PyTorch BERT 类型错误: forward() 函数收到了一个意外的关键字参数 'labels'。

Question

使用PyTorch transformers训练BERT模型（按照此处的教程）。

教程中的以下语句

loss = model(b_input_ids, token_type_ids=None, attention_mask=b_input_mask, labels=b_labels)

导致

TypeError: forward() got an unexpected keyword argument 'labels'

以下是完整的错误信息，

TypeError                                 Traceback (most recent call last)
<ipython-input-53-56aa2f57dcaf> in <module>
     26         optimizer.zero_grad()
     27         # Forward pass
---> 28         loss = model(b_input_ids, token_type_ids=None, attention_mask=b_input_mask, labels=b_labels)
     29         train_loss_set.append(loss.item())
     30         # Backward pass

~/anaconda3/envs/systreviewclassifi/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    539             result = self._slow_forward(*input, **kwargs)
    540         else:
--> 541             result = self.forward(*input, **kwargs)
    542         for hook in self._forward_hooks.values():
    543             hook_result = hook(self, input, result)

TypeError: forward() got an unexpected keyword argument 'labels'

我似乎无法确定forward()函数需要什么样的参数。

这里有一个类似的问题here，但我仍然不明白解决方案是什么。

系统信息：

• 操作系统：Ubuntu 16.04 LTS
• Python版本：3.6.x
• Torch版本：1.3.0
• Torch Vision版本：0.4.1
• PyTorch transformers版本：1.2.0

- Anjani Dhrangadhariya

---

你是怎么定义你的模型的呢？我认为带有“...ForSequenceClassification”后缀的模型可以接受“labels”参数。 - Aswin Candra

@AswinCandra 我使用的是普通的BERT模型，它不接受标签，因为没有这样的参数。 - Anjani Dhrangadhariya

Answer 1

据我所知，BertModel在forward()函数中不接受标签。请查看forward函数参数。

我猜测您正在尝试微调BertModel以进行序列分类任务，而API提供了一个专门用于此类任务的类BertForSequenceClassification。您可以查看它的forward（）函数定义：

def forward(self, input_ids, attention_mask=None, token_type_ids=None,
            position_ids=None, head_mask=None, labels=None):

请注意，forward()方法返回以下内容。

Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
        **loss**: (`optional`, returned when ``labels`` is provided) ``torch.FloatTensor`` of shape ``(1,)``:
            Classification (or regression if config.num_labels==1) loss.
        **logits**: ``torch.FloatTensor`` of shape ``(batch_size, config.num_labels)``
            Classification (or regression if config.num_labels==1) scores (before SoftMax).
        **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
            list of ``torch.FloatTensor`` (one for the output of each layer + the output of the embeddings)
            of shape ``(batch_size, sequence_length, hidden_size)``:
            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        **attentions**: (`optional`, returned when ``config.output_attentions=True``)
            list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. 

希望这能有所帮助！

- Wasi Ahmad