make_predictions TypeError on preprocessed data

[clsteel]

I successfully pre-processed all my data and have the directories of h5 files, but when attempting to run the make_predictions.py script it partially processes one file and then throws this error:

Traceback (most recent call last):
  File "/.conda/envs/deep_postures_pytorch/lib/python3.11/site-packages/numpy/lib/_shape_base_impl.py", line 872, in split
    len(indices_or_sections)
TypeError: object of type 'int' has no len()

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "DeepPostures/MSSE-2021/make_predictions.py", line 323, in <module>
    generate_predictions(args.pre_processed_dir, output_dir=args.predictions_dir, model=args.model, segment=not args.no_segment, output_label=args.output_label,
  File "DeepPostures/MSSE-2021/make_predictions.py", line 141, in generate_predictions
    reshaped_subject_data = np.split(subject_data, subject_data.shape[0]//bi_lstm_win_size)
                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".conda/envs/deep_postures_pytorch/lib/python3.11/site-packages/numpy/lib/_shape_base_impl.py", line 876, in split
    if N % sections:
       ~~^~~~~~~~~~
ZeroDivisionError: integer modulo by zero

I don't know fully how to interact with the h5 files to try to troubleshoot this. Thanks very much for any assistance!