PyTorch Dataloader-枚举时列表不可调用错误

当在PyTorch数据加载器上迭代时，例如

# define dataset, dataloader
train_data = datasets.ImageFolder(data_dir + '/train', transform=train_transforms)
test_data = datasets.ImageFolder(data_dir + '/test', transform=test_transforms)
trainloader = torch.utils.data.DataLoader(train_data, batch_size=64, shuffle=True)
testloader = torch.utils.data.DataLoader(test_data, batch_size=64)

# define model, optimizer, loss
# not included - irrelevant to the question

for ii, (inputs, labels) in enumerate(trainloader):

    # Move input and label tensors to the GPU
    inputs, labels = inputs.to(device), labels.to(device)

    start = time.time()

    outputs = model.forward(inputs)
    loss = criterion(outputs, labels)
    loss.backward()

我得到一个

TypeError:“list”对象不可在此行调用

for ii, (inputs, labels) in enumerate(trainloader):

train_data = datasets.ImageFolder(data_dir + '/train', transform=train_transforms)

---

我忘了什么蠢事了？

你记得调用

转换吗。在你的转换列表中编写

在这一行

for ii, (inputs, labels) in enumerate(trainloader):

train_data = datasets.ImageFolder(data_dir + '/train', transform=train_transforms)

transform
参数需要一个可调用的对象，而不是列表

例如，这是错误的：

train_transforms = [
    transforms.RandomResizedCrop(224),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]

应该是这样的

train_transforms = transforms.Compose([
    transforms.RandomResizedCrop(224),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])