h5 does not contain key 'text/bert'

[dafei-qin]

Thanks for sharing the data! I found some annoying errors that might be caused by the data.

When I run this:

from data import Data
from tqdm import tqdm
common_kwargs = dict(path2data = 'data',
                     speaker = ['bee'],
                     modalities = ['pose/data', 'audio/log_mel_512', 'text/bert'],
                     fs_new = [15, 15, 15],
                     batch_size = 4,
                     window_hop = 5)
data = Data(**common_kwargs)

It raises an error below. Seems that the file data/processed/bee/cmu0000025765.h5 does not contain the text/bertpart. By further investigation, I found many of the h5 in bee lost their text/bert part.

G:\PATS\pats\data\dataUtils.py:134: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  self.df = self.df.append(pd.read_csv((Path(self.path2data)/'cmu_intervals_df_transforms.csv').as_posix())) ## file with evil twins
  0%|                                                                                          | 0/576 [00:00<?, ?it/s]
data/processed/bee/cmu0000025765.h5 text/bert
---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
File G:\PATS\pats\data\dataUtils.py:485, in MiniData.__init__(self, path2h5, modalities, fs_new, time, modality_classes, window_hop, style, repeat_text, text_in_modalities, filler, **kwargs)
    484 try:
--> 485   data, h5 = self.load(self.path2h5, modality)
    486 except:

File G:\PATS\pats\data\common.py:39, in HDF5.load(filename, key)
     36 # if key not in h5:
     37 #   print(f"{key} not in P{filename}!")
     38 #   return [], h5
---> 39 data = h5[key]
     40 return data, h5

File h5py\_objects.pyx:54, in h5py._objects.with_phil.wrapper()

File h5py\_objects.pyx:55, in h5py._objects.with_phil.wrapper()

File ~\anaconda3\envs\pats\lib\site-packages\h5py\_hl\group.py:305, in Group.__getitem__(self, name)
    304 elif isinstance(name, (bytes, str)):
--> 305     oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
    306 else:

File h5py\_objects.pyx:54, in h5py._objects.with_phil.wrapper()

File h5py\_objects.pyx:55, in h5py._objects.with_phil.wrapper()

File h5py\h5o.pyx:190, in h5py.h5o.open()

KeyError: 'Unable to open object (component not found)'

During handling of the above exception, another exception occurred:

SystemExit                                Traceback (most recent call last)
    [... skipping hidden 1 frame]

Input In [3], in <cell line: 1>()
----> 1 data = Data(**common_kwargs)



File G:\PATS\pats\data\dataUtils.py:155, in Data.__init__(self, path2data, speaker, modalities, fs_new, time, split, batch_size, shuffle, num_workers, window_hop, load_data, style_iters, num_training_sample, sample_all_styles, repeat_text, quantile_sample, quantile_num_training_sample, weighted, filler, num_training_iters)
    153 #if self.load_data:
    154 ## get train-dev-test split
--> 155 self.datasets = self.tdt_split()
    156 self.dataLoader_kwargs = {'batch_size':batch_size,
    157                           'shuffle':shuffle,
    158                           'num_workers':num_workers,
    159                           'pin_memory':False}

File G:\PATS\pats\data\dataUtils.py:292, in Data.tdt_split(self)
    290 self.test_intervals = test_intervals
--> 292 dataset_train = ConcatDatasetIndex(self.get_minidata_list(train_intervals))
    293 dataset_dev = ConcatDatasetIndex(self.get_minidata_list(dev_intervals))

File G:\PATS\pats\data\dataUtils.py:247, in Data.get_minidata_list(self, intervals)
    246 def get_minidata_list(self, intervals):
--> 247   return [MiniData(self.getPath2file(interval_id), style=self.getStyle(interval_id), **self.minidataKwargs)
    248                                  for interval_id in tqdm(intervals)]

File G:\PATS\pats\data\dataUtils.py:247, in <listcomp>(.0)
    246 def get_minidata_list(self, intervals):
--> 247   return [MiniData(self.getPath2file(interval_id), style=self.getStyle(interval_id), **self.minidataKwargs)
    248                                  for interval_id in tqdm(intervals)]

File G:\PATS\pats\data\dataUtils.py:491, in MiniData.__init__(self, path2h5, modalities, fs_new, time, modality_classes, window_hop, style, repeat_text, text_in_modalities, filler, **kwargs)
    488   # print(f"{modality} not in {self.path2h5}")
    489   # return
--> 491   sys.exit(1)
    493 self.shapes.append(data.shape)

SystemExit: 1

During handling of the above exception, another exception occurred:

AssertionError                            Traceback (most recent call last)
    [... skipping hidden 1 frame]

File ~\anaconda3\envs\pats\lib\site-packages\IPython\core\interactiveshell.py:1972, in InteractiveShell.showtraceback(self, exc_tuple, filename, tb_offset, exception_only, running_compiled_code)
   1969 if exception_only:
   1970     stb = ['An exception has occurred, use %tb to see '
   1971            'the full traceback.\n']
-> 1972     stb.extend(self.InteractiveTB.get_exception_only(etype,
   1973                                                      value))
   1974 else:
   1975     try:
   1976         # Exception classes can customise their traceback - we
   1977         # use this in IPython.parallel for exceptions occurring
   1978         # in the engines. This should return a list of strings.

File ~\anaconda3\envs\pats\lib\site-packages\IPython\core\ultratb.py:578, in ListTB.get_exception_only(self, etype, value)
    570 def get_exception_only(self, etype, value):
    571     """Only print the exception type and message, without a traceback.
    572 
    573     Parameters
   (...)
    576     value : exception value
    577     """
--> 578     return ListTB.structured_traceback(self, etype, value)

File ~\anaconda3\envs\pats\lib\site-packages\IPython\core\ultratb.py:436, in ListTB.structured_traceback(self, etype, evalue, etb, tb_offset, context)
    433     chained_exc_ids.add(id(exception[1]))
    434     chained_exceptions_tb_offset = 0
    435     out_list = (
--> 436         self.structured_traceback(
    437             etype, evalue, (etb, chained_exc_ids),
    438             chained_exceptions_tb_offset, context)
    439         + chained_exception_message
    440         + out_list)
    442 return out_list

File ~\anaconda3\envs\pats\lib\site-packages\IPython\core\ultratb.py:1105, in AutoFormattedTB.structured_traceback(self, etype, value, tb, tb_offset, number_of_lines_of_context)
   1103 else:
   1104     self.tb = tb
-> 1105 return FormattedTB.structured_traceback(
   1106     self, etype, value, tb, tb_offset, number_of_lines_of_context)

File ~\anaconda3\envs\pats\lib\site-packages\IPython\core\ultratb.py:999, in FormattedTB.structured_traceback(self, etype, value, tb, tb_offset, number_of_lines_of_context)
    996 mode = self.mode
    997 if mode in self.verbose_modes:
    998     # Verbose modes need a full traceback
--> 999     return VerboseTB.structured_traceback(
   1000         self, etype, value, tb, tb_offset, number_of_lines_of_context
   1001     )
   1002 elif mode == 'Minimal':
   1003     return ListTB.get_exception_only(self, etype, value)

File ~\anaconda3\envs\pats\lib\site-packages\IPython\core\ultratb.py:852, in VerboseTB.structured_traceback(self, etype, evalue, etb, tb_offset, number_of_lines_of_context)
    850 """Return a nice text document describing the traceback."""
    851 assert etb is not None
--> 852 formatted_exception = self.format_exception_as_a_whole(etype, evalue, etb, number_of_lines_of_context,
    853                                                        tb_offset)
    855 colors = self.Colors  # just a shorthand + quicker name lookup
    856 colorsnormal = colors.Normal  # used a lot

File ~\anaconda3\envs\pats\lib\site-packages\IPython\core\ultratb.py:786, in VerboseTB.format_exception_as_a_whole(self, etype, evalue, etb, number_of_lines_of_context, tb_offset)
    784 assert isinstance(tb_offset, int)
    785 head = self.prepare_header(etype, self.long_header)
--> 786 records = self.get_records(etb, number_of_lines_of_context, tb_offset)
    788 frames = []
    789 skipped = 0

File ~\anaconda3\envs\pats\lib\site-packages\IPython\core\ultratb.py:840, in VerboseTB.get_records(self, etb, number_of_lines_of_context, tb_offset)
    834 options = stack_data.Options(
    835     before=before,
    836     after=after,
    837     pygments_formatter=formatter,
    838 )
    839 assert etb is not None
--> 840 return list(stack_data.FrameInfo.stack_data(etb, options=options))[tb_offset:]

File ~\anaconda3\envs\pats\lib\site-packages\stack_data\core.py:546, in FrameInfo.stack_data(cls, frame_or_tb, options, collapse_repeated_frames)
    530 @classmethod
    531 def stack_data(
    532         cls,
   (...)
    536         collapse_repeated_frames: bool = True
    537 ) -> Iterator[Union['FrameInfo', RepeatedFrames]]:
    538     """
    539     An iterator of FrameInfo and RepeatedFrames objects representing
    540     a full traceback or stack. Similar consecutive frames are collapsed into RepeatedFrames
   (...)
    544     and optionally an Options object to configure.
    545     """
--> 546     stack = list(iter_stack(frame_or_tb))
    548     # Reverse the stack from a frame so that it's in the same order
    549     # as the order from a traceback, which is the order of a printed
    550     # traceback when read top to bottom (most recent call last)
    551     if is_frame(frame_or_tb):

File ~\anaconda3\envs\pats\lib\site-packages\stack_data\utils.py:98, in iter_stack(frame_or_tb)
     96 while frame_or_tb:
     97     yield frame_or_tb
---> 98     if is_frame(frame_or_tb):
     99         frame_or_tb = frame_or_tb.f_back
    100     else:

File ~\anaconda3\envs\pats\lib\site-packages\stack_data\utils.py:91, in is_frame(frame_or_tb)
     90 def is_frame(frame_or_tb: Union[FrameType, TracebackType]) -> bool:
---> 91     assert_(isinstance(frame_or_tb, (types.FrameType, types.TracebackType)))
     92     return isinstance(frame_or_tb, (types.FrameType,))

File ~\anaconda3\envs\pats\lib\site-packages\stack_data\utils.py:172, in assert_(condition, error)
    170 if isinstance(error, str):
    171     error = AssertionError(error)
--> 172 raise error

AssertionError:

[adamhamden]

I believe this may be related to the fact that the missing intervals are somehow not removed from the list of complete intervals. In particular, the following seemed problematic in dataUtils.py.

get_intervals = lambda x: sorted(list(set(x['interval_id'].unique()) - missing_intervals))

[chahuja]

Some of the videos had processing issues, hence we created a posthoc set of interval ids that do not have all the features. All of those are loaded as a variable missing_intervals and excluded from the dataset.