pytorch分布式训练（四Sampler介绍）

初步掌握pytorch分布式后（见文章1），接下来分析用到的类：

一、DistributedSampler（Sampler）

pytorch在对dataset进行Sampler时候，通过修改indics进行识别在哪个GPU上运行，代码如下。
主要通过indices[self.rank:self.total_size:self.num_replicas]进行多GPU的index索引。

#class DistributedSampler(Sampler):

#train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)

    def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True):
        if num_replicas is None:
            if not dist.is_available():
                raise RuntimeError("Requires distributed package to be available")
            num_replicas = dist.get_world_size()
        if rank is None:
            if not dist.is_available():
                raise RuntimeError("Requires distributed package to be available")
            rank = dist.get_rank()
        self.dataset = dataset
        self.num_replicas = num_replicas
        self.rank = rank
        self.epoch = 0
        self.num_samples = int(math.ceil(len(self.dataset) * 1.0 / self.num_replicas))
        self.total_size = self.num_samples * self.num_replicas
        self.shuffle = shuffle

    def __iter__(self):
        # deterministically shuffle based on epoch
        g = torch.Generator()
        g.manual_seed(self.epoch)
        if self.shuffle:
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = list(range(len(self.dataset)))


        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)

    def __len__(self):
        return self.num_samples

    def set_epoch(self, epoch):
        self.epoch = epoch

二、BatchSampler//torch.utils.data.sampler.BatchSampler

#sampler from upfunction
batch_sampler = make_batch_data_sampler(
            dataset, sampler, aspect_grouping, images_per_gpu, num_iters, start_iter
        )

class BatchSampler(Sampler):
    r"""Wraps another sampler to yield a mini-batch of indices.

    Args:
        sampler (Sampler): Base sampler.
        batch_size (int): Size of mini-batch.
        drop_last (bool): If ``True``, the sampler will drop the last batch if
            its size would be less than ``batch_size``

    Example:
        >>> list(BatchSampler(SequentialSampler(range(10)), batch_size=3, drop_last=False))
        [[0, 1, 2], [3, 4, 5], [6, 7, 8], [9]]
        >>> list(BatchSampler(SequentialSampler(range(10)), batch_size=3, drop_last=True))
        [[0, 1, 2], [3, 4, 5], [6, 7, 8]]
    """

    def __init__(self, sampler, batch_size, drop_last):
        if not isinstance(sampler, Sampler):
            raise ValueError("sampler should be an instance of "
                             "torch.utils.data.Sampler, but got sampler={}"
                             .format(sampler))
        if not isinstance(batch_size, _int_classes) or isinstance(batch_size, bool) or \
                batch_size <= 0:
            raise ValueError("batch_size should be a positive integer value, "
                             "but got batch_size={}".format(batch_size))
        if not isinstance(drop_last, bool):
            raise ValueError("drop_last should be a boolean value, but got "
                             "drop_last={}".format(drop_last))
        self.sampler = sampler
        self.batch_size = batch_size
        self.drop_last = drop_last

    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

    def __len__(self):
        if self.drop_last:
            return len(self.sampler) // self.batch_size
        else:
            return (len(self.sampler) + self.batch_size - 1) // self.batch_size

三、pytorch官网其它sampler：

• RandomSampler
• SequentialSampler
• SubsetRandomSampler
• WeightedRandomSampler

配合分布式使用

def make_data_sampler(dataset, shuffle, distributed):
    if distributed:
        return samplers.DistributedSampler(dataset, shuffle=shuffle)
    if shuffle:
        sampler = torch.utils.data.sampler.RandomSampler(dataset)
    else:
        sampler = torch.utils.data.sampler.SequentialSampler(dataset)
    return sampler