File Deserialization Error during Splitpredict Command Execution with Pretrained Model.

[OthmaneKabal]

Hello there!

I appreciate you taking the time to consider my question amidst your busy schedule. I'm currently attempting to perform inference using your checkpoint (pretrained model). While I can successfully make predictions using the standard predict command (I obtain result without conjunctive sentence resolution), I encounter an error related to file serialization when utilizing the splitpredict command.

(openie6) C:\Users\PC\openie6-master>python run.py --mode splitpredict --inp carb/data/carb_sentences.txt --out models/results/final --rescoring --task oie --gpus 0 --oie_model models/oie_model/epoch=14_eval_acc=0.551_v0.ckpt --conj_model models/conj_model/epoch=28_eval_acc=0.854.ckpt --rescore_model models/rescore_model --num_extractions 5
WARNING:root:This caffe2 python run does not have GPU support. Will run in CPU only mode.
C:\Users\PC\anaconda3\envs\openie6\lib\site-packages\sklearn\utils\deprecation.py:143: FutureWarning: The sklearn.preprocessing.data module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.preprocessing. Anything that cannot be imported from sklearn.preprocessing is now part of the private API.
  warnings.warn(message, FutureWarning)
1282it [00:00, 3498.79it/s]
Traceback (most recent call last):
  File "run.py", line 470, in <module>
    main(hyperparams)
  File "run.py", line 460, in main
    train_dataloader, val_dataloader, test_dataloader, all_sentences)
  File "run.py", line 161, in splitpredict
    model = predict(hparams, None, meta_data_vocab, None, None, test_dataloader, all_sentences)
  File "run.py", line 132, in predict
    loaded_hparams_dict = torch.load(checkpoint_path, map_location=torch.device('cpu'))['hparams']
  File "C:\Users\PC\anaconda3\envs\openie6\lib\site-packages\torch\serialization.py", line 386, in load
    return _load(f, map_location, pickle_module, **pickle_load_args)
  File "C:\Users\PC\anaconda3\envs\openie6\lib\site-packages\torch\serialization.py", line 580, in _load
    deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly)
OSError: [Errno 22] Invalid argument

If you suspect this is an IPython 7.16.1 bug, please report it at:
    https://github.com/ipython/ipython/issues
or send an email to the mailing list at [email protected]

You can print a more detailed traceback right now with "%tb", or use "%debug"
to interactively debug it.

Extra-detailed tracebacks for bug-reporting purposes can be enabled via:
    %config Application.verbose_crash=True