74 lines
2.9 KiB
Python
74 lines
2.9 KiB
Python
# Copyright (c) OpenMMLab. All rights reserved.
|
|
from __future__ import division
|
|
from typing import Iterator, Optional
|
|
|
|
import torch
|
|
from torch.utils.data import Dataset
|
|
from torch.utils.data import DistributedSampler as _DistributedSampler
|
|
|
|
from mmseg.core.utils import sync_random_seed
|
|
from mmseg.registry import DATA_SAMPLERS
|
|
|
|
|
|
@DATA_SAMPLERS.register_module()
|
|
class DistributedSampler(_DistributedSampler):
|
|
"""DistributedSampler inheriting from
|
|
`torch.utils.data.DistributedSampler`.
|
|
|
|
Args:
|
|
datasets (Dataset): the dataset will be loaded.
|
|
num_replicas (int, optional): Number of processes participating in
|
|
distributed training. By default, world_size is retrieved from the
|
|
current distributed group.
|
|
rank (int, optional): Rank of the current process within num_replicas.
|
|
By default, rank is retrieved from the current distributed group.
|
|
shuffle (bool): If True (default), sampler will shuffle the indices.
|
|
seed (int): random seed used to shuffle the sampler if
|
|
:attr:`shuffle=True`. This number should be identical across all
|
|
processes in the distributed group. Default: ``0``.
|
|
"""
|
|
|
|
def __init__(self,
|
|
dataset: Dataset,
|
|
num_replicas: Optional[int] = None,
|
|
rank: Optional[int] = None,
|
|
shuffle: bool = True,
|
|
seed=0) -> None:
|
|
super().__init__(
|
|
dataset, num_replicas=num_replicas, rank=rank, shuffle=shuffle)
|
|
|
|
# In distributed sampling, different ranks should sample
|
|
# non-overlapped data in the dataset. Therefore, this function
|
|
# is used to make sure that each rank shuffles the data indices
|
|
# in the same order based on the same seed. Then different ranks
|
|
# could use different indices to select non-overlapped data from the
|
|
# same data list.
|
|
self.seed = sync_random_seed(seed)
|
|
|
|
def __iter__(self) -> Iterator:
|
|
"""
|
|
Yields:
|
|
Iterator: iterator of indices for rank.
|
|
"""
|
|
# deterministically shuffle based on epoch
|
|
if self.shuffle:
|
|
g = torch.Generator()
|
|
# When :attr:`shuffle=True`, this ensures all replicas
|
|
# use a different random ordering for each epoch.
|
|
# Otherwise, the next iteration of this sampler will
|
|
# yield the same ordering.
|
|
g.manual_seed(self.epoch + self.seed)
|
|
indices = torch.randperm(len(self.dataset), generator=g).tolist()
|
|
else:
|
|
indices = torch.arange(len(self.dataset)).tolist()
|
|
|
|
# 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)
|