使用 PyTorch 轉換器訓練 BERT 模型（按照此處的教程進行操作）。教程中的以下聲明loss = model(b_input_ids, token_type_ids=None, attention_mask=b_input_mask, labels=b_labels)導致TypeError: forward() got an unexpected keyword argument 'labels'這是完整的錯誤，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'我似乎無法弄清楚 forward() 函數期望什么樣的參數。這里有一個類似的問題，但我仍然不明白解決方案是什么。
1 回答
湖上湖
TA貢獻2003條經驗 獲得超2個贊
據我所知，BertModel 在函數中不帶標簽forward()。查看forward函數參數。
我懷疑您正在嘗試為序列分類任務微調 BertModel，并且 API 為BertForSequenceClassification提供了一個類。如您所見，它的 forward() 函數定義：
def forward(self, input_ids, attention_mask=None, token_type_ids=None,
position_ids=None, head_mask=None, labels=None):
請注意，forward() 方法返回以下內容。
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.
希望這可以幫助！
添加回答
舉報
0/150
提交
取消