daniilsorokin
commented
5 years ago Hi,
sometimes git messes up pickle files, try downloading the models from our server: https://public.ukp.informatik.tu-darmstadt.de/starsem18-entity-linking/FeatureModel_SimplifiedVCG.zip
Daniil
Hi, Maybe the pickle file is not saved properly, could you please have a look at the file?
% python test.py Traceback (most recent call last): File "test.py", line 8, in
entitylinker = core.MLLinker(path_to_model="trainedmodels/FeatureModel_SimplifiedVCG.param")
File "/john/starsem2018-entity-linking/entitylinking/core/ml_entity_linker.py", line 20, in init
self._elmodel.load_from_file(path_to_model)
File "/john/starsem2018-entity-linking/entitylinking/mlearning/models/pytorchmodel.py", line 403, in load_from_file
super(ELModel, self).load_from_file(path_to_model)
File "/john/starsem2018-entity-linking/entitylinking/mlearning/models/pytorchmodel.py", line 162, in load_from_file
self._model.load_state_dict(torch.load(path_to_model))
File "/home/zchen/anaconda3/envs/starsem2018/lib/python3.6/site-packages/torch/serialization.py", line 267, in load
return _load(f, map_location, pickle_module)
File "/home/zchen/anaconda3/envs/starsem2018/lib/python3.6/site-packages/torch/serialization.py", line 410, in _load
magic_number = pickle_module.load(f)
_pickle.UnpicklingError: invalid load key, '{'.
test.py:
coding=utf-8
from entitylinking import core
entitylinker = core.MLLinker(path_to_model="trainedmodels/FeatureModel_Baseline.torchweights")
FeatureModel_SimplifiedVCG.param
entitylinker = core.MLLinker(path_to_model="trainedmodels/FeatureModel_SimplifiedVCG.param")
entitylinker = core.MLLinker(path_to_model="trainedmodels/FeatureModel_Baseline.torchweights")
output = entitylinker.link_entities_in_raw_input("Barack Obama is a president.") print(output.entities)