机器学习-dataset、dataloader的使用（pytorch环境）

Dataset

官方的dataset

例子

import torchvision.datasets
from torch.utils.tensorboard import SummaryWriter

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

train_set = torchvision.datasets.CIFAR10(root='./dataset',train=True,transform=dataset_transform,download=True)
test_set = torchvision.datasets.CIFAR10(root='./dataset',train=False,transform=dataset_transform,download=True)

print(test_set[0])

writer = SummaryWriter("log")
for i in range(10):
    img,target = test_set[i]
    print(type(img),img)
    print(type(target),target)
    writer.add_image("test_set",img,i)

writer.close()

class CIFAR10(VisionDataset):
    """`CIFAR10 <https://www.cs.toronto.edu/~kriz/cifar.html>`_ Dataset.

    Args:
        root (string): Root directory of dataset where directory
            ``cifar-10-batches-py`` exists or will be saved to if download is set to True.
        train (bool, optional): If True, creates dataset from training set, otherwise
            creates from test set.
        transform (callable, optional): A function/transform that takes in an PIL image
            and returns a transformed version. E.g, ``transforms.RandomCrop``
        target_transform (callable, optional): A function/transform that takes in the
            target and transforms it.
        download (bool, optional): If true, downloads the dataset from the internet and
            puts it in root directory. If dataset is already downloaded, it is not
            downloaded again.

    """

该数据集重写了__getitem__函数，所以可以使用下标访问元素

    def __getitem__(self, index: int) -> Tuple[Any, Any]:
        """
        Args:
            index (int): Index

        Returns:
            tuple: (image, target) where target is index of the target class.
        """
        img, target = self.data[index], self.targets[index]

        # doing this so that it is consistent with all other datasets
        # to return a PIL Image
        img = Image.fromarray(img)

        if self.transform is not None:
            img = self.transform(img)

        if self.target_transform is not None:
            target = self.target_transform(target)

        return img, target

DataLoader

例子

import torchvision.datasets
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

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

train_set = torchvision.datasets.CIFAR10(root='./dataset',train=True,transform=dataset_transform,download=True)
test_set = torchvision.datasets.CIFAR10(root='./dataset',train=False,transform=dataset_transform,download=True)

writer = SummaryWriter("dataLoader")

test_loader = DataLoader(dataset=test_set,batch_size=64,shuffle=True,num_workers=0,drop_last=False)

step = 0
for data in test_loader:
    imgs,targets = data
    writer.add_images("test_data",imgs,step)
    step += 1

writer.close()

class DataLoader(Generic[T_co]):
    r"""
    Data loader. Combines a dataset and a sampler, and provides an iterable over
    the given dataset.

    The :class:`~torch.utils.data.DataLoader` supports both map-style and
    iterable-style datasets with single- or multi-process loading, customizing
    loading order and optional automatic batching (collation) and memory pinning.

    See :py:mod:`torch.utils.data` documentation page for more details.

    Args:
        dataset (Dataset): dataset from which to load the data.
        batch_size (int, optional): how many samples per batch to load
            (default: ``1``).
        shuffle (bool, optional): set to ``True`` to have the data reshuffled
            at every epoch (default: ``False``).
        sampler (Sampler or Iterable, optional): defines the strategy to draw
            samples from the dataset. Can be any ``Iterable`` with ``__len__``
            implemented. If specified, :attr:`shuffle` must not be specified.
        batch_sampler (Sampler or Iterable, optional): like :attr:`sampler`, but
            returns a batch of indices at a time. Mutually exclusive with
            :attr:`batch_size`, :attr:`shuffle`, :attr:`sampler`,
            and :attr:`drop_last`.
        num_workers (int, optional): how many subprocesses to use for data
            loading. ``0`` means that the data will be loaded in the main process.
            (default: ``0``)
        collate_fn (callable, optional): merges a list of samples to form a
            mini-batch of Tensor(s).  Used when using batched loading from a
            map-style dataset.
        pin_memory (bool, optional): If ``True``, the data loader will copy Tensors
            into CUDA pinned memory before returning them.  If your data elements
            are a custom type, or your :attr:`collate_fn` returns a batch that is a custom type,
            see the example below.
        drop_last (bool, optional): set to ``True`` to drop the last incomplete batch,
            if the dataset size is not divisible by the batch size. If ``False`` and
            the size of dataset is not divisible by the batch size, then the last batch
            will be smaller. (default: ``False``)
        timeout (numeric, optional): if positive, the timeout value for collecting a batch
            from workers. Should always be non-negative. (default: ``0``)
        worker_init_fn (callable, optional): If not ``None``, this will be called on each
            worker subprocess with the worker id (an int in ``[0, num_workers - 1]``) as
            input, after seeding and before data loading. (default: ``None``)
        generator (torch.Generator, optional): If not ``None``, this RNG will be used
            by RandomSampler to generate random indexes and multiprocessing to generate
            `base_seed` for workers. (default: ``None``)
        prefetch_factor (int, optional, keyword-only arg): Number of samples loaded
            in advance by each worker. ``2`` means there will be a total of
            2 * num_workers samples prefetched across all workers. (default: ``2``)
        persistent_workers (bool, optional): If ``True``, the data loader will not shutdown
            the worker processes after a dataset has been consumed once. This allows to
            maintain the workers `Dataset` instances alive. (default: ``False``)


    .. warning:: If the ``spawn`` start method is used, :attr:`worker_init_fn`
                 cannot be an unpicklable object, e.g., a lambda function. See
                 :ref:`multiprocessing-best-practices` on more details related
                 to multiprocessing in PyTorch.

    .. warning:: ``len(dataloader)`` heuristic is based on the length of the sampler used.
                 When :attr:`dataset` is an :class:`~torch.utils.data.IterableDataset`,
                 it instead returns an estimate based on ``len(dataset) / batch_size``, with proper
                 rounding depending on :attr:`drop_last`, regardless of multi-process loading
                 configurations. This represents the best guess PyTorch can make because PyTorch
                 trusts user :attr:`dataset` code in correctly handling multi-process
                 loading to avoid duplicate data.

                 However, if sharding results in multiple workers having incomplete last batches,
                 this estimate can still be inaccurate, because (1) an otherwise complete batch can
                 be broken into multiple ones and (2) more than one batch worth of samples can be
                 dropped when :attr:`drop_last` is set. Unfortunately, PyTorch can not detect such
                 cases in general.

                 See `Dataset Types`_ for more details on these two types of datasets and how
                 :class:`~torch.utils.data.IterableDataset` interacts with
                 `Multi-process data loading`_.

    .. warning:: See :ref:`reproducibility`, and :ref:`dataloader-workers-random-seed`, and
                 :ref:`data-loading-randomness` notes for random seed related questions.
    """