main() 실행 시 RuntimeError: Input, output and indices must be on the current device라고 뜨면서 NER수행이 안되는데 혹시 수정할 부분 있을까요 의존성은 requirements.txt대로 깔았습니다 ㅠ
전체 에러문입니다.
`RuntimeError Traceback (most recent call last)
Input In [5], in <cell line: 1>()
----> 1 main()
main() 실행 시 RuntimeError: Input, output and indices must be on the current device라고 뜨면서 NER수행이 안되는데 혹시 수정할 부분 있을까요 의존성은 requirements.txt대로 깔았습니다 ㅠ 전체 에러문입니다. `RuntimeError Traceback (most recent call last) Input In [5], in <cell line: 1>() ----> 1 main()
Input In [3], in main() 45 list_of_input_ids = tokenizer.list_of_string_to_list_of_cls_sep_token_ids([input_text]) 46 x_input = torch.tensor(list_of_input_ids).long() ---> 47 list_of_pred_ids = model(x_input) 49 list_of_ner_word, decoding_ner_sentence = decoder_from_res(list_of_input_ids=list_of_input_ids, list_of_pred_ids=list_of_pred_ids) 50 print("output>", decoding_ner_sentence)
File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/modules/module.py:889, in Module._call_impl(self, *input, kwargs) 887 result = self._slow_forward(*input, *kwargs) 888 else: --> 889 result = self.forward(input, kwargs) 890 for hook in itertools.chain( 891 _global_forward_hooks.values(), 892 self._forward_hooks.values()): 893 hook_result = hook(self, input, result)
File /electra/ner_tagging/pytorch-bert-crf-ner/model/net.py:41, in KobertCRF.forward(self, input_ids, token_type_ids, tags) 38 attention_mask = input_ids.ne(self.vocab.token_to_idx[self.vocab.padding_token]).float() 40 # outputs: (last_encoder_layer, pooled_output, attention_weight) ---> 41 outputs = self.bert(input_ids=input_ids, 42 token_type_ids=token_type_ids, 43 attention_mask=attention_mask) 44 last_encoder_layer = outputs[0] 45 last_encoder_layer = self.dropout(last_encoder_layer)
File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/modules/module.py:889, in Module._call_impl(self, *input, kwargs) 887 result = self._slow_forward(*input, *kwargs) 888 else: --> 889 result = self.forward(input, kwargs) 890 for hook in itertools.chain( 891 _global_forward_hooks.values(), 892 self._forward_hooks.values()): 893 hook_result = hook(self, input, result)
File /electra/ner_tagging/.venv/lib/python3.8/site-packages/pytorch_pretrained_bert/modeling.py:730, in BertModel.forward(self, input_ids, token_type_ids, attention_mask, output_all_encoded_layers) 727 extended_attention_mask = extended_attention_mask.to(dtype=next(self.parameters()).dtype) # fp16 compatibility 728 extended_attention_mask = (1.0 - extended_attention_mask) * -10000.0 --> 730 embedding_output = self.embeddings(input_ids, token_type_ids) 731 encoded_layers = self.encoder(embedding_output, 732 extended_attention_mask, 733 output_all_encoded_layers=output_all_encoded_layers) 734 sequence_output = encoded_layers[-1]
File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/modules/module.py:889, in Module._call_impl(self, *input, kwargs) 887 result = self._slow_forward(*input, *kwargs) 888 else: --> 889 result = self.forward(input, kwargs) 890 for hook in itertools.chain( 891 _global_forward_hooks.values(), 892 self._forward_hooks.values()): 893 hook_result = hook(self, input, result)
File /electra/ner_tagging/.venv/lib/python3.8/site-packages/pytorch_pretrained_bert/modeling.py:267, in BertEmbeddings.forward(self, input_ids, token_type_ids) 264 if token_type_ids is None: 265 token_type_ids = torch.zeros_like(input_ids) --> 267 words_embeddings = self.word_embeddings(input_ids) 268 position_embeddings = self.position_embeddings(position_ids) 269 token_type_embeddings = self.token_type_embeddings(token_type_ids)
File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/modules/module.py:889, in Module._call_impl(self, *input, kwargs) 887 result = self._slow_forward(*input, *kwargs) 888 else: --> 889 result = self.forward(input, kwargs) 890 for hook in itertools.chain( 891 _global_forward_hooks.values(), 892 self._forward_hooks.values()): 893 hook_result = hook(self, input, result)
File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/modules/sparse.py:156, in Embedding.forward(self, input) 155 def forward(self, input: Tensor) -> Tensor: --> 156 return F.embedding( 157 input, self.weight, self.padding_idx, self.max_norm, 158 self.norm_type, self.scale_grad_by_freq, self.sparse)
File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/functional.py:1916, in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse) 1910 # Note [embedding_renorm set_grad_enabled] 1911 # XXX: equivalent to 1912 # with torch.no_grad(): 1913 # torch.embeddingrenorm 1914 # remove once script supports set_grad_enabled 1915 _no_grad_embeddingrenorm(weight, input, max_norm, norm_type) -> 1916 return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Input, output and indices must be on the current device`