warning('Could not find %s, ignoring example.', path)
      continue
    with tf.gfile.GFile(path, 'r') as fid:
      xml_str = fid.read()
    xml = etree.fromstring(xml_str)
    data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

    tf_example = dict_to_tf_example(data, label_map_dict, image_dir)
    writer.write(tf_example.SerializeToString())

  writer.close()


# TODO: Add test for pet/PASCAL main files. 
Example #30
Source File: create_pascal_tf_record.py    From vehicle_counting_tensorflow with MIT License 5 votes vote down vote up
def main(_):
  if FLAGS.set not in SETS:
    raise ValueError('set must be in : {}'.format(SETS))
  if FLAGS.year not in YEARS:
    raise ValueError('year must be in : {}'.format(YEARS))

  data_dir = FLAGS.data_dir
  years = ['VOC2007', 'VOC2012']
  if FLAGS.year != 'merged':
    years = [FLAGS.year]

  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  for year in years:
    logging.info('Reading from PASCAL %s dataset.', year)
    examples_path = os.path.join(data_dir, year, 'ImageSets', 'Main',
                                 'aeroplane_' + FLAGS.set + '.txt')
    annotations_dir = os.path.join(data_dir, year, FLAGS.annotations_dir)
    examples_list = dataset_util.read_examples_list(examples_path)
    for idx, example in enumerate(examples_list):
      if idx % 100 == 0:
        logging.info('On image %d of %d', idx, len(examples_list))
      path = os.path.join(annotations_dir, example + '.xml')
      with tf.gfile.GFile(path, 'r') as fid:
        xml_str = fid.read()
      xml = etree.fromstring(xml_str)
      data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']

      tf_example = dict_to_tf_example(data, FLAGS.data_dir, label_map_dict,
                                      FLAGS.ignore_difficult_instances)
      writer.write(tf_example.SerializeToString())

  writer.close()