search

Maluuba / nlg-eval

Evaluation code for various unsupervised automated metrics for Natural Language Generation.
http://arxiv.org/abs/1706.09799
Other
1.35k stars 224 forks source link

_pickle.UnpicklingError: pickle data was truncated #73

Closed kangkang59812 closed 5 years ago

kangkang59812 commented 5 years ago

python3.6

from nlgeval import NLGEval nlgeval = NLGEval() Traceback (most recent call last): File "", line 1, in File "/home/lkk/code/caption_v1/nlgeval/nlgeval/init.py", line 192, in init self.load_skipthought_model() File "/home/lkk/code/caption_v1/nlgeval/nlgeval/init.py", line 226, in load_skipthought_model model = skipthoughts.load_model() File "/home/lkk/code/caption_v1/nlgeval/nlgeval/skipthoughts/skipthoughts.py", line 59, in load_model utable, btable = load_tables() File "/home/lkk/code/caption_v1/nlgeval/nlgeval/skipthoughts/skipthoughts.py", line 79, in load_tables utable = numpy.load(os.path.join(path_to_tables, 'utable.npy'), allow_pickle=True, encoding='bytes') File "/home/lkk/anaconda3/lib/python3.6/site-packages/numpy/lib/npyio.py", line 433, in load pickle_kwargs=pickle_kwargs) File "/home/lkk/anaconda3/lib/python3.6/site-packages/numpy/lib/format.py", line 657, in read_array array = pickle.load(fp, **pickle_kwargs) _pickle.UnpicklingError: pickle data was truncated

juharris commented 5 years ago

Possible duplicate of https://github.com/Maluuba/nlg-eval/issues/60 Basically it seems like some files may not have finished downloading. You can check #60 for the correct file sizes and which file(s) you can try to delete and re-download. The easiest way to re-download the files is to manually delete them and then re-run the setup.