CLIC dataset does not load

[isaacdonis]

This was an issue in tfds-nightly and I thought it would be fixed for the official release, but it looks as if there's an ExtractError whenever tfds.load("clic") is ran.

Is this expected?

[Conchylicultor]

Could you share the full logs, stacktrace ?

[isaacdonis]

--------------------------------------------------------------
OutOfRangeError              Traceback (most recent call last)
~\Anaconda3\lib\site-packages\tensorflow_datasets\core\download\extractor.py in _sync_extract(self, from_path, method, to_path)
     87     try:
---> 88       for path, handle in iter_archive(from_path, method):
     89         path = tf.compat.as_text(path)

~\Anaconda3\lib\site-packages\tensorflow_datasets\core\download\extractor.py in iter_zip(arch_f)
    190   with _open_or_pass(arch_f) as fobj:
--> 191     z = zipfile.ZipFile(fobj)
    192     for member in z.infolist():

~\Anaconda3\lib\zipfile.py in __init__(self, file, mode, compression, allowZip64, compresslevel)
   1221             if mode == 'r':
-> 1222                 self._RealGetContents()
   1223             elif mode in ('w', 'x'):

~\Anaconda3\lib\zipfile.py in _RealGetContents(self)
   1284         try:
-> 1285             endrec = _EndRecData(fp)
   1286         except OSError:

~\Anaconda3\lib\zipfile.py in _EndRecData(fpin)
    258     # Determine file size
--> 259     fpin.seek(0, 2)
    260     filesize = fpin.tell()

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\util\deprecation.py in new_func(*args, **kwargs)
    506                 instructions)
--> 507       return func(*args, **kwargs)
    508 

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\lib\io\file_io.py in seek(self, offset, whence, position)
    158     elif whence == 2:
--> 159       offset += self.size()
    160     else:

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\lib\io\file_io.py in size(self)
     96     """Returns the size of the file."""
---> 97     return stat(self.__name).length
     98 

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\lib\io\file_io.py in stat(filename)
    792   """
--> 793   return stat_v2(filename)
    794 

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\lib\io\file_io.py in stat_v2(path)
    808   """
--> 809   return _pywrap_file_io.Stat(path)
    810 

OutOfRangeError: C:\Users\tensorflow_datasets\downloads\data.visi.ee.ethz.ch_cvl_clic_mobi_trai_20EEs08MDPY3lACVToJQa9wD35rhdI-HltMiZMkAAjbtc.zip; Unknown error

During handling of the above exception, another exception occurred:

ExtractError                 Traceback (most recent call last)
<ipython-input-6-dd66274794f1> in <module>
----> 1 ds = tfds.load('clic')

~\Anaconda3\lib\site-packages\tensorflow_datasets\core\load.py in load(name, split, data_dir, batch_size, shuffle_files, download, as_supervised, decoders, read_config, with_info, builder_kwargs, download_and_prepare_kwargs, as_dataset_kwargs, try_gcs)
    342   if download:
    343     download_and_prepare_kwargs = download_and_prepare_kwargs or {}
--> 344     dbuilder.download_and_prepare(**download_and_prepare_kwargs)
    345 
    346   if as_dataset_kwargs is None:

~\Anaconda3\lib\site-packages\tensorflow_datasets\core\dataset_builder.py in download_and_prepare(self, download_dir, download_config)
    385           self._download_and_prepare(
    386               dl_manager=dl_manager,
--> 387               download_config=download_config)
    388 
    389           # NOTE: If modifying the lines below to put additional information in

~\Anaconda3\lib\site-packages\tensorflow_datasets\core\dataset_builder.py in _download_and_prepare(self, dl_manager, download_config)
   1022     super(GeneratorBasedBuilder, self)._download_and_prepare(
   1023         dl_manager=dl_manager,
-> 1024         max_examples_per_split=download_config.max_examples_per_split,
   1025     )
   1026 

~\Anaconda3\lib\site-packages\tensorflow_datasets\core\dataset_builder.py in _download_and_prepare(self, dl_manager, **prepare_split_kwargs)
    960         prepare_split_kwargs)
    961     for split_generator in self._split_generators(
--> 962         dl_manager, **split_generators_kwargs):
    963       if str(split_generator.split_info.name).lower() == "all":
    964         raise ValueError(

~\Anaconda3\lib\site-packages\tensorflow_datasets\image\clic.py in _split_generators(self, dl_manager)
     80         'prof_val': CLIC_PROFESSIONAL_VALIDATION,
     81         'mobile_test': CLIC_MOBILE_TEST,
---> 82         'prof_test': CLIC_PROFESSIONAL_TEST,
     83     })
     84 

~\Anaconda3\lib\site-packages\tensorflow_datasets\core\download\download_manager.py in download_and_extract(self, url_or_urls)
    601     with self._downloader.tqdm():
    602       with self._extractor.tqdm():
--> 603         return _map_promise(self._download_extract, url_or_urls)
    604 
    605   @property

~\Anaconda3\lib\site-packages\tensorflow_datasets\core\download\download_manager.py in _map_promise(map_fn, all_inputs)
    634   """Map the function into each element and resolve the promise."""
    635   all_promises = tf.nest.map_structure(map_fn, all_inputs)  # Apply the function
--> 636   res = tf.nest.map_structure(lambda p: p.get(), all_promises)  # Wait promises
    637   return res

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\util\nest.py in map_structure(func, *structure, **kwargs)
    633 
    634   return pack_sequence_as(
--> 635       structure[0], [func(*x) for x in entries],
    636       expand_composites=expand_composites)
    637 

~\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\util\nest.py in <listcomp>(.0)
    633 
    634   return pack_sequence_as(
--> 635       structure[0], [func(*x) for x in entries],
    636       expand_composites=expand_composites)
    637 

~\Anaconda3\lib\site-packages\tensorflow_datasets\core\download\download_manager.py in <lambda>(p)
    634   """Map the function into each element and resolve the promise."""
    635   all_promises = tf.nest.map_structure(map_fn, all_inputs)  # Apply the function
--> 636   res = tf.nest.map_structure(lambda p: p.get(), all_promises)  # Wait promises
    637   return res

~\Anaconda3\lib\site-packages\promise\promise.py in get(self, timeout)
    510         target = self._target()
    511         self._wait(timeout or DEFAULT_TIMEOUT)
--> 512         return self._target_settled_value(_raise=True)
    513 
    514     def _target_settled_value(self, _raise=False):

~\Anaconda3\lib\site-packages\promise\promise.py in _target_settled_value(self, _raise)
    514     def _target_settled_value(self, _raise=False):
    515         # type: (bool) -> Any
--> 516         return self._target()._settled_value(_raise)
    517 
    518     _value = _reason = _target_settled_value

~\Anaconda3\lib\site-packages\promise\promise.py in _settled_value(self, _raise)
    224             if _raise:
    225                 raise_val = self._fulfillment_handler0
--> 226                 reraise(type(raise_val), raise_val, self._traceback)
    227             return self._fulfillment_handler0
    228 

~\Anaconda3\lib\site-packages\six.py in reraise(tp, value, tb)
    691             if value.__traceback__ is not tb:
    692                 raise value.with_traceback(tb)
--> 693             raise value
    694         finally:
    695             value = None

~\Anaconda3\lib\site-packages\promise\promise.py in handle_future_result(future)
    842         # type: (Any) -> None
    843         try:
--> 844             resolve(future.result())
    845         except Exception as e:
    846             tb = exc_info()[2]

~\Anaconda3\lib\concurrent\futures\_base.py in result(self, timeout)
    423                 raise CancelledError()
    424             elif self._state == FINISHED:
--> 425                 return self.__get_result()
    426 
    427             self._condition.wait(timeout)

~\Anaconda3\lib\concurrent\futures\_base.py in __get_result(self)
    382     def __get_result(self):
    383         if self._exception:
--> 384             raise self._exception
    385         else:
    386             return self._result

~\Anaconda3\lib\concurrent\futures\thread.py in run(self)
     55 
     56         try:
---> 57             result = self.fn(*self.args, **self.kwargs)
     58         except BaseException as exc:
     59             self.future.set_exception(exc)

~\Anaconda3\lib\site-packages\tensorflow_datasets\core\download\extractor.py in _sync_extract(self, from_path, method, to_path)
    101             'https://docs.python.org/3/using/windows.html#removing-the-max-path-limitation'
    102         )
--> 103       raise ExtractError(msg)
    104     # `tf.io.gfile.Rename(overwrite=True)` doesn't work for non empty
    105     # directories, so delete destination first, if it already exists.

ExtractError: Error while extracting C:\Users\tensorflow_datasets\downloads\data.visi.ee.ethz.ch_cvl_clic_mobi_trai_20EEs08MDPY3lACVToJQa9wD35rhdI-HltMiZMkAAjbtc.zip to C:\Users\tensorflow_datasets\downloads\extracted\ZIP.data.visi.ee.ethz.ch_cvl_clic_mobi_trai_20EEs08MDPY3lACVToJQa9wD35rhdI-HltMiZMkAAjbtc.zip (file: None) : C:\Users\tensorflow_datasets\downloads\data.visi.ee.ethz.ch_cvl_clic_mobi_trai_20EEs08MDPY3lACVToJQa9wD35rhdI-HltMiZMkAAjbtc.zip; Unknown error``

[rohit11544]

Can I take this issue?

[vijayphoenix]

Thanks for reporting.
It seems that using tf.io.gfile with python zipfile results in corruption of the data. (For some reason Windows only)
Similar issue #2539

For more info tensorflow/tensorflow#32975