def __init__(self, data_dir, split, headers=True, columns=None, **kwargs):
"""Initializes the reader, allowing to override internal settings.
Arguments:
data_dir: Path to base directory where all the files are
located. See class docstring for a description on the expected
structure.
split: Split to read. Possible values depend on the dataset itself.
headers (boolean): Whether the CSV file has headers indicating
field names, in which case those will be considered.
columns (list or str): Column names for when `headers` is `False`
(i.e. the CSV file has no headers). Will be ignored if
`headers` is `True`.
"""
super(CSVReader, self).__init__(**kwargs)
self._data_dir = data_dir
self._split = split
self._annotations_path = os.path.join(
self._data_dir, '{}.csv'.format(self._split)
)
if not tf.gfile.Exists(self._annotations_path):
raise InvalidDataDirectory(
'CSV annotation file not found. Should be located at '
'`{}`'.format(self._annotations_path)
)
self._images_dir = os.path.join(self._data_dir, self._split)
if not tf.gfile.Exists(self._images_dir):
raise InvalidDataDirectory(
'Image directory not found. Should be located at '
'`{}`'.format(self._images_dir)
)
if columns is not None:
if is_basestring(columns):
columns = columns.split(',')
else:
columns = self.DEFAULT_COLUMNS
self._columns = columns
self._column_names = set(self._columns)
self._has_headers = headers
# Cache for the records.
# TODO: Don't read it all upfront.
self._records = None
# Whether the structure of the CSV file has been checked already.
self._csv_checked = False
self.errors = 0
self.yielded_records = 0
def __init__(self, data_dir, split, columns=DEFAULT_COLUMNS,
field_mapper=FIELD_MAPPER, with_header=False, **kwargs):
super(CSVReader, self).__init__(**kwargs)
self._data_dir = data_dir
self._split = split
self._labels_filename = self._get_labels_filename()
if is_basestring(columns):
columns = columns.split(',')
self._columns = columns
self._field_mapper = field_mapper
self._with_header = with_header
self._files = None
self.errors = 0
self.yielded_records = 0
def __init__(self,
data_dir,
split,
columns=DEFAULT_COLUMNS,
field_mapper=FIELD_MAPPER,
with_header=False,
**kwargs):
super(CSVReader, self).__init__(**kwargs)
self._data_dir = data_dir
self._split = split
self._labels_filename = self._get_labels_filename()
if is_basestring(columns):
columns = columns.split(',')
self._columns = columns
self._field_mapper = field_mapper
self._with_header = with_header
self._files = None
self.errors = 0
self.yielded_records = 0