AttributeError: 'CrossEntropyLoss' object has no attribute 'backward'

Question

我正在尝试在 CIFAR10 数据集上训练一个非常基本的 CNN，但出现以下错误： AttributeError: 'CrossEntropyLoss' 对象没有属性 'backward'

criterion =nn.CrossEntropyLoss
optimizer=optim.SGD(net.parameters(),lr=0.001,momentum=0.9)

for epoch in range(2):  # loop over the dataset multiple times
        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            # get the inputs
            inputs, labels = data
             # wrap them in Variable
            inputs, labels = Variable(inputs), Variable(labels)

            # zero the parameter gradients
            optimizer.zero_grad()
            # forward + backward + optimize
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
            # print statistics
            running_loss += loss.data[0]
            if i % 2000 == 1999:    # print every 2000 mini-batches
                print('[%d, %5d] loss: %.3f' %
                      (epoch + 1, i + 1, running_loss / 2000))
                running_loss = 0.0

Answer 1

问题已解决。我的错误，我漏掉了括号

criterion = nn.CrossEntropyLoss()

Answer 2

通常如果你使用 l = loss(net(X), y) 然后你调用 l.backward() 而不是 loss.backward() 这就是我的错误。

#defining loss
loss = nn.CrossEntropyLoss()
...
#inside training loop
l = loss(net(X), y)
...
# for backpropogation
l.backward()

AttributeError: 'CrossEntropyLoss' object has no attribute 'backward'

AttributeError: 'CrossEntropyLoss' object has no attribute 'backward'

python

neural-network

deep-learning

conv-neural-network

pytorch