search

nusnlp / crosentgec

Code for cross-sentence grammatical error correction using multilayer convolutional seq2seq models (ACL 2019)
GNU General Public License v3.0
50 stars 12 forks source link

Decode development/test sets issues #5

Closed pidugusundeep closed 4 years ago

pidugusundeep commented 4 years ago

./decode.sh conll13st-test models/bpe/mlconvgec_aaai18_bpe.model models/dicts This is the error

Traceback (most recent call last):
  File "fairseq/interactive_multi.py", line 195, in <module>
    main(args)
  File "fairseq/interactive_multi.py", line 102, in main
    models, model_args = utils.load_ensemble_for_inference(model_paths, task)
  File "/home/liferay172/Documents/SundeepPidugu/crosentgec/fairseq/fairseq/utils.py", line 153, in load_ensemble_for_inference
    state = torch.load(filename, map_location=lambda s, l: default_restore_location(s, 'cpu'))
  File "/home/liferay172/anaconda3/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
    return _load(f, map_location, pickle_module, **pickle_load_args)
  File "/home/liferay172/anaconda3/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
    magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: could not find MARK

Please let me know if iam passing the parameters correctly and providing an example is much appreciated.

pidugusundeep commented 4 years ago

I was providing the wrong model directory. the correct path would be something similar to below. ./decode.sh conll13st-test models/crosent/model1 models/dicts