yangheng95
PyABSA Version 2 not working- RuntimeError: Exception: expected str, bytes or os.PathLike object, not NoneType Fail to load the model from multilingual!
Version PyABSA version 2.4.1.post1
Describe the bug I have installed PyABSA and tried to run the examples, but I keep getting the error that the Runtime wrror that the model has failed to load. I have tried version 1, and this works, but none of the version 2 packages have worked. How do I go about solving this?
Code To Reproduce pip install -U pyabsa
from pyabsa import AspectTermExtraction as ATEPC, available_checkpoints
you can view all available checkpoints by calling available_checkpoints()
checkpoint_map = available_checkpoints()
aspect_extractor = ATEPC.AspectExtractor('multilingual', auto_device=True, # False means load model on CPU cal_perplexity=True, )
instance inference
aspect_extractor.predict(['I love this movie, it is so great!'], save_result=True, print_result=True, # print the result ignore_error=True, # ignore the error when the model cannot predict the input )
inference_source = ATEPC.ATEPCDatasetList.Restaurant16 atepc_result = aspect_extractor.batch_predict(target_file=inference_source, # save_result=True, print_result=True, # print the result pred_sentiment=True, # Predict the sentiment of extracted aspect terms )
print(atepc_result)
Expected behavior This was expected to run and provide the sentiment classifications, but when run, the execution always fails with this error:
RuntimeError: Exception: expected str, bytes or os.PathLike object, not NoneType Fail to load the model from multilingual! File /local_disk0/.ephemeral_nfs/envs/pythonEnv-b49d82e8-1a51-4577-a57e-bdaccd63c848/lib/python3.10/site-packages/pyabsa/tasks/AspectTermExtraction/prediction/aspect_extractor.py:82, in AspectExtractor.init(self, checkpoint, **kwargs) 80 fprint("tokenizer: {}".format(tokenizer_path)) ---> 82 with open(config_path, mode="rb") as f: 83 self.config = pickle.load(f) File /local_disk0/.ephemeral_nfs/envs/pythonEnv-b49d82e8-1a51-4577-a57e-bdaccd63c848/lib/python3.10/site-packages/pyabsa/tasks/AspectTermExtraction/prediction/aspect_extractor.py:131, in AspectExtractor.init(self, checkpoint, **kwargs) 128 self.tokenizer = pickle.load(f) 130 except Exception as e: --> 131 raise RuntimeError( 132 "Exception: {} Fail to load the model from {}! ".format( 133 e, self.checkpoint 134 ) 135 ) 137 if not hasattr(ATEPCModelList, self.model.class.name): 138 raise KeyError( 139 "The checkpoint you are loading is not from any ATEPC model." 140 )
I have tried a number of things, including downloading the checkpoint, but I'm now not sure how to get this to work.
