Some exceptions happen when starting the Built-in attack

[QianLongLongLong]

I tried to start the demo code in readme.md, but it seems that some exceptions have happened....

The code is shown as below:

import OpenAttack as oa

choose a trained victim classification model

victim = oa.DataManager.load("Victim.BERT.SST")

choose an evaluation dataset

dataset = oa.DataManager.load("Dataset.SST.sample")

choose Genetic as the attacker and initialize it with default parameters

attacker = oa.attackers.GeneticAttacker()

prepare for attacking

attack_eval = oa.attack_evals.DefaultAttackEval(attacker, victim)

launch attacks and print attack results

attack_eval.eval(dataset, visualize=False)

And the exceptions are as below:

0%| | 0/1000 [00:00<?, ?it/s]C:\Users\13189\Anaconda3\envs\Envtextworld\lib\site-packages\transformers\tokenization_utils_base.py:1770: FutureWarning: The pad_to_max_length argument is deprecated and will be removed in a future version, use padding=True or padding='longest' to pad to the longest sequence in the batch, or use padding='max_length' to pad to a max length. In this case, you can give a specific length with max_length (e.g. max_length=45) or leave max_length to None to pad to the maximal input size of the model (e.g. 512 for Bert).
FutureWarning,
0%| | 0/1000 [00:01<?, ?it/s]
Traceback (most recent call last):
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\site-packages\OpenAttack\data_manager.py", line 73, in load
cls.data_path[data_name]
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\site-packages\OpenAttack\data\nltk_senttokenizer.py", line 17, in LOAD
return import("nltk").data.load(os.path.join(path, "english.pickle")).tokenize
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\site-packages\nltk\data.py", line 752, in load
opened_resource = _open(resource_url)
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\site-packages\nltk\data.py", line 882, in _open
return urlopen(resource_url)
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\urllib\request.py", line 222, in urlopen
return opener.open(url, data, timeout)
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\urllib\request.py", line 525, in open
response = self._open(req, data)
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\urllib\request.py", line 548, in _open
'unknown_open', req)
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\urllib\request.py", line 503, in _call_chain
result = func(*args)
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\urllib\request.py", line 1389, in unknown_open
raise URLError('unknown url type: %s' % type)
urllib.error.URLError:

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "e:\ResearchTraining\openAttack\test.py", line 11, in
attack_eval.eval(dataset, visualize=False)
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\site-packages\OpenAttack\attack_evals\default.py", line 96, in eval
for data, x_adv, y_adv, info in (tqdm(self.eval_results(dataset), total=total_len) if self.__progress_bar else self.eval_results(dataset)):
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\site-packages\tqdm\std.py", line 1129, in iter
for obj in iterable:
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\site-packages\OpenAttack\attack_evals\default.py", line 151, in eval_results
res = self.attacker(self.classifier, data.x, data.target)
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\site-packages\OpenAttack\attackers\genetic.py", line 86, in call
x_orig = self.config["processor"].get_tokens(x_orig)
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\site-packages\OpenAttack\text_processors\default.py", line 37, in get_tokens
self.__tokenize = self.__make_tokenizer( DataManager.load("TProcess.NLTKSentTokenizer") )
File "C:\Users\13189\Anaconda3\envs\Envtextworld\lib\site-packages\OpenAttack\data_manager.py", line 76, in load
raise DataNotExistException(data_name, cls.data_path[data_name])
OpenAttack.exceptions.data_manager.DataNotExistException: ('TProcess.NLTKSentTokenizer', 'E:\ResearchTraining\openAttack\data\TProcess.NLTKSentTokenizer')

Sorry but I don't know how to solve this problem......Please help me. Thank you !

[Cypredar]

Thank you for this question.
We have solved this problem, please check.