ictmcg / pref-fend Goto Github PK

Dear Zhang Xue Yao: I am a master student in SEU, and my research derection is in line with yours.Your paper "Pref-FEND"is quite well-wirtten, and I want to reproduce the result in this article. But I can't find the dataset refered in the article .I will appreciate it if you can kindly send me the dataset(including social media posts and relevant articles, named "Weibo Dataset" and "Twitter Dataset").I assure you that the dataset is for academic use only.Thanks so much~!

您好！运行完后在ckpts里的test-res-1-50里保存了很多文件，请问哪个是最终的测试结果呢？

Traceback (most recent call last):
File "main.py", line 158, in
graphs_pattern, graphs_others, nums_nodes)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/cv/ZMD/Pref-FEND-main/model/PrefFEND.py", line 100, in forward
idxs, dataset, tokens_features, map_for_fact_detector=map_entity, map_for_pattern_detector=map_pattern, fcs=self.fcs)
File "/home/cv/ZMD/Pref-FEND-main/model/PrefFEND.py", line 62, in forward_PreferencedDetector
idxs, dataset, tokens_features, map_for_pattern_detector)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/cv/ZMD/Pref-FEND-main/model/PatternBasedModels.py", line 131, in forward
out = self.forward_BERT(idxs, dataset, nodes_tokens, maps=tokened_maps)
File "/home/cv/ZMD/Pref-FEND-main/model/PatternBasedModels.py", line 144, in forward_BERT
seq_output, _ = self.bert(input_ids)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/transformers/modeling_bert.py", line 837, in forward
return_dict=return_dict,
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/transformers/modeling_bert.py", line 492, in forward
output_attentions,
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/transformers/modeling_bert.py", line 412, in forward
output_attentions=output_attentions,
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/transformers/modeling_bert.py", line 349, in forward
output_attentions,
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/transformers/modeling_bert.py", line 250, in forward
mixed_query_layer = self.query(hidden_states)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/linear.py", line 91, in forward
return F.linear(input, self.weight, self.bias)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/functional.py", line 1676, in linear
output = input.matmul(weight.t())
RuntimeError: CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling cublasCreate(handle)

Start training...

Start Training Epoch 0 : 2023-03-25 16:48:34
0%| | 0/2206 [00:01<?, ?it/s]
Traceback (most recent call last):
File "main.py", line 158, in
graphs_pattern, graphs_others, nums_nodes)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/cv/ZMD/Pref-FEND-main/model/PrefFEND.py", line 100, in forward
idxs, dataset, tokens_features, map_for_fact_detector=map_entity, map_for_pattern_detector=map_pattern, fcs=self.fcs)
File "/home/cv/ZMD/Pref-FEND-main/model/PrefFEND.py", line 62, in forward_PreferencedDetector
idxs, dataset, tokens_features, map_for_pattern_detector)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/cv/ZMD/Pref-FEND-main/model/PatternBasedModels.py", line 131, in forward
out = self.forward_BERT(idxs, dataset, nodes_tokens, maps=tokened_maps)
File "/home/cv/ZMD/Pref-FEND-main/model/PatternBasedModels.py", line 163, in forward_BERT
out = self.fc(output)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/modules/linear.py", line 93, in forward
return F.linear(input, self.weight, self.bias)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/torch/nn/functional.py", line 1690, in linear
ret = torch.addmm(bias, input, weight.t())
RuntimeError: mat1 dim 1 must match mat2 dim 0

似乎是bert维度的问题，请问大佬要怎么设置呢

您好！python input_of_emotions.py --dataset 'Weibo' 时提示

No such file or directory: '../../resources/Chinese/大连
理工大学情感词汇本体库/preprocess/words2array.pkl'

FileNotFoundError: [Errno 2] No such file or directory: '../preprocess/BERT_Emo/code/preprocess/data/Twitter/train.npy'

大佬你好！单独的BERT_Emo以及其他不含BERT_Emo的模型组合都可以正常运行，只有BERT_Emo和MAC或者EVIN等组合时会报错，感觉是bert输入问题
==================== Experimental Dataset: Weibo ====================

Start time: 2023-03-25 14:57:35
save path: ckpts/BERT_Emo+DeClarE

Loading model...

Traceback (most recent call last):
File "main.py", line 57, in
model = PrefFEND(args)
File "/home/cv/ZMD/Pref-FEND-main/model/PrefFEND.py", line 29, in init
'{}(args)'.format(args.pattern_based_model))
File "", line 1, in
File "/home/cv/ZMD/Pref-FEND-main/model/PatternBasedModels.py", line 52, in init
args.bert_pretrained_model, return_dict=False)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/transformers/modeling_utils.py", line 853, in from_pretrained
**kwargs,
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/transformers/configuration_utils.py", line 312, in from_pretrained
config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/transformers/configuration_utils.py", line 335, in get_config_dict
if os.path.isdir(pretrained_model_name_or_path):
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/genericpath.py", line 42, in isdir
st = os.stat(s)
TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType

==================== Experimental Dataset: Weibo ====================

Start time: 2023-03-20 22:48:13
save path: ckpts/BERT_Emo+DeClarE_with_Pref-FEND

Loading model...

Traceback (most recent call last):
File "main.py", line 57, in
model = PrefFEND(args)
File "/home/cv/ZMD/Pref-FEND-main/model/PrefFEND.py", line 29, in init
'{}(args)'.format(args.pattern_based_model))
File "", line 1, in
File "/home/cv/ZMD/Pref-FEND-main/model/PatternBasedModels.py", line 52, in init
args.bert_pretrained_model, return_dict=False)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/transformers/modeling_utils.py", line 853, in from_pretrained
**kwargs,
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/transformers/configuration_utils.py", line 312, in from_pretrained
config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/site-packages/transformers/configuration_utils.py", line 335, in get_config_dict
if os.path.isdir(pretrained_model_name_or_path):
File "/home/cv/miniconda3/envs/Zmd/lib/python3.6/genericpath.py", line 42, in isdir
st = os.stat(s)
TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType