Loading the weights

[aibak365]

I am trying to use the evaluation.py code to make an experiment on my research using an ubuntu machine

but keep facing this error
Traceback (most recent call last):
File "/home/aljadaaa/Documents/Aibak_research_stuff/NSFW (2)/NSFW/Testing/defense/GuardT2I/evaluation.py", line 134, in
clip_model = torch.load("/home/aljadaaa/Documents/Aibak_research_stuff/NSFW (2)/NSFW/Testing/defense/GuardT2I/GuardT2I/clip_model.pt",)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/aljadaaa/Documents/Aibak_research_stuff/NSFW (2)/NSFW/.venv/lib/python3.12/site-packages/torch/serialization.py", line 1494, in load
raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
_pickle.UnpicklingError: Weights only load failed. In PyTorch 2.6, we changed the default value of the weights_only argument in torch.load from False to True. Re-running torch.load with weights_only set to False will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
Please file an issue with the following so that we can make weights_only=True compatible with your use case: WeightsUnpickler error: Unsupported operand 118

Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.

please note that I have tried the weights_only = True and was the same error
and i have tried with false and got the following

Traceback (most recent call last):
File "/home/aljadaaa/Documents/Aibak_research_stuff/NSFW (2)/NSFW/Testing/defense/GuardT2I/evaluation.py", line 134, in
clip_model = torch.load("/home/aljadaaa/Documents/Aibak_research_stuff/NSFW (2)/NSFW/Testing/defense/GuardT2I/GuardT2I/clip_model.pt",weights_only = False)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/aljadaaa/Documents/Aibak_research_stuff/NSFW (2)/NSFW/.venv/lib/python3.12/site-packages/torch/serialization.py", line 1495, in load
return _legacy_load(
^^^^^^^^^^^^^
File "/home/aljadaaa/Documents/Aibak_research_stuff/NSFW (2)/NSFW/.venv/lib/python3.12/site-packages/torch/serialization.py", line 1744, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
_pickle.UnpicklingError: invalid load key, 'v'.

it looks some issues related to the serilization process?
could you please help me to figure it out?

[tomwang777]

got similar problems while loading weights

File "evaluation.py", line 171, in
caption_tokenlized = clip_tokenizer(caption, padding="max_length", max_length=77, return_tensors="pt", truncation=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv\Lib\site-packages\transformers\tokenization_utils_base.py", line 2857, in call
"split_special_tokens": kwargs.pop("split_special_tokens", self.split_special_tokens),
^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv\Lib\site-packages\transformers\tokenization_utils_base.py", line 1108, in getattr
raise AttributeError(f"{self.class.name} has no attribute {key}")
AttributeError: CLIPTokenizer has no attribute split_special_tokens. Did you mean: 'all_special_tokens'?
i changed the attribute but the error still existed

[CheZiLi-rgb]

Hello, may I ask if you have successfully reproduced it?

[CharlesGong12]

Hello, may I ask have you successfully run the code?

[tomwang777]

got similar problems while loading weights

File "evaluation.py", line 171, in caption_tokenlized = clip_tokenizer(caption, padding="max_length", max_length=77, return_tensors="pt", truncation=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File ".venv\Lib\site-packages\transformers\tokenization_utils_base.py", line 2857, in call "split_special_tokens": kwargs.pop("split_special_tokens", self.split_special_tokens), ^^^^^^^^^^^^^^^^^^^^^^^^^ File ".venv\Lib\site-packages\transformers\tokenization_utils_base.py", line 1108, in getattr raise AttributeError(f"{self.class.name} has no attribute {key}") AttributeError: CLIPTokenizer has no attribute split_special_tokens. Did you mean: 'all_special_tokens'? i changed the attribute but the error still existed

successfully ran the code after installing packages according to requirement.txt :)

[Jangorithm]

got similar problems while loading weights
File "evaluation.py", line 171, in caption_tokenlized = clip_tokenizer(caption, padding="max_length", max_length=77, return_tensors="pt", truncation=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File ".venv\Lib\site-packages\transformers\tokenization_utils_base.py", line 2857, in call "split_special_tokens": kwargs.pop("split_special_tokens", self.split_special_tokens), ^^^^^^^^^^^^^^^^^^^^^^^^^ File ".venv\Lib\site-packages\transformers\tokenization_utils_base.py", line 1108, in getattr raise AttributeError(f"{self.class.name} has no attribute {key}") AttributeError: CLIPTokenizer has no attribute split_special_tokens. Did you mean: 'all_special_tokens'? i changed the attribute but the error still existed

successfully ran the code after installing packages according to requirement.txt :)

Thanks for sharing this! 🙏 Would it be possible for you to share the exact package versions you used (e.g., via pip freeze)? It would really help to reproduce the same environment