Python object_detection.utils.dataset_util.read_examples_list() Examples

The following are 30 code examples of object_detection.utils.dataset_util.read_examples_list(). 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: create_dataset.py    From object_detection_kitti with Apache License 2.0 6 votes vote down vote up 
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
Example #2
Source File: create_pet_tf_record.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up 
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)
Example #3
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 #4
Source File: create_pet_tf_record.py    From MBMD with MIT License 5 votes vote down vote up 
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)
Example #5
Source File: dataset_util_test.py    From AniSeg with Apache License 2.0 5 votes vote down vote up 
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)
Example #6
Source File: dataset_util_test.py    From MAX-Object-Detector with Apache License 2.0 5 votes vote down vote up 
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)
Example #7
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 #8
Source File: dataset_util_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
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)
Example #9
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 #10
Source File: dataset_util_test.py    From models with Apache License 2.0 5 votes vote down vote up 
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)
Example #11
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 #12
Source File: dataset_util_test.py    From motion-rcnn with MIT License 5 votes vote down vote up 
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)
Example #13
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 #14
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 #15
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 #16
Source File: dataset_util_test.py    From MBMD with MIT License 5 votes vote down vote up 
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)
Example #17
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 #18
Source File: dataset_util_test.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up 
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)
Example #19
Source File: dataset_util_test.py    From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 5 votes vote down vote up 
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)
Example #20
Source File: create_pet_tf_record.py    From hands-detection with MIT License 5 votes vote down vote up 
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)
Example #21
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 #22
Source File: dataset_util_test.py    From hands-detection with MIT License 5 votes vote down vote up 
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)
Example #23
Source File: create_knots_tf_record.py    From active-learning-detect with MIT License 5 votes vote down vote up 
def get_examples_list(data_dir, prefix, setName):
    examples_path = os.path.join(data_dir, 'ImageSets', 'Main',
                                 prefix + setName+ '.txt')
    examples_list = dataset_util.read_examples_list(examples_path)
    return examples_list
Example #24
Source File: create_pet_tf_record.py    From moveo_ros with MIT License 5 votes vote down vote up 
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)
Example #25
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 #26
Source File: dataset_util_test.py    From moveo_ros with MIT License 5 votes vote down vote up 
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)
Example #27
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 #28
Source File: dataset_util_test.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
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)
Example #29
Source File: dataset_util_test.py    From BMW-TensorFlow-Training-GUI with Apache License 2.0 5 votes vote down vote up 
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)
Example #30
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()