AttributeError：“int”对象没有属性“view”（1）

Question

我的代码在下面，我的问题在input_gray = input_gray.view(batch_size,1,64,32)。由于我使用了 enumerate，所以我猜有问题但不知道如何解决，我需要您的帮助，谢谢。

for epoch in range(epochs):
    # Train for one epoch, then validate
    train(train_loader, model, criterion, optimizer, epoch)
    correct=0
    total=0

    with torch.no_grad():
        losses = validate(val_loader, model, criterion, save_images, epoch)
        for data in enumerate(train_loader):
            input_gray, labels = data
            input_gray = input_gray.view(batch_size,1,64,32)
            input_gray = input_gray.float()

        if use_gpu:
            input_gray, labels = input_gray.to.cuda(), labels.to.cuda()

        output_ab = model(input_gray)
        _, predicted = torch.max(output_ab.data,1)
        total+=labels.size()
        correct+=(predicted==labels).sum().item()

    print("Accuracy train %d %%"%(100*correct/total))
    train_acc.append(100*correct/total)    

    # Save checkpoint and replace old best model if current model is better   
    if losses < best_losses:
        best_losses = losses
        torch.save(model.state_dict(), 'checkpoints/model-epoch-{}-losses-{:.3f}.pth'.format(epoch+1,losses))

Answer 1

如果你枚举一个列表，你会得到每个项目及其索引作为元组返回 (index,item)。

class something:
    def __init__(self,prop1,prop2):
        self.prop1=prop1
        self.prop2=prop2

l = [something(1,"a"),something(2,"b")]


for k in enumerate(l):
    index, data = k              # so k is a tuple of (index,item) - you can deref it

    print(index)                 

    # you can access the items properties like so:
    print(data.prop1, data.prop2) 

输出：

0
1 a
1
2 b

您的代码可能需要：

for data in enumerate(train_loader):
     index, (input_gray, labels) = data

Answer 2

只需替换为这一行：

for i, data in enumerate(train_loader):

或者用这一行，如果你不需要索引：

for data in train_loader: