0

我尝试使用 Google Colab 为 Kaggle 初始化的 Notebook 并发现了一个奇怪的行为，因为它给了我类似的东西：

 16   # text2tensor
---> 17   train_seq,train_mask,train_y = textToTensor(train_text,train_labels,pad_len)
     18   val_seq,val_mask,val_y       = textToTensor(val_text,val_labels,pad_len)
     19 

<ipython-input-9-ee85c4607a30> in textToTensor(text, labels, max_len)
      4   tokens = tokenizer.batch_encode_plus(text.tolist(), max_length=max_len, padding='max_length', truncation=True)
      5 
----> 6   text_seq = torch.tensor(tokens['input_ids'])
      7   text_mask = torch.tensor(tokens['attention_mask'])
      8 

ValueError: expected sequence of length 38 at dim 1 (got 13)

错误来自以下代码：

def textToTensor(text,labels=None,max_len=38):#max_len is 38
  
  tokens = tokenizer.batch_encode_plus(text.tolist(), max_length=max_len, padding='max_length', truncation=True)
  
  text_seq = torch.tensor(tokens['input_ids']) # ERROR CAME FROM HERE
  text_mask = torch.tensor(tokens['attention_mask'])

  text_y = None
  if isinstance(labels,np.ndarray):
    text_y = torch.tensor(labels.tolist())

  return text_seq, text_mask, text_y



train_seq,train_mask,train_y = textToTensor(train_text,train_labels,pad_len)
train_data = TensorDataset(train_seq, train_mask, train_y)
train_sampler = RandomSampler(train_data)
train_dataloader = DataLoader(train_data, sampler=train_sampler, batch_size=batch_size)

我再次在COLAB上运行了这段代码，它运行得很顺利。可能是因为版本之类的吗？有人可以取悦这个吗？

Kaggle 配置：

transformers: '2.11.0'
torch: '1.5.1'
python: 3.7.6

Colab 配置：

torch: 1.7.0+cu101
transformers: 3.5.1
python: 3.6.9

编辑：我train_text是一个 numpy 文本数组，train_labels是一维数值数组，有 4 个类别，范围为 0-3。

另外：我将我的标记器初始化为：

from transformers import BertTokenizerFast
tokenizer = BertTokenizerFast.from_pretrained('bert-base-uncased')
4

0 回答 0