Please try again or make sure your Internet connection is on. about recognize-anything

[lvboodvl]

@yinjiahuidada hello, I meet the same problem, and switch to transformer offine mode as below:
TRANSFORMERS_OFFLINE=1 python inference_ram.py --image images/1641173_2291260800.jpg --pretrained pretrained/ram_swin_large_14m.pth

[lcc815]

@lvboodvl thanks for your solutions, but i still got the following errors following your way

Traceback (most recent call last):
  File "inference_ram.py", line 43, in <module>
    model = ram(pretrained=args.pretrained,
  File "/mnt/csi-data-aly/user/*/recognize-anything/ram/models/ram.py", line 263, in ram
    model = RAM(**kwargs)
  File "/mnt/csi-data-aly/user/*/recognize-anything/ram/models/ram.py", line 103, in __init__
    self.tokenizer = init_tokenizer()
  File "/mnt/csi-data-aly/user/*/recognize-anything/ram/models/utils.py", line 131, in init_tokenizer
    tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
  File "/opt/conda/envs/bevfusion/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 1736, in from_pretrained
    raise EnvironmentError(msg)
OSError: Can't load tokenizer for 'bert-base-uncased'. Make sure that:

- 'bert-base-uncased' is a correct model identifier listed on 'https://huggingface.co/models'
  (make sure 'bert-base-uncased' is not a path to a local directory with something else, in that case)

- or 'bert-base-uncased' is the correct path to a directory containing relevant tokenizer files