python - 我该如何解决 "TypeError: max() received an invalid combination of arguments - got (Linear, int), but expected"？

Question

如何解决这个错误，我正在尝试训练票证分类模型

我正在尝试使用 Pytorch 库制作票务分类器，但出现此错误。我不明白我做错了什么你能帮我吗？

data_transforms = {
    'train' : transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val' : transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ])

}

data_dir = 'dataset_billete_argentino'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
                                              shuffle=True, num_workers=4)
               for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_name = image_datasets['train'].classes

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3,6,5)
        self.pool = nn.MaxPool2d(2,2)
        self.conv2 = nn.Conv2d(6,16,5)
        self.fc1 = nn.Linear(16 * 53 * 53, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 2)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(x.size(0), 16* 53 * 53)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3
        return x

net = Net()

def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
    since = time.time()

    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
            if phase == 'train':
                model.train()  # Set model to training mode
            else:
                model.eval()   # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                # track history if only in train
                with torch.set_grad_enabled(phase == 'train'):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)

                    # backward + optimize only if in training phase
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # statistics
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)
            if phase == 'train':
                scheduler.step()

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]

            print('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))

            # deep copy the model
            if phase == 'val' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())

        print()

    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))
    print('Best val Acc: {:4f}'.format(best_acc))

    # load best model weights
    model.load_state_dict(best_model_wts)
    return model

from torch.optim import lr_scheduler

exp_lr_scheduler = lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)

net = train_model(net, criterion, optimizer, exp_lr_scheduler,
                  num_epochs=25)

并给出这个错误类型错误:max() 收到无效的参数组合 - 得到 (Linear, int)，但需要以下之一: *(张量输入) *(张量输入，名称暗淡， bool keepdim，张量输出元组) *(张量输入、张量其他、张量输出) *(张量输入，int dim，bool keepdim，张量输出元组)

Epoch 0/24
----------
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-27-29dfe3459d8a> in <module>
      4 
      5 net = train_model(net, criterion, optimizer, exp_lr_scheduler,
----> 6                   num_epochs=25)

<ipython-input-19-1a5d4f162548> in train_model(model, criterion, optimizer, scheduler, num_epochs)
     31                 with torch.set_grad_enabled(phase == 'train'):
     32                     outputs = model(inputs)
---> 33                     _, preds = torch.max(outputs, 1)
     34                     loss = criterion(outputs, labels)
     35 

TypeError: max() received an invalid combination of arguments - got (Linear, int), but expected one of:
 * (Tensor input)
 * (Tensor input, name dim, bool keepdim, tuple of Tensors out)
 * (Tensor input, Tensor other, Tensor out)
 * (Tensor input, int dim, bool keepdim, tuple of Tensors out)

Answer 1

正如错误消息所示，问题出在这一行:

_, preds = torch.max(outputs, 1)

这里有两个问题:

1. 正如 @Idodo 所说，你给出了 2 个参数，但它们都不是张量。根据消息，它们分别是 Linear 和 int。

2. 如果删除 int，您仍然会遇到错误，因为您正在尝试计算 nn.Linear 的最大值，而这不是可能的。评估你的代码我得到了第二个错误。在模型的前向方法中，您有:

x = self.fc3

这就是问题所在。你必须这样做:

x = self.fc3(x)