TypeError: object of type 'module' has no len()

Question

在运行代码时遇到如下问题

D:/main.py
Traceback (most recent call last):
  File "E:/main.py", line 184, in <module>
    train_dataloader = DataLoader(
  File "D:\pythonproject3.8\lib\site-packages\torch\utils\data\dataloader.py", line 353, in __init__
    sampler = RandomSampler(dataset, generator=generator)  # type: ignore[arg-type]
  File "D:\pythonproject3.8\lib\site-packages\torch\utils\data\sampler.py", line 106, in __init__
    if not isinstance(self.num_samples, int) or self.num_samples <= 0:
  File "D:\pythonproject3.8\lib\site-packages\torch\utils\data\sampler.py", line 114, in num_samples
    return len(self.data_source)
TypeError: object of type 'module' has no len()

报错部分代码如下：

    data_source: Sized
    replacement: bool

    def __init__(self, data_source: Sized, replacement: bool = False,
                 num_samples: Optional[int] = None, generator=None) -> None:
        self.data_source = data_source
        self.replacement = replacement
        self._num_samples = num_samples
        self.generator = generator

        if not isinstance(self.replacement, bool):
            raise TypeError("replacement should be a boolean value, but got "
                            "replacement={}".format(self.replacement))

        if not isinstance(self.num_samples, int) or self.num_samples <= 0:
            raise ValueError("num_samples should be a positive integer "
                             "value, but got num_samples={}".format(self.num_samples))

    @property
    def num_samples(self) -> int:
        # dataset size might change at runtime
        if self._num_samples is None:
            return len(self.data_source)    #此处报错
        return self._num_samples

    def __iter__(self) -> Iterator[int]:
        n = len(self.data_source)
        if self.generator is None:
            seed = int(torch.empty((), dtype=torch.int64).random_().item())
            generator = torch.Generator()
            generator.manual_seed(seed)
        else:
            generator = self.generator

        if self.replacement:
            for _ in range(self.num_samples // 32):
                yield from torch.randint(high=n, size=(32,), dtype=torch.int64, generator=generator).tolist()
            yield from torch.randint(high=n, size=(self.num_samples % 32,), dtype=torch.int64, generator=generator).tolist()
        else:
            for _ in range(self.num_samples // n):
                yield from torch.randperm(n, generator=generator).tolist()
            yield from torch.randperm(n, generator=generator).tolist()[:self.num_samples % n]

    def __len__(self) -> int:
        return self.num_samples

求问有什么解决方法吗？

Answer 1

self.data_source 是一个 module 对象，len()方法接收的参数不能是module，可以是一个列表，字符串等可迭代的对象