【发布时间】：2022-01-12 23:30:39
【问题描述】：
我用这个代码
训练模型的函数
def train():
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 for r in batch]
sent_id, mask, labels = batch['input_ids'],batch['attention_mask'],batch['labels']
print(6)
print(sent_id)
print(mask)
print(labels)
print(batch['input_ids'].shape)
print(batch['attention_mask'].shape)
print(batch['labels'].shape)
# clear previously calculated gradients
model.zero_grad()
print(7)
# get model predictions for the current batch
preds = model(sent_id, mask)
print(8)
print(len(preds))
print(len(labels))
print(preds.size())
preds =torch.argmax(preds, dim=1)
preds =torch.argmax(preds, dim=1)
print(preds)
print(labels)
# compute the loss between actual and predicted values
loss = loss_fn(preds, labels)
print(9)
# add on to the total loss
total_loss = total_loss + loss.item()
print(10)
# backward pass to calculate the gradients
loss.backward()
# clip the the gradients to 1.0. It helps in preventing the exploding gradient problem
# clip the the gradients to 1.0. It helps in preventing the exploding gradient problem
torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)
# update parameters
optimizer.step()
# model predictions are stored on GPU. So, push it to CPU
preds=preds.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
import torch.nn as nn
loss_fn=nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.00001)
我在计算损失时出错 预测 张量（[5, 1, 1, 1, 0, 2, 1, 4, 2, 3, 0, 2, 0, 1, 0, 3, 5, 3, 1, 2, 0, 2, 2, 1 , 0, 1, 4, 0, 5, 5, 4, 5, 0, 2, 0, 1, 4, 0, 0, 3, 5, 1, 1, 1, 4, 4, 4, 1, 2, 1, 3, 3, 2, 1, 0, 2, 0, 4, 4, 4, 3, 2, 0, 5])
标签 张量（[0, 0, 1, 2, 3, 0, 0, 0, 0, 1, 1, 0, 0, 0, 4, 0, 0, 2, 1, 0, 0, 0, 0, 0 , 1, 0, 0, 1, 1, 2, 1, 3, 2, 0, 3, 4, 0, 1, 0, 0, 0, 0, 0, 0, 5, 0, 0, 3, 0, 0, 1, 0, 0, 0, 2, 0, 0, 2, 0, 0, 2, 0, 0, 0]) 我用过它们 损失=损失_fn（预测，标签） 错误：
in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing)
2844 if size_average is not None or reduce is not None:
2845 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 2846 return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
2847
2848
RuntimeError: Expected floating point type for target with class probabilities, got Long
【问题讨论】：
-
你有什么问题？
标签： python neural-network torch bert-language-model cross-entropy