无法通过Pytorch Dataloader进行迭代。不等张量

Question

我正在imdbdataset上训练一个基于BERT的模型。但是，我无法迭代Pytorch数据加载器

这是完全可复制的代码。培训文件为上述csv

import transformers
from sklearn import model_selection
import torch
import pandas as pd
    
    
tokenizer = transformers.BertTokenizer.from_pretrained("bert-base-cased", do_lower_case=True)
max_len = 512
train_batch_size = 8
    
"""
This class takes reviews and targets as arguments 
- Split the reviews and tokenizes
"""
class BERTDataset:
    def __init__(self, review, target):
        self.review = review
        self.target = target
        self.tokenizer = tokenizer
        self.max_len = max_len

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

    def __getitem__(self, item):
        review = str(self.review[item])
        review = " ".join(review.split())

        tokenized_inputs = self.tokenizer.encode_plus(
            review,
            None,
            add_special_tokens=True,
            max_length=self.max_len,
            padding=True,
            truncation=True
        )

        ids = tokenized_inputs["input_ids"]
        mask = tokenized_inputs["attention_mask"]
        token_type_ids = tokenized_inputs["token_type_ids"]

        return {
            "ids": torch.tensor(ids, dtype=torch.long),
            "mask": torch.tensor(mask, dtype=torch.long),
            "token_type_ids": torch.tensor(token_type_ids, dtype=torch.long),
            "targets": torch.tensor(self.target[item], dtype=torch.float),
        }


dfx = pd.read_csv(training_file).fillna("none")
dfx['sentiment'] = dfx['sentiment'].apply(lambda x: 1 if x == 'positive' else 0)

df_train, df_valid = model_selection.train_test_split(
                        dfx,
                        test_size=0.1,
                        random_state=42,
                        stratify=dfx['sentiment'].values
                        )

# reset indices 
df_train = df_train.reset_index(drop=True)

# get ids, tokens, masks and targets  
train_dataset = BERTDataset(review=df_train['review'], target=df_train['sentiment'])

# load into pytorch dataset object
# DataLoader inputs tensor dataset of Inputs and targets 
train_data_loader = torch.utils.data.DataLoader(train_dataset, batch_size=train_batch_size, num_workers=0)

# Iterating to the Data loader
train_iter = iter(train_data_loader)
print(type(train_iter))

review, labels = train_iter.next()

出现以下错误

    RuntimeError Traceback (most recent call last)
    <ipython-input-19-c99d0829d5d9> in <module>()
          2 print(type(train_iter))
          3 
    ----> 4 images, labels = train_iter.next()
    
    5 frames
    /usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/collate.py in default_collate(batch)
         53             storage = elem.storage()._new_shared(numel)
         54             out = elem.new(storage)
    ---> 55         return torch.stack(batch, 0, out=out)
         56     elif elem_type.__module__ == 'numpy' and elem_type.__name__ != 'str_' \
         57             and elem_type.__name__ != 'string_':
    
    RuntimeError: stack expects each tensor to be equal size, but got [486] at entry 0 and [211] at entry 1

数据加载器中的num_workers=0修复了内存问题。有人能帮我弄清楚我遗漏了什么吗