TFDS UnicodeDecodeError stack trace

gistfile1.txt

---------------------------------------------------------------------------
UnicodeDecodeError                        Traceback (most recent call last)
Cell In[10], line 1
----> 1 b = Builder()

File ~\miniconda3\envs\gee\lib\site-packages\tensorflow_datasets\core\logging\__init__.py:289, in builder_init.<locals>.decorator(function, dsbuilder, args, kwargs)
    287 _thread_id_to_builder_init_count[metadata.thread_id] += 1
    288 try:
--> 289   return function(*args, **kwargs)
    290 except Exception:
    291   metadata.mark_error()

File ~\miniconda3\envs\gee\lib\site-packages\tensorflow_datasets\core\dataset_builder.py:1370, in FileReaderBuilder.__init__(self, file_format, **kwargs)
   1353 @tfds_logging.builder_init()
   1354 def __init__(
   1355     self,
   (...)
   1358     **kwargs: Any,
   1359 ):
   1360   """Initializes an instance of FileReaderBuilder.
   1361 
   1362   Callers must pass arguments as keyword arguments.
   (...)
   1368     **kwargs: Arguments passed to `DatasetBuilder`.
   1369   """
-> 1370   super().__init__(**kwargs)
   1371   self.info.set_file_format(file_format)

File ~\miniconda3\envs\gee\lib\site-packages\tensorflow_datasets\core\logging\__init__.py:289, in builder_init.<locals>.decorator(function, dsbuilder, args, kwargs)
    287 _thread_id_to_builder_init_count[metadata.thread_id] += 1
    288 try:
--> 289   return function(*args, **kwargs)
    290 except Exception:
    291   metadata.mark_error()

File ~\miniconda3\envs\gee\lib\site-packages\tensorflow_datasets\core\dataset_builder.py:287, in DatasetBuilder.__init__(self, data_dir, config, version)
    285   self.info.read_from_directory(self._data_dir)
    286 else:  # Use the code version (do not restore data)
--> 287   self.info.initialize_from_bucket()

File ~\miniconda3\envs\gee\lib\site-packages\tensorflow_datasets\core\logging\__init__.py:169, in _FunctionDecorator.__call__(self, function, instance, args, kwargs)
    167 metadata = self._start_call()
    168 try:
--> 169   return function(*args, **kwargs)
    170 except Exception:
    171   metadata.mark_error()

File ~\miniconda3\envs\gee\lib\site-packages\tensorflow_datasets\core\dataset_builder.py:482, in DatasetBuilder.info(self)
    474 if not getattr(self, "_version", None):
    475   # Message for developers creating new dataset. Will trigger if they are
    476   # using .info in the constructor before calling super().__init__
    477   raise AssertionError(
    478       "Info should not been called before version has been defined. "
    479       "Otherwise, the created .info may not match the info version from "
    480       "the restored dataset."
    481   )
--> 482 info = self._info()
    483 if not isinstance(info, dataset_info.DatasetInfo):
    484   raise TypeError(
    485       "DatasetBuilder._info should returns `tfds.core.DatasetInfo`, not "
    486       f" {type(info)}."
    487   )

File project\test\test_dataset_builder.py:17, in Builder._info(self)
     15 """Returns the dataset metadata."""
     16 # TODO(test): Specifies the tfds.core.DatasetInfo object
---> 17 return self.dataset_info_from_configs(
     18     features=tfds.features.FeaturesDict({
     19         # These are the features of your dataset like images, labels ...
     20         'image': tfds.features.Image(shape=(None, None, 3)),
     21         'label': tfds.features.ClassLabel(names=['no', 'yes']),
     22     }),
     23     # If there's a common (input, target) tuple from the
     24     # features, specify them here. They'll be used if
     25     # `as_supervised=True` in `builder.as_dataset`.
     26     supervised_keys=('image', 'label'),  # Set to `None` to disable
     27     homepage='https://dataset-homepage/',
     28 )

File ~\miniconda3\envs\gee\lib\site-packages\tensorflow_datasets\core\dataset_builder.py:1124, in DatasetBuilder.dataset_info_from_configs(self, **kwargs)
   1112 def dataset_info_from_configs(self, **kwargs):
   1113   """Returns the DatasetInfo using given kwargs and config files.
   1114 
   1115   Sub-class should call this and add information not present in config files
   (...)
   1122     **kwargs: kw args to pass to DatasetInfo directly.
   1123   """
-> 1124   metadata = self.get_metadata()
   1125   if metadata.description:
   1126     kwargs["description"] = metadata.description

File ~\miniconda3\envs\gee\lib\site-packages\tensorflow_datasets\core\dataset_builder.py:245, in DatasetBuilder.get_metadata(cls)
    238 @classmethod
    239 def get_metadata(cls) -> dataset_metadata.DatasetMetadata:
    240   """Returns metadata (README, CITATIONS, ...) specified in config files.
    241 
    242   The config files are read from the same package where the DatasetBuilder has
    243   been defined, so those metadata might be wrong for legacy builders.
    244   """
--> 245   return dataset_metadata.load(cls._get_pkg_dir_path())

File ~\miniconda3\envs\gee\lib\site-packages\tensorflow_datasets\core\dataset_metadata.py:81, in load(pkg_path)
     78 @functools.lru_cache(maxsize=256)
     79 def load(pkg_path: epath.Path) -> DatasetMetadata:
     80   """Returns dataset metadata loaded from files in pkg."""
---> 81   raw_metadata = _read_files(pkg_path)
     82   tags = _get_tags(raw_metadata.get(TAGS_FILENAME, ""))
     83   return DatasetMetadata(
     84       description=raw_metadata.get(DESCRIPTIONS_FILENAME, None),
     85       citation=raw_metadata.get(CITATIONS_FILENAME, None),
     86       tags=tags,
     87   )

File ~\miniconda3\envs\gee\lib\site-packages\tensorflow_datasets\core\dataset_metadata.py:104, in _read_files(path)
    102   if inode.name in _METADATA_FILES:
    103     name2path[inode.name] = path.joinpath(inode.name)
--> 104 return etree.parallel_map(lambda f: f.read_text(encoding="utf-8"), name2path)

File ~\miniconda3\envs\gee\lib\site-packages\etils\etree\tree_utils.py:93, in TreeAPI.parallel_map(self, map_fn, num_threads, progress_bar, is_leaf, *trees)
     91   for f in itr:  # Propagate exception to main thread.
     92     if f.exception():
---> 93       raise f.exception()
     95 return self.backend.map(lambda f: f.result(), futures)

File ~\miniconda3\envs\gee\lib\concurrent\futures\thread.py:58, in _WorkItem.run(self)
     55     return
     57 try:
---> 58     result = self.fn(*self.args, **self.kwargs)
     59 except BaseException as exc:
     60     self.future.set_exception(exc)

File ~\miniconda3\envs\gee\lib\site-packages\tensorflow_datasets\core\dataset_metadata.py:104, in _read_files.<locals>.<lambda>(f)
    102   if inode.name in _METADATA_FILES:
    103     name2path[inode.name] = path.joinpath(inode.name)
--> 104 return etree.parallel_map(lambda f: f.read_text(encoding="utf-8"), name2path)

File ~\miniconda3\envs\gee\lib\site-packages\etils\epath\abstract_path.py:157, in Path.read_text(self, encoding)
    155 """Reads contents of self as a string."""
    156 with self.open('r', encoding=encoding) as f:
--> 157   return f.read()

File ~\miniconda3\envs\gee\lib\codecs.py:322, in BufferedIncrementalDecoder.decode(self, input, final)
    319 def decode(self, input, final=False):
    320     # decode input (taking the buffer into account)
    321     data = self.buffer + input
--> 322     (result, consumed) = self._buffer_decode(data, self.errors, final)
    323     # keep undecoded input until the next call
    324     self.buffer = data[consumed:]

UnicodeDecodeError: 'utf-8' codec can't decode byte 0xed in position 4352: invalid continuation byte