pytorch中dataloader 的sampler 参数详解

 def __init__(self, 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, multiprocessing_context=None):

	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:
	            sampler = RandomSampler(dataset)
	        else:
	            sampler = SequentialSampler(dataset)

    def __iter__(self):
        n = len(self.data_source)
        # dataset的长度， 按顺序索引
        if self.replacement：# 对应的replace参数
            return iter(torch.randint(high=n, size=(self.num_samples,), dtype=torch.int64).tolist())
        return iter(torch.randperm(n).tolist())        

    if batch_size is not None and batch_sampler is None:
        # auto_collation without custom batch_sampler
        batch_sampler = BatchSampler(sampler, batch_size, drop_last)
        
    self.sampler = sampler
    self.batch_sampler = batch_sampler

# 略去类的初始化
    def __iter__(self):
        batch = []
        for idx in self.sampler:
            batch.append(idx)
            if len(batch) == self.batch_size:
                yield batch
                batch = []
        if len(batch) > 0 and not self.drop_last:
            yield batch

# DataLoader中iter的部分
    def __iter__(self):
        if self.num_workers == 0:
            return _SingleProcessDataLoaderIter(self)
        else:
            return _MultiProcessingDataLoaderIter(self)

# 再看调用的另一个类
class _SingleProcessDataLoaderIter(_BaseDataLoaderIter):
    def __init__(self, loader):
        super(_SingleProcessDataLoaderIter, self).__init__(loader)
        assert self._timeout == 0
        assert self._num_workers == 0

        self._dataset_fetcher = _DatasetKind.create_fetcher(
            self._dataset_kind, self._dataset, self._auto_collation, self._collate_fn, self._drop_last)

    def __next__(self):
        index = self._next_index()  
        data = self._dataset_fetcher.fetch(index)  
        if self._pin_memory:
            data = _utils.pin_memory.pin_memory(data)
        return data