pytorch 的数据加载到模型的操作顺序是这样的:
① 创建一个 Dataset 对象
② 创建一个 DataLoader 对象
③ 循环这个 DataLoader 对象,将img, label加载到模型中进行训练
dataset = MyDataset()
dataloader = DataLoader(dataset)
num_epoches = 100
for epoch in range(num_epoches):
for img, label in dataloader:
....
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=batchSize,
shuffle=shuffle,
num_workers=int(workers))
ref
https://www.jianshu.com/p/a32ae0294223
https://blog.csdn.net/sunflower_Yolanda/article/details/51725143
参数:
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 (an int in ``[0, num_workers - 1]``) as
input, after seeding and before data loading. (default: None)
源代码
class DataLoader(object):
r"""
Data loader. Combines a dataset and a sampler, and provides
single- or multi-process iterators over the dataset.
.. note:: By default, each worker will have its PyTorch seed set to
``base_seed + worker_id``, where ``base_seed`` is a long generated
by main process using its RNG. However, seeds for other libraies
may be duplicated upon initializing workers (w.g., NumPy), causing
each worker to return identical random numbers. (See
:ref:`dataloader-workers-random-seed` section in FAQ.) You may
use ``torch.initial_seed()`` to access the PyTorch seed for each
worker in :attr:`worker_init_fn`, and use it to set other seeds
before data loading.
.. warning:: If ``spawn`` start method is used, :attr:`worker_init_fn` cannot be an
unpicklable object, e.g., a lambda function.
"""
__initialized = False
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 option is mutually exclusive '
'with batch_size, shuffle, sampler, and '
'drop_last')
self.batch_size = None
self.drop_last = None
if sampler is not None and shuffle:
raise ValueError('sampler option is mutually exclusive with '
'shuffle')
if self.num_workers < 0:
raise ValueError('num_workers option 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
self.__initialized = True
def __setattr__(self, attr, val):
if self.__initialized and attr in ('batch_size', 'sampler', 'drop_last'):
raise ValueError('{} attribute should not be set after {} is '
'initialized'.format(attr, self.__class__.__name__))
super(DataLoader, self).__setattr__(attr, val)
def __iter__(self):
return _DataLoaderIter(self)
def __len__(self):
return len(self.batch_sampler)