LittleGuoKe / ConceptFERE

This code is the source code of our paper "Entity Concept-enhanced Few-shot Relation Extraction" in the ACL2021
MIT License
32 stars 9 forks source link

apex的版本不适配,不知道您的版本是? #3

Closed BunnyNLP closed 2 years ago

BunnyNLP commented 2 years ago

Traceback (most recent call last): File "train_demo.py", line 370, in main() File "train_demo.py", line 327, in main model = Pair(sentence_encoder, hidden_size=opt.hidden_size)#入口 models/pair.py -> Pair File "/root/workspace/czb/ConceptFERE/fewshot_re_kit/framework.py", line 212, in train logits, pred = model(batch, N_for_train, K, File "/root/miniconda3/envs/czb_KnowPrompt/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, kwargs) File "/root/workspace/czb/ConceptFERE/models/pair.py", line 26, in forward logits = self.sentence_encoder(batch) File "/root/miniconda3/envs/czb_KnowPrompt/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, *kwargs) File "/root/miniconda3/envs/czb_KnowPrompt/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 166, in forward return self.module(inputs[0], kwargs[0]) File "/root/miniconda3/envs/czb_KnowPrompt/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, *kwargs) File "/root/workspace/czb/ConceptFERE/fewshot_re_kit/sentence_encoder.py", line 488, in forward quer_sen_hava_cpt = self.sentence_have_concept(query_sen, queryConceptID) File "/root/workspace/czb/ConceptFERE/fewshot_re_kit/sentence_encoder.py", line 585, in sentence_have_concept sen_vec = self.projector2(sen_vec) File "/root/miniconda3/envs/czb_KnowPrompt/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(input, **kwargs) File "/root/miniconda3/envs/czb_KnowPrompt/lib/python3.8/site-packages/torch/nn/modules/linear.py", line 103, in forward return F.linear(input, self.weight, self.bias) File "/root/miniconda3/envs/czb_KnowPrompt/lib/python3.8/site-packages/apex/amp/wrap.py", line 21, in wrapper args[i] = utils.cached_cast(cast_fn, args[i], handle.cache) File "/root/miniconda3/envs/czb_KnowPrompt/lib/python3.8/site-packages/apex/amp/utils.py", line 97, in cached_cast if cached_x.grad_fn.next_functions[1][0].variable is not x: IndexError: tuple index out of range

LittleGuoKe commented 2 years ago

谢谢你关注我的工作,apex的版本以及其它库的版本号可以看根目录下的environment.yml文件。你可以执行conda env create -f environment.yml安装项目需要的所有的依赖库。 五一快乐呀!

LittleGuoKe commented 2 years ago

代码我更新了sentence encoder文件模型的性能会和论文一致,你可以重新下载运行

BunnyNLP commented 2 years ago

由于environment.yml中没有涉及apex的版本信息,所以我修改了运行参数已经能正常运行~非常感谢您的回复,祝你假期愉快哦~