pytorch DataLoader

torch.utils.data.Dataloader

---dataset

---batch_size=1

---shuffle=False

---sampler=None

---batch_sampler=None

---num_workers=0

---collate_fn=None

---pin_memory=False

---drop_last=False

---timeout=0

---worker_init_fn=None

---prefetch_factor=2

---persistent_workers=False

 

collate_fn

1.when automatic batching is disabled,the default collate_fn simply converts Numpy arrays in Pytorch tensors

由此可见，当automatic batching is disabled,numpy 的图片直接被转为tensor类型。

2.when automatic batching is enabled

---it always prepends a new dimension as the batch dimension

---it automatically converts Numpy arrays and Python numerical values into Pytorch Tensors

---it preserve data structure,if each sample is a dictionary,it outputs a dictionary with the same set of keys but batched Tensors a values

def default_collate(batch):
    r"""Puts each data field into a tensor with outer dimension batch size"""

    elem = batch[0]
    elem_type = type(elem)
    if isinstance(elem, torch.Tensor):
        out = None
        if torch.utils.data.get_worker_info() is not None:
            # If we're in a background process, concatenate directly into a
            # shared memory tensor to avoid an extra copy
            numel = sum([x.numel() for x in batch])
            storage = elem.storage()._new_shared(numel)
            out = elem.new(storage)
        return torch.stack(batch, 0, out=out)
    elif elem_type.__module__ == 'numpy' and elem_type.__name__ != 'str_' \
            and elem_type.__name__ != 'string_':
        elem = batch[0]
        if elem_type.__name__ == 'ndarray':
            # array of string classes and object
            if np_str_obj_array_pattern.search(elem.dtype.str) is not None:
                raise TypeError(default_collate_err_msg_format.format(elem.dtype))

            return default_collate([torch.as_tensor(b) for b in batch])
        elif elem.shape == ():  # scalars
            return torch.as_tensor(batch)
    elif isinstance(elem, float):
        return torch.tensor(batch, dtype=torch.float64)
    elif isinstance(elem, int_classes):
        return torch.tensor(batch)
    elif isinstance(elem, string_classes):
        return batch
    elif isinstance(elem, container_abcs.Mapping):
        return {key: default_collate([d[key] for d in batch]) for key in elem}
    elif isinstance(elem, tuple) and hasattr(elem, '_fields'):  # namedtuple
        return elem_type(*(default_collate(samples) for samples in zip(*batch)))
    elif isinstance(elem, container_abcs.Sequence):
        transposed = zip(*batch)
        return [default_collate(samples) for samples in transposed]

    raise TypeError(default_collate_err_msg_format.format(elem_type))

 

torch.utils.data.Dataset

1. 继承时__getitem__()必须被overwrite，装入DataLoader时__len__()必须被overwrite。

2.DataLoader默认构造 a index sampler that yeilds integral indices。To make it work with a map-style dataset with non-integral indices/keys,a custom sampler must be provided

 

torch.utils.data.Sampler

1.every sampler subclass has to provide an __iter__() method, providing a way to iterate over indices of dataset elements,and a __len__() method that returns the length of the returned iterators.

2.default sampler

RandomSampler & SequentialSampler

if sampler is None:  # give default samplers
            if self._dataset_kind == _DatasetKind.Iterable:
                # See NOTE [ Custom Samplers and IterableDataset ]
                sampler = _InfiniteConstantSampler()
            else:  # map-style
                if shuffle:
                    # Cannot statically verify that dataset is Sized
                    # Somewhat related: see NOTE [ Lack of Default `__len__` in Python Abstract Base Classes ]
                    sampler = RandomSampler(dataset, generator=generator)  # type: ignore
                else:
                    sampler = SequentialSampler(dataset)

3.SequentialSampler

可以看到torch.utils.data.Dataset必须提供__len__()方法

class SequentialSampler(Sampler[int]):
    r"""Samples elements sequentially, always in the same order.

    Arguments:
        data_source (Dataset): dataset to sample from
    """
    data_source: Sized

    def __init__(self, data_source):
        self.data_source = data_source

    def __iter__(self):
        return iter(range(len(self.data_source)))

    def __len__(self) -> int:
        return len(self.data_source)

4.RandomSampler

---replacement:True代表放回采样

---_num_samples:当使用放回采样时，可指定采样的个数为_num_samples

__generator:用到再看

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


def __iter__(self):
        n = len(self.data_source)
        if self.generator is None:
            generator = torch.Generator()
            generator.manual_seed(int(torch.empty((), dtype=torch.int64).random_().item()))
        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:
            yield from torch.randperm(n, generator=self.generator).tolist()

def __len__(self):
        return self.num_samples

 

torchvision.datasets.vision.VisionDataset

   提供了self.transforms / self.transforms&self.target_transform（二者不能同时出现）,但是DatasetFolder里没有初始化transforms，所以不要用这个了。

class VisionDataset(data.Dataset):
    _repr_indent = 4

    def __init__(self, root, transforms=None, transform=None, target_transform=None):
        if isinstance(root, torch._six.string_classes):
            root = os.path.expanduser(root)
        self.root = root

        has_transforms = transforms is not None
        has_separate_transform = transform is not None or target_transform is not None
        if has_transforms and has_separate_transform:
            raise ValueError("Only transforms or transform/target_transform can "
                             "be passed as argument")

        # for backwards-compatibility
        self.transform = transform
        self.target_transform = target_transform

        if has_separate_transform:
            transforms = StandardTransform(transform, target_transform)
        self.transforms = transforms

    def __getitem__(self, index):
        raise NotImplementedError

    def __len__(self):
        raise NotImplementedError

    def __repr__(self):
        head = "Dataset " + self.__class__.__name__
        body = ["Number of datapoints: {}".format(self.__len__())]
        if self.root is not None:
            body.append("Root location: {}".format(self.root))
        body += self.extra_repr().splitlines()
        if hasattr(self, "transforms") and self.transforms is not None:
            body += [repr(self.transforms)]
        lines = [head] + [" " * self._repr_indent + line for line in body]
        return '\n'.join(lines)

    def _format_transform_repr(self, transform, head):
        lines = transform.__repr__().splitlines()
        return (["{}{}".format(head, lines[0])] +
                ["{}{}".format(" " * len(head), line) for line in lines[1:]])

    def extra_repr(self):
        return ""

class StandardTransform(object):
    def __init__(self, transform=None, target_transform=None):
        self.transform = transform
        self.target_transform = target_transform

    def __call__(self, input, target):
        if self.transform is not None:
            input = self.transform(input)
        if self.target_transform is not None:
            target = self.target_transform(target)
        return input, target

    def _format_transform_repr(self, transform, head):
        lines = transform.__repr__().splitlines()
        return (["{}{}".format(head, lines[0])] +
                ["{}{}".format(" " * len(head), line) for line in lines[1:]])

    def __repr__(self):
        body = [self.__class__.__name__]
        if self.transform is not None:
            body += self._format_transform_repr(self.transform,
                                                "Transform: ")
        if self.target_transform is not None:
            body += self._format_transform_repr(self.target_transform,
                                                "Target transform: ")

        return '\n'.join(body)

torchvision.datasets.folder.DatastFolder

概述：提供一个root文件夹，root文件夹下面的格式为：

        root/class_x/xxx.ext
        root/class_x/xxy.ext
        root/class_x/xxz.ext

        root/class_y/123.ext
        root/class_y/nsdf3.ext
        root/class_y/asd932_.ext

       同时提供transform和target transform的方法。__getitem__()返回的是transform之后的图片和标签。

       注意：这里读取一个文件夹下面所有的图片，并以(path,target)的形式存储在self.samples里面(此时的target 为int类型,class到target的映射方法是class按照字典序进行排序，下标对应target)。如果需要更改为从txt读取path和target的话，只需要更改       make_dataset

class DatasetFolder(VisionDataset):
    """A generic data loader where the samples are arranged in this way: ::

        root/class_x/xxx.ext
        root/class_x/xxy.ext
        root/class_x/xxz.ext

        root/class_y/123.ext
        root/class_y/nsdf3.ext
        root/class_y/asd932_.ext

    Args:
        root (string): Root directory path.
        loader (callable): A function to load a sample given its path.
        extensions (tuple[string]): A list of allowed extensions.
            both extensions and is_valid_file should not be passed.
        transform (callable, optional): A function/transform that takes in
            a sample and returns a transformed version.
            E.g, ``transforms.RandomCrop`` for images.
        target_transform (callable, optional): A function/transform that takes
            in the target and transforms it.
        is_valid_file (callable, optional): A function that takes path of an Image file
            and check if the file is a valid_file (used to check of corrupt files)
            both extensions and is_valid_file should not be passed.

     Attributes:
        classes (list): List of the class names.
        class_to_idx (dict): Dict with items (class_name, class_index).
        samples (list): List of (sample path, class_index) tuples
        targets (list): The class_index value for each image in the dataset
    """

    def __init__(self, root, loader, extensions=None, transform=None,
                 target_transform=None, is_valid_file=None):
        super(DatasetFolder, self).__init__(root, transform=transform,
                                            target_transform=target_transform)
        classes, class_to_idx = self._find_classes(self.root)
        samples = make_dataset(self.root, class_to_idx, extensions, is_valid_file)
        if len(samples) == 0:
            raise (RuntimeError("Found 0 files in subfolders of: " + self.root + "\n"
                                "Supported extensions are: " + ",".join(extensions)))

        self.loader = loader
        self.extensions = extensions

        self.classes = classes
        self.class_to_idx = class_to_idx
        self.samples = samples
        self.targets = [s[1] for s in samples]

    def _find_classes(self, dir):
        """
        Finds the class folders in a dataset.

        Args:
            dir (string): Root directory path.

        Returns:
            tuple: (classes, class_to_idx) where classes are relative to (dir), and class_to_idx is a dictionary.

        Ensures:
            No class is a subdirectory of another.
        """
        if sys.version_info >= (3, 5):
            # Faster and available in Python 3.5 and above
            classes = [d.name for d in os.scandir(dir) if d.is_dir()]
        else:
            classes = [d for d in os.listdir(dir) if os.path.isdir(os.path.join(dir, d))]
        classes.sort()
        class_to_idx = {classes[i]: i for i in range(len(classes))}
        return classes, class_to_idx

    def __getitem__(self, index):
        """
        Args:
            index (int): Index

        Returns:
            tuple: (sample, target) where target is class_index of the target class.
        """
        path, target = self.samples[index]
        sample = self.loader(path)
        if self.transform is not None:
            sample = self.transform(sample)
        if self.target_transform is not None:
            target = self.target_transform(target)

        return sample, target

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



def make_dataset(
    directory: str,
    class_to_idx: Dict[str, int],
    extensions: Optional[Tuple[str, ...]] = None,
    is_valid_file: Optional[Callable[[str], bool]] = None,
) -> List[Tuple[str, int]]:
    instances = []
    directory = os.path.expanduser(directory)
    both_none = extensions is None and is_valid_file is None
    both_something = extensions is not None and is_valid_file is not None
    if both_none or both_something:
        raise ValueError("Both extensions and is_valid_file cannot be None or not None at the same time")
    if extensions is not None:
        def is_valid_file(x: str) -> bool:
            return has_file_allowed_extension(x, cast(Tuple[str, ...], extensions))
    is_valid_file = cast(Callable[[str], bool], is_valid_file)
    for target_class in sorted(class_to_idx.keys()):
        class_index = class_to_idx[target_class]
        target_dir = os.path.join(directory, target_class)
        if not os.path.isdir(target_dir):
            continue
        for root, _, fnames in sorted(os.walk(target_dir, followlinks=True)):
            for fname in sorted(fnames):
                path = os.path.join(root, fname)
                if is_valid_file(path):
                    item = path, class_index
                    instances.append(item)
    return instances