torchvision dataset和torch.utils.data.DataLoader

CIFAR
dset.CIFAR10(root, train=True, transform=None, target_transform=None, download=False)

dset.CIFAR100(root, train=True, transform=None, target_transform=None, download=False)

from torch.utils.data.sampler import Sampler
from torch.utils.data.dataset import Dataset
from torch.utils.data.dataloader import DataLoader
 
dataset = MyDataset() # 第一步：构建 Dataset 对象
dataloader = DataLoader(dataset) # 第二步：通过Dataloader来构建迭代对象
 
num_epoches = 100
for epoch in range(num_epoches):
    for i, data in enumerate(dataloader):
        # 训练代码

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)
 
 
 
    Arguments:
        dataset (Dataset): 是一个DataSet对象，表示需要加载的数据集.
        batch_size (int, optional): 每一个batch加载多少组样本，即指定batch_size，默认是 1 
        shuffle (bool, optional): 布尔值True或者是False ，表示每一个epoch之后是否对样本进行随机打乱，默认是False
------------------------------------------------------------------------------------
        sampler (Sampler, optional): 自定义从数据集中抽取样本的策略，如果指定这个参数，那么shuffle必须为False
        batch_sampler (Sampler, optional): 与sampler类似，但是一次只返回一个batch的indices（索引），需要注意的是，一旦指定了这个参数，那么batch_size,shuffle,sampler,drop_last就不能再制定了（互斥）
------------------------------------------------------------------------------------
        num_workers (int, optional): 这个参数决定了有几个进程来处理data loading。0意味着所有的数据都会被load进主进程。（默认为0）
        collate_fn (callable, optional): 将一个list的sample组成一个mini-batch的函数（这个还不是很懂）
        pin_memory (bool, optional): 如果设置为True，那么data loader将会在返回它们之前，将tensors拷贝到CUDA中的固定内存（CUDA pinned memory）中.
------------------------------------------------------------------------------------
        drop_last (bool, optional): 如果设置为True：这个是对最后的未完成的batch来说的，比如你的batch_size设置为64，而一个epoch只有100个样本，那么训练的时候后面的36个就被扔掉了，如果为False（默认），那么会继续正常执行，只是最后的batch_size会小一点。
------------------------------------------------------------------------------------
        timeout (numeric, optional): 如果是正数，表明等待从worker进程中收集一个batch等待的时间，若超出设定的时间还没有收集到，那就不收集这个内容了。这个numeric应总是大于等于0。默认为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``)

class DataLoader(object):
"""
    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).
        sampler (Sampler, optional): defines the strategy to draw samples from
            the dataset. If specified, ``shuffle`` must be False.
        batch_sampler (Sampler, optional): like sampler, but returns a batch of
            indices at a time. Mutually exclusive with batch_size, shuffle,
            sampler, and 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.
        pin_memory (bool, optional): If ``True``, the data loader will copy tensors
            into CUDA pinned memory before returning them.
        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 as input, after seeding and before data
            loading. (default: None)
"""

    def __init__(self, dataset, batch_size=1, shuffle=False, sampler=None, batch_sampler=None,
                 num_workers=0, collate_fn=default_collate, pin_memory=False, drop_last=False,
                 timeout=0, worker_init_fn=None):
        self.dataset = dataset
        self.batch_size = batch_size
        self.num_workers = num_workers
        self.collate_fn = collate_fn
        self.pin_memory = pin_memory
        self.drop_last = drop_last
        self.timeout = timeout
        self.worker_init_fn = worker_init_fn

        if timeout < 0:
            raise ValueError('timeout option should be non-negative')

        if batch_sampler is not None:
            if batch_size > 1 or shuffle or sampler is not None or drop_last:
                raise ValueError('batch_sampler is mutually exclusive with '
                                 'batch_size, shuffle, sampler, and drop_last')

        if sampler is not None and shuffle:
            raise ValueError('sampler is mutually exclusive with shuffle')

        if self.num_workers < 0:
            raise ValueError('num_workers cannot be negative; '
                             'use num_workers=0 to disable multiprocessing.')

        if batch_sampler is None:
            if sampler is None:
                if shuffle:
                    sampler = RandomSampler(dataset)
                else:
                    sampler = SequentialSampler(dataset)
            batch_sampler = BatchSampler(sampler, batch_size, drop_last)

        self.sampler = sampler
        self.batch_sampler = batch_sampler

    def __iter__(self):
        return DataLoaderIter(self)

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

train_data=torch.utils.data.DataLoader(...)
for i, (input, target) in enumerate(train_data):
...

class DataLoaderIter(object):
    "Iterates once over the DataLoader's dataset, as specified by the sampler"

    def __init__(self, loader):
        self.dataset = loader.dataset
        self.collate_fn = loader.collate_fn
        self.batch_sampler = loader.batch_sampler
        self.num_workers = loader.num_workers
        self.pin_memory = loader.pin_memory and torch.cuda.is_available()
        self.timeout = loader.timeout
        self.done_event = threading.Event()

        self.sample_iter = iter(self.batch_sampler)

        if self.num_workers > 0:
            self.worker_init_fn = loader.worker_init_fn
            self.index_queue = multiprocessing.SimpleQueue()
            self.worker_result_queue = multiprocessing.SimpleQueue()
            self.batches_outstanding = 0
            self.worker_pids_set = False
            self.shutdown = False
            self.send_idx = 0
            self.rcvd_idx = 0
            self.reorder_dict = {}

            base_seed = torch.LongTensor(1).random_()[0]
            self.workers = [
                multiprocessing.Process(
                    target=_worker_loop,
                    args=(self.dataset, self.index_queue, self.worker_result_queue, self.collate_fn,
                          base_seed + i, self.worker_init_fn, i))
                for i in range(self.num_workers)]

            if self.pin_memory or self.timeout > 0:
                self.data_queue = queue.Queue()
                self.worker_manager_thread = threading.Thread(
                    target=_worker_manager_loop,
                    args=(self.worker_result_queue, self.data_queue, self.done_event, self.pin_memory,
                          torch.cuda.current_device()))
                self.worker_manager_thread.daemon = True
                self.worker_manager_thread.start()
            else:
                self.data_queue = self.worker_result_queue

            for w in self.workers:
                w.daemon = True  # ensure that the worker exits on process exit
                w.start()

            _update_worker_pids(id(self), tuple(w.pid for w in self.workers))
            _set_SIGCHLD_handler()
            self.worker_pids_set = True

            # prime the prefetch loop
            for _ in range(2 * self.num_workers):
                self._put_indices()