pytorch DataLoader

r"""Definition of the DataLoader and it's iterator _DataLoaderIter classes.

To support these two classes, in `./_utils` we define many utility methods and
functions to be run in multiprocessing. E.g., the data loading worker loop is
in `./_utils/worker.py`.
"""

import torch
import torch.multiprocessing as multiprocessing
from . import SequentialSampler, RandomSampler, BatchSampler
from . import _utils
import threading
from torch._six import queue


# This function used to be defined in this file. However, it was moved to
# _utils/collate.py. Although it is rather hard to access this from user land
# (one has to explicitly directly `import torch.utils.data.dataloader`), there
# probably is user code out there using it. This aliasing maintains BC in this
# aspect.
default_collate = _utils.collate.default_collate


class DataLoader(object):
    r"""
    Data loader. Combines a dataset and a sampler, and provides
    single- or multi-process iterators over the dataset.

    Arguments:
        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``).  每个 epoch 重新随机数据
        sampler (Sampler, optional): defines the strategy to draw samples from
            the dataset. If specified, ``shuffle`` must be False.  定义抽样方法
        batch_sampler (Sampler, optional): like 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``)  多少个线程 用于 加载数据
        collate_fn (callable, optional): merges a list of samples to form a mini-batch. 把 list sample 合并成 mini-batch
        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 ``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``)  当 batch 很大是，最后一轮可能样本数量偏少，影响模型训练
        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``)
    """