jupyter实现pytorch版BERT（单标签分类版）
nlp-notebooks/Text classification with BERT in PyTorch.ipynb
通过改写上述代码，实现多标签分类
参考解决方案 ，我选择的解决方案是继承BertForSequenceClassification并改写，即将上述代码的ln [9] 改为以下内容：
python
from transformers.modeling_bert import BertForSequenceClassification
from transformers.modeling_outputs import SequenceClassifierOutput
class BertForMultilabelSequenceClassification(BertForSequenceClassification):
def __init__(self, config):
super().__init__(config)
def forward(self,
input_ids=None,
attention_mask=None,
token_type_ids=None,
position_ids=None,
head_mask=None,
inputs_embeds=None,
labels=None,
output_attentions=None,
output_hidden_states=None,
return_dict=None):
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
outputs = self.bert(input_ids,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
position_ids=position_ids,
head_mask=head_mask,
inputs_embeds=inputs_embeds,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict)
pooled_output = outputs[1]
pooled_output = self.dropout(pooled_output)
logits = self.classifier(pooled_output)
loss = None
if labels is not None:
loss_fct = torch.nn.BCEWithLogitsLoss()
loss = loss_fct(logits.view(-1, self.num_labels),
labels.float().view(-1, self.num_labels))
if not return_dict:
output = (logits,) + outputs[2:]
return ((loss,) + output) if loss is not None else output
return SequenceClassifierOutput(loss=loss,
logits=logits,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions)
model = BertForMultilabelSequenceClassification.from_pretrained(BERT_MODEL, num_labels = len(label2idx))
model.to(device)