Python dataset_util.read_examples_list方法代码示例

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import read_examples_list [as 别名]
def create_records(data_dir, to_path='data/train.tfrecord'):
    annotations_dir, examples_path = get_fun_paths(data_dir)
    writer = tf.python_io.TFRecordWriter(to_path)
    labels = {}
    examples_list = dataset_util.read_examples_list(examples_path)
    assert len(examples_list) > 0, examples_path
    for i, example in enumerate(examples_list):
        path = os.path.join(annotations_dir, example + '.xml')
        data = xml_to_dict(path)
        assert 'object' in data, data['filename']
        labels[i] = [k['name'] for k in data['object']]
        try:
            tf_example = dict_to_tf_example(data, data_dir, label_map_dict)
        except Exception as e: #TODO(SS): remove me
            print(e)
            import pdb; pdb.set_trace()
        writer.write(tf_example.SerializeToString())
    writer.close()
    return labels  # to inspect a bit 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import read_examples_list [as 别名]
def test_read_examples_list(self):
    example_list_data = """example1 1\nexample2 2"""
    example_list_path = os.path.join(self.get_temp_dir(), 'examples.txt')
    with tf.gfile.Open(example_list_path, 'wb') as f:
      f.write(example_list_data)

    examples = dataset_util.read_examples_list(example_list_path)
    self.assertListEqual(['example1', 'example2'], examples) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import read_examples_list [as 别名]
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() 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import read_examples_list [as 别名]
def main(_):
  data_dir = FLAGS.data_dir
  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  logging.info('Reading from Pet dataset.')
  image_dir = os.path.join(data_dir, 'images')
  annotations_dir = os.path.join(data_dir, 'annotations')
  examples_path = os.path.join(annotations_dir, 'trainval.txt')
  examples_list = dataset_util.read_examples_list(examples_path)

  # Test images are not included in the downloaded data set, so we shall perform
  # our own split.
  random.seed(42)
  random.shuffle(examples_list)
  num_examples = len(examples_list)
  num_train = int(0.7 * num_examples)
  train_examples = examples_list[:num_train]
  val_examples = examples_list[num_train:]
  logging.info('%d training and %d validation examples.',
               len(train_examples), len(val_examples))

  train_output_path = os.path.join(FLAGS.output_dir, 'pet_train.record')
  val_output_path = os.path.join(FLAGS.output_dir, 'pet_val.record')
  create_tf_record(train_output_path, label_map_dict, annotations_dir,
                   image_dir, train_examples)
  create_tf_record(val_output_path, label_map_dict, annotations_dir,
                   image_dir, val_examples) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import read_examples_list [as 别名]
def main(_):
  label_map_dict = label_map_util.get_label_map_dict('annotations/label_map.pbtxt')

  logging.info('Reading from Pet dataset.')
  image_dir = 'images'
  annotations_dir = 'annotations'
  examples_path = os.path.join(annotations_dir, 'trainval.txt')
  examples_list = dataset_util.read_examples_list(examples_path)

  # Test images are not included in the downloaded data set, so we shall perform
  # our own split.
  random.seed(42)
  random.shuffle(examples_list)
  num_examples = len(examples_list)
  num_train = int(0.7 * num_examples)
  train_examples = examples_list[:num_train]
  val_examples = examples_list[num_train:]
  logging.info('%d training and %d validation examples.',
               len(train_examples), len(val_examples))

  train_output_path = 'train.record'
  val_output_path = 'val.record'
  create_tf_record(train_output_path, label_map_dict, annotations_dir,
                   image_dir, train_examples)
  create_tf_record(val_output_path, label_map_dict, annotations_dir,
                   image_dir, val_examples) 

# 需要导入模块: from object_detection.utils import dataset_util [as 别名]
# 或者: from object_detection.utils.dataset_util import read_examples_list [as 别名]
def main(_):
  data_dir = FLAGS.data_dir
  label_map_dict = label_map_util.get_label_map_dict(FLAGS.label_map_path)

  logging.info('Reading from Pet dataset.')
  image_dir = os.path.join(data_dir, 'images')
  annotations_dir = os.path.join(data_dir, 'annotations')
  examples_path = os.path.join(annotations_dir, 'trainval.txt')
  examples_list = dataset_util.read_examples_list(examples_path)

  # Test images are not included in the downloaded data set, so we shall perform
  # our own split.
  random.seed(42)
  random.shuffle(examples_list)
  num_examples = len(examples_list)
  num_train = int(0.7 * num_examples)
  train_examples = examples_list[:num_train]
  val_examples = examples_list[num_train:]
  logging.info('%d training and %d validation examples.',
               len(train_examples), len(val_examples))

  train_output_path = os.path.join(FLAGS.output_dir, 'pet_train.record')
  val_output_path = os.path.join(FLAGS.output_dir, 'pet_val.record')
  if FLAGS.faces_only:
    train_output_path = os.path.join(FLAGS.output_dir,
                                     'pet_train_with_masks.record')
    val_output_path = os.path.join(FLAGS.output_dir,
                                   'pet_val_with_masks.record')
  create_tf_record(train_output_path, label_map_dict, annotations_dir,
                   image_dir, train_examples, faces_only=FLAGS.faces_only)
  create_tf_record(val_output_path, label_map_dict, annotations_dir,
                   image_dir, val_examples, faces_only=FLAGS.faces_only)