'bert-base-multilingual-uncased'数据加载器RuntimeError：堆栈期望每个张量相等

如何解决'bert-base-multilingual-uncased'数据加载器RuntimeError：堆栈期望每个张量相等

我是nlp的初学者，因为我参加了比赛https://www.kaggle.com/c/contradictory-my-dear-watson，我正在使用模型'bert-base-multilingual-uncased'，并且使用同一模型中的BERT标记器。我也在使用kaggle tpu。这是我创建的自定义数据加载器。

class SherlockDataset(torch.utils.data.Dataset):

def __init__(self,premise,hypothesis,tokenizer,max_len,target = None):
    super(SherlockDataset,self).__init__()
    self.premise = premise
    self.hypothesis = hypothesis
    self.tokenizer = tokenizer
    self.max_len = max_len
    self.target = target

def __len__(self):
    return len(self.premise)

def __getitem__(self,item):
    sen1 = str(self.premise[item])
    sen2 = str(self.hypothesis[item])
    
    encode_dict = self.tokenizer.encode_plus(sen1,sen2,add_special_tokens = True,max_len = self.max_len,pad_to_max_len = True,return_attention_mask = True,return_tensors = 'pt'
                                       )
    input_ids = encode_dict["input_ids"][0]
    token_type_ids = encode_dict["token_type_ids"][0]
    att_mask = encode_dict["attention_mask"][0]
    
    if self.target is not None:
        sample = {
        "input_ids":input_ids,"token_type_ids":token_type_ids,"att_mask":att_mask,"targets": self.target[item]
        }
    else:
        sample = {
        "input_ids":input_ids,"att_mask":att_mask
        }
    
    return sample

以及在将数据加载到数据加载器的过程中

def train_fn(model,dataloader,optimizer,criterion,scheduler = None):
model.train()
print("train")
for idx,sample in enumerate(dataloader):
    '''
    input_ids = sample["input_ids"].to(config.DEVICE)
    token_type_ids = sample["token_type_ids"].to(config.DEVICE)
    att_mask = sample["att_mask"].to(config.DEVICE)
    targets = sample["targets"].to(config.DEVICE)
    '''
    print("train_out")
    input_ids = sample[0].to(config.DEVICE)
    token_type_ids = sample[1].to(config.DEVICE)
    att_mask = sample[2].to(config.DEVICE)
    targets = sample[3].to(config.DEVICE)
    
    optimizer.zero_grad()
    output = model(input_ids,token_type_ids,att_mask)
    output = np.argmax(output,axis = 1)
    loss = criterion(outputs,targets)
    accuracy = accuracy_score(output,targets)
    loss.backward()
    torch.nn.utils.clip_grad_norm_(model.parameters(),1.0)
    xm.optimizer_step(optimizer,barrier=True)
    if scheduler is not None:
        scheduler.step()
    if idx%50==0:
        print(f"idx : {idx},TRAIN LOSS : {loss}")

我一次又一次地遇到此错误

RuntimeError: Caught RuntimeError in DataLoader worker process 0. Original Traceback (most recent 
call last): File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py",line 
178,in _worker_loop data = fetcher.fetch(index) File "/opt/conda/lib/python3.7/site- 
packages/torch/utils/data/_utils/fetch.py",line 47,in fetch return self.collate_fn(data) File 
"/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/collate.py",line 79,in 
 default_collate return [default_collate(samples) for samples in transposed] File 
"/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/collate.py",in return 
 [default_collate(samples) for samples in transposed] File "/opt/conda/lib/python3.7/site- 
 packages/torch/utils/data/_utils/collate.py",line 55,in default_collate return torch.stack(batch,out=out) RuntimeError: stack expects each tensor to be equal size,but got [47] at entry 0 and 
 [36] at entry 1

我尝试更改num_workers值，更改批次大小。我已经检查了数据，并且其中的任何文本都不为null，0或任何形式的损坏。我也曾尝试在tokenizer中更改max_len，但无法找到解决此问题的方法。请检查并告知我该如何解决。

解决方法

data_loader = torch.utils.data.DataLoader（batch_size = batch_size，数据集= data，shuffle = shuffle，num_workers = 0，collat​​e_fn = lambda x：x）

在数据加载器中使用Collat​​e_fn应该可以解决问题。