Class CustomDistributedSampler

util/sampler.py:6–36

from typing import TypeVar, Optional, Iterator

class CustomDistributedSampler(DistributedSampler):
    def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True, drop_last: bool = False):
        super().__init__(dataset, num_replicas=num_replicas, rank=rank, shuffle=shuffle, drop_last=drop_last)


    def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch and seed
            g = torch.Generator()
            g.manual_seed(self.seed + self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()  # type: ignore[arg-type]
        else:
            indices = list(range(len(self.dataset)))  # type: ignore[arg-type]

        if not self.drop_last:
            # add extra samples to make it evenly divisible
            padding_size = self.total_size - len(indices)
            if padding_size <= len(indices):
                indices += indices[:padding_size]
            else:
                indices += (indices * math.ceil(padding_size / len(indices)))[:padding_size]
        else:
            # remove tail of data to make it evenly divisible.
            indices = indices[:self.total_size]
        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)