Run on a device without GPU

[MartinChiaHsinLiu]

I had successfully install all dependency for PhenoTagger.
However, my device is old without GPU card supporting.
When I run the example using the given command in README (python PhenoTagger_tagging.py -i ../example/input/ -o ../example/output/)
I get the following error message and I think it is caused by the GPU usage issue.
Consequently, I just wonder weather I can run PhenoTagger using just CPU ?

The error message is as following:

/media/r740/Script/Public_softwares/9.others/PhenoTagger/src/PhenoTagger_tagging.py:35: SyntaxWarning: invalid escape sequence '\|'
  p_title = re.compile('^([0-9]+)\|t\|(.*)$')
/media/r740/Script/Public_softwares/9.others/PhenoTagger/src/PhenoTagger_tagging.py:36: SyntaxWarning: invalid escape sequence '\|'
  p_abstract = re.compile('^([0-9]+)\|a\|(.*)$')
/media/r740/Script/Public_softwares/9.others/PhenoTagger/src/PhenoTagger_tagging.py:235: SyntaxWarning: invalid escape sequence '\|'
  pattern_pubtator = re.compile('^([^\|]+)\|[^\|]+\|(.*)')
2025-01-19 04:23:24.644501: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
2025-01-19 04:23:24.649508: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
2025-01-19 04:23:24.662747: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1737278604.683947 2710561 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1737278604.690330 2710561 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2025-01-19 04:23:32.415721: E external/local_xla/xla/stream_executor/cuda/cuda_driver.cc:152] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: UNKNOWN ERROR (303)
Num GPUs Available:  0
loading dict!
Dic_len: 51201
load dic done!
Traceback (most recent call last):
  File "/media/r740/Script/Public_softwares/9.others/PhenoTagger/src/PhenoTagger_tagging.py", line 278, in <module>
    phenotagger_tag(args.infolder,para_set,args.outfolder)
  File "/media/r740/Script/Public_softwares/9.others/PhenoTagger/src/PhenoTagger_tagging.py", line 213, in phenotagger_tag
    nn_model=bioTag_BERT(vocabfiles)
             ^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/r740/Script/Public_softwares/9.others/PhenoTagger/src/nn_model.py", line 110, in __init__
    self.rep = BERT_RepresentationLayer(self.checkpoint_path, self.label_file, lowercase=self.lowercase)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/r740/Script/Public_softwares/9.others/PhenoTagger/src/nn_represent.py", line 217, in __init__
    self.tokenizer = AutoTokenizer.from_pretrained(tokenizer_name_or_path, use_fast=True,do_lower_case=lowercase)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/anaconda3/envs/NLP_2025/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 871, in from_pretrained
    tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/anaconda3/envs/NLP_2025/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 725, in get_tokenizer_config
    result = json.load(reader)
             ^^^^^^^^^^^^^^^^^
  File "/home/anaconda3/envs/NLP_2025/lib/python3.12/json/__init__.py", line 293, in load
    return loads(fp.read(),
           ^^^^^^^^^^^^^^^^
  File "/home/anaconda3/envs/NLP_2025/lib/python3.12/json/__init__.py", line 346, in loads
    return _default_decoder.decode(s)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/anaconda3/envs/NLP_2025/lib/python3.12/json/decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/anaconda3/envs/NLP_2025/lib/python3.12/json/decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

[lingluodlut]

Hi,
You can run PhenoTagger using only the CPU, but it will process text slowly.
I don't think this error is related to the GPU usage. It seems to be caused by the Python version. You could try installing Python 3.10.