Python RuntimeError:张量a(4000)的大小必须与张量b(512)在非单态维度1的大小相匹配
我正在尝试建立一个文档分类模型。我正在将Python RuntimeError:张量a(4000)的大小必须与张量b(512)在非单态维度1的大小相匹配,python,deep-learning,pytorch,bert-language-model,huggingface-transformers,Python,Deep Learning,Pytorch,Bert Language Model,Huggingface Transformers,我正在尝试建立一个文档分类模型。我正在将BERT与PyTorch一起使用 我用下面的代码得到了伯特模型 bert = AutoModel.from_pretrained('bert-base-uncased') 这是培训代码 for epoch in range(epochs): print('\n Epoch {:} / {:}'.format(epoch + 1, epochs)) #train model train_loss, _ = modhelper.
BERT
与PyTorch
一起使用
我用下面的代码得到了伯特模型
bert = AutoModel.from_pretrained('bert-base-uncased')
这是培训代码
for epoch in range(epochs):
print('\n Epoch {:} / {:}'.format(epoch + 1, epochs))
#train model
train_loss, _ = modhelper.train(proc.train_dataloader)
#evaluate model
valid_loss, _ = modhelper.evaluate()
#save the best model
if valid_loss < best_valid_loss:
best_valid_loss = valid_loss
torch.save(modhelper.model.state_dict(), 'saved_weights.pt')
# append training and validation loss
train_losses.append(train_loss)
valid_losses.append(valid_loss)
print(f'\nTraining Loss: {train_loss:.3f}')
print(f'Validation Loss: {valid_loss:.3f}')
preds=self.model(sent\u id,mask)
此行抛出以下错误(包括完全回溯)
Epoch 1/1
火炬尺寸([324000])火炬尺寸([324000])
回溯(最近一次呼叫最后一次):
文件“”,第8行,在
列车丢失,=modhelper.train(过程列车数据加载器)
列车中第71行的文件“E:\BertTorch\model.py”
preds=自我模型(已发送\u id,掩码)
文件“E:\BertTorch\venv\lib\site packages\torch\nn\modules\module.py”,第727行,在调用impl中
结果=自我转发(*输入,**kwargs)
文件“E:\bertorch\model.py”,第181行,向前
#将输入传递给模型
文件“E:\BertTorch\venv\lib\site packages\torch\nn\modules\module.py”,第727行,在调用impl中
结果=自我转发(*输入,**kwargs)
文件“E:\bertorch\venv\lib\site packages\transformers\modeling\u bert.py”,第837行,向前
嵌入\输出=自嵌入(
文件“E:\BertTorch\venv\lib\site packages\torch\nn\modules\module.py”,第727行,在调用impl中
结果=自我转发(*输入,**kwargs)
文件“E:\bertorch\venv\lib\site packages\transformers\modeling\u bert.py”,第201行,向前
嵌入=输入\嵌入+位置\嵌入+标记\类型\嵌入
RuntimeError:张量a(4000)的大小必须与张量b(512)在非单态维度1的大小相匹配
如果你注意的话,我已经在代码中打印了火炬的尺寸。
打印(已发送\u id.size()、掩码.size())
该行代码的输出是torch.Size([324000])torch.Size([324000])
正如我们所看到的,大小是一样的,但它会抛出错误。请把你的想法。真的很感激
如果您需要进一步的信息,请发表意见。我会很快添加所需内容。问题是关于BERT的字数限制。我已将字数传递为4000,其中支持的最大字数为512(必须为字符串开头和结尾的“[cls]”和“[Sep]”再放弃2个,因此仅为510)。减少字数或使用其他模型解决问题。类似于上面评论中@cronoik所建议的
谢谢。这一行特别出现了错误:
embeddings=inputs\u embeddings+position\u embeddings+token\u type\u embeddings
。这三个变量之间可能存在形状不匹配,因此产生了错误。@planet\u pluto希望您检查了显示两个tnsors.torch.size([324000])torch.size的行([324000])为什么要标记?@Venkatesh我知道self.model()
抛出错误。但是如果仔细查看堆栈跟踪,您可以找到在模型向前传递过程中发生错误的确切位置。您加载的BET经过训练,可以处理长度为512个元素的序列。您提供的序列有4000个元素,而模型告诉您它无法处理。您可以它是使用不同的模型(如longformer)还是使用滑动窗口方法。这取决于您的任务。
def train(self, train_dataloader):
self.model.train()
total_loss, total_accuracy = 0, 0
# empty list to save model predictions
total_preds=[]
# iterate over batches
for step, batch in enumerate(train_dataloader):
# progress update after every 50 batches.
if step % 50 == 0 and not step == 0:
print(' Batch {:>5,} of {:>5,}.'.format(step, len(train_dataloader)))
# push the batch to gpu
#batch = [r.to(device) for r in batch]
sent_id, mask, labels = batch
# clear previously calculated gradients
self.model.zero_grad()
print(sent_id.size(), mask.size())
# get model predictions for the current batch
preds = self.model(sent_id, mask) #This line throws the error
# compute the loss between actual and predicted values
self.loss = self.cross_entropy(preds, labels)
# add on to the total loss
total_loss = total_loss + self.loss.item()
# backward pass to calculate the gradients
self.loss.backward()
# clip the the gradients to 1.0. It helps in preventing the exploding gradient problem
torch.nn.utils.clip_grad_norm_(self.model.parameters(), 1.0)
# update parameters
self.optimizer.step()
# model predictions are stored on GPU. So, push it to CPU
#preds=preds.detach().cpu().numpy()
# append the model predictions
total_preds.append(preds)
# compute the training loss of the epoch
avg_loss = total_loss / len(train_dataloader)
# predictions are in the form of (no. of batches, size of batch, no. of classes).
# reshape the predictions in form of (number of samples, no. of classes)
total_preds = np.concatenate(total_preds, axis=0)
#returns the loss and predictions
return avg_loss, total_preds
Epoch 1 / 1
torch.Size([32, 4000]) torch.Size([32, 4000])
Traceback (most recent call last):
File "<ipython-input-39-17211d5a107c>", line 8, in <module>
train_loss, _ = modhelper.train(proc.train_dataloader)
File "E:\BertTorch\model.py", line 71, in train
preds = self.model(sent_id, mask)
File "E:\BertTorch\venv\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "E:\BertTorch\model.py", line 181, in forward
#pass the inputs to the model
File "E:\BertTorch\venv\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "E:\BertTorch\venv\lib\site-packages\transformers\modeling_bert.py", line 837, in forward
embedding_output = self.embeddings(
File "E:\BertTorch\venv\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "E:\BertTorch\venv\lib\site-packages\transformers\modeling_bert.py", line 201, in forward
embeddings = inputs_embeds + position_embeddings + token_type_embeddings
RuntimeError: The size of tensor a (4000) must match the size of tensor b (512) at non-singleton dimension 1