PyTorch TypeError:“ToTensor”对象不可编辑

Question

我试图在每次迭代中打印一个图像名称。但是，我得到一个错误TypeError:“ToTensor”对象是不可编辑的。请问我要去哪里？非常感谢

from torchvision import datasets
import torch.utils.data
from torch.utils.data import DataLoader
from torchvision import transforms
from dataset2 import CellsDataset
from torchvision import datasets
import torch
import torchvision
import torchvision.transforms as transforms


class ImageFolderWithPaths(datasets.ImageFolder):
    """Custom dataset that includes image file paths. Extends
    torchvision.datasets.ImageFolder
    """

# override the __getitem__ method. this is the method that dataloader calls
def __getitem__(self, index):
    # this is what ImageFolder normally returns 
    original_tuple = super(ImageFolderWithPaths, self).__getitem__(index)
    # the image file path
    path = self.imgs[index][0]
    # make a new tuple that includes original and the path
    tuple_with_path = (original_tuple + (path,))
    return tuple_with_path

# EXAMPLE USAGE:
# instantiate the dataset and dataloader
data_dir = "/Users/nubstech/Documents/GitHub/CellCountingDirectCount/Eddata/"
dataset = ImageFolderWithPaths(data_dir) # our custom dataset
#dataloader = DataLoader(dataset)
transform = transforms.Compose([
    # you can add other transformations in this list
    transforms.ToTensor()
])
dataset = DataLoader(data_dir, transforms.Compose(transforms.ToTensor()))
dataloader = torch.utils.DataLoader(dataset)

# iterate over data
for inputs, labels, paths in dataloader:
    # use the above variables freely
   print(inputs, labels, paths)

回溯消息：

Traceback (most recent call last):
  File "file_location2.py", line 37, in <module>
    dataset = DataLoader(data_dir, transforms.Compose(transforms.ToTensor()))
  File "/Users/nubstech/opt/anaconda3/envs/Cells_Counting/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 219, in __init__
    batch_sampler = BatchSampler(sampler, batch_size, drop_last)
  File "/Users/nubstech/opt/anaconda3/envs/Cells_Counting/lib/python3.7/site-packages/torch/utils/data/sampler.py", line 190, in __init__
    "but got batch_size={}".format(batch_size))
  File "/Users/nubstech/opt/anaconda3/envs/Cells_Counting/lib/python3.7/site-packages/torchvision/transforms/transforms.py", line 66, in __repr__
    for t in self.transforms:
TypeError: 'ToTensor' object is not iterable

Answer 1

这是因为transforms.Compose()需要是一个列表（可能还接受其他一些iterables）。问题在于：

dataset = DataLoader(data_dir, transforms.Compose(transforms.ToTensor()))

尝试：

transforms = transforms.Compose([transforms.ToTensor()])

这将创建一个可调用函数，您可以在其中传递数据