python - TypeError：字符串索引必须是整数 - PyTorch

Question

我正在尝试使用以下代码循环通过我预先训练的 CNN，它从 PyTorch 的示例中稍作修改：

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 i, batch in loaders[phase]:
                inputs = batch["image"].float().to(device)   # <---- error happens here
                labels = batch["label"].float().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

但是我得到了错误：

Epoch 0/24
----------
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-53-79684c739f29> in <module>()
----> 1 model_ft = train_model(resnet_cnn, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=25)

<ipython-input-49-55bb790e99a0> in train_model(model, criterion, optimizer, scheduler, num_epochs)
     21             # Iterate over data.
     22             for i, batch in loaders[phase]:
---> 23                 inputs = batch["image"].float().to(device)
     24                 labels = batch["label"].float().to(device)
     25 

TypeError: string indices must be integers

loader 变量是：

loaders = {"train":train_loader, "val":valid_loader}

我为 train_loader 和 valid_loader 使用的 Dataset 类是，并解释了为什么我在初始模型函数中使用字符串：

class GetDataLabel(Dataset):

  def __init__(self, df, root, transform = None):
    self.df = df
    self.root = root
    self.transform = transform

  def __len__(self):
    return len(self.df)

  def __getitem__(self, idx):
    if torch.is_tensor(idx):
      idx = idx.tolist()

    img_path = os.path.join(self.root, self.df.iloc[idx, 0])
    img = Image.open(img_path)
    label = self.df.iloc[idx, 1]

    if self.transform:
      img = self.transform(img)
    
    img_lab = {"image": img,
               "label": label}
    return (img_lab)

先感谢您。

标签： pythonnumpypytorch

Answer 1

有一个缺失enumerate：

for i, batch in enumerate(loaders[phase]):  # <--- here
    inputs = batch["image"].float().to(device)
    labels = batch["label"].float().to(device)