python - 'bert-base-multilingual-uncased' dataloader RuntimeError:堆栈期望每个张量大小相等
问题描述
我是 nlp 的初学者,因为我正在参加这个比赛https://www.kaggle.com/c/contradictory-my-dear-watson我正在使用模型“bert-base-multilingual-uncased”并使用 BERT 标记器从同一个。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,
"token_type_ids":token_type_ids,
"att_mask":att_mask
}
return sample
在数据加载器中加载数据期间
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}")
我一次又一次地面临这个错误
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", line 79, 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,
0, out=out) RuntimeError: stack expects each tensor to be equal size, but got [47] at entry 0 and
[36] at entry 1
我试过改变 num_workers 值,改变批量大小。我检查了数据,其中没有任何文本为空、0 或任何意义上的损坏。我也尝试在 tokenizer 中更改 max_len,但我无法找到解决此问题的方法。请检查并让我知道如何解决它。
解决方案
data_loader = torch.utils.data.DataLoader(batch_size=batch_size, dataset=data, shuffle=shuffle, num_workers=0, collate_fn=lambda x: x)
在dataloader中使用Collate_fn应该可以解决问题。
推荐阅读
- pandas - 创建额外的列来计算由另一列分组的累积出现次数
- json - react-hook-form axios post - 无法创建有效负载
- hibernate - 当实体类名和表名不同时,无法使用@ManyToMany @JoinTable 创建唯一键约束
- javascript - 我的 jQuery 不能在 Vs 代码控制台上运行
- flutter - 应用栏下方的颤振 showModalBottomSheet
- android - 使用 Android Studio 构建奇怪的混合配置
- shell - 为 shell 脚本设置自定义 argv[0]
- sql - 如果 expiryAmt 大于 orderAmt 的 2%,则 SUM & Count expiryAmt
- java - 下面的Java代码真的包含循环依赖吗?
- python - 如何增加内联查询超时?