在 PyTorch 中打印每个时期的验证损失

Question

我想在每个 epoch 中打印模型的验证损失，获取和打印验证损失的正确方法是什么？

是这样的吗:

criterion = nn.CrossEntropyLoss(reduction='mean')
for x, y in validation_loader:
 optimizer.zero_grad()
 out = model(x)
 loss = criterion(out, y)
 loss.backward()
 optimizer.step()
 losses += loss

display_loss = losses/len(validation_loader)
print(display_loss)

或者像这样

criterion = nn.CrossEntropyLoss(reduction='mean')
for x, y in validation_loader:
     optimizer.zero_grad()
     out = model(x)
     loss = criterion(out, y)
     loss.backward()
     optimizer.step()
     losses += loss
    
display_loss = losses/len(validation_loader.dataset)
print(display_loss)

还是别的？谢谢。

Answer 1

没有!!!!

在任何情况下都不应使用验证/测试数据训练模型（即调用 loss.backward() + optimizer.step()）！！！

如果您想验证您的模型：

model.eval()  # handle drop-out/batch norm layers
loss = 0
with torch.no_grad():
  for x,y in validation_loader:
    out = model(x)  # only forward pass - NO gradients!!
    loss += criterion(out, y)
# total loss - divide by number of batches
val_loss = loss / len(validation_loader)

请注意 optimizer 如何与在验证集上评估模型无关。您不根据验证数据更改模型 - 仅验证它。

在 PyTorch 中打印每个时期的验证损失

Print the validation loss in each epoch in PyTorch

cross-entropy

pytorch