运行pytorch报错object() takes no parameters

错误返回

TypeError                                 Traceback (most recent call last)
<ipython-input-3-4b01de57c05d> in <module>
     83     correct=0
     84     total=0
---> 85     for images,labels in test_loader:
     86         outputs = model(images)
     87         outputs = model(images)

D:\Program Files (x86)\python3.6\lib\site-packages\torch\utils\data\dataloader.py in __next__(self)
    613         if self.num_workers == 0:  # same-process loading
    614             indices = next(self.sample_iter)  # may raise StopIteration
--> 615             batch = self.collate_fn([self.dataset[i] for i in indices])
    616             if self.pin_memory:
    617                 batch = pin_memory_batch(batch)

D:\Program Files (x86)\python3.6\lib\site-packages\torch\utils\data\dataloader.py in <listcomp>(.0)
    613         if self.num_workers == 0:  # same-process loading
    614             indices = next(self.sample_iter)  # may raise StopIteration
--> 615             batch = self.collate_fn([self.dataset[i] for i in indices])
    616             if self.pin_memory:
    617                 batch = pin_memory_batch(batch)

D:\Program Files (x86)\python3.6\lib\site-packages\torchvision\datasets\mnist.py in __getitem__(self, index)
     74 
     75         if self.transform is not None:
---> 76             img = self.transform(img)
     77 
     78         if self.target_transform is not None:

TypeError: object() takes no parameters

本来以为是torch版本或者torchvision的问题，换了几个版本依旧没有解决。
后面才发现原来少了个括号

加上就没有报错了