29 lines
978 B
Python
29 lines
978 B
Python
|
import torch
|
||
|
|
from torch.utils.data import DistributedSampler as _DistributedSampler
|
||
|
|
|
||
|
|
|
||
|
|
class DistributedSampler(_DistributedSampler):
|
||
|
|
|
||
|
|
def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True):
|
||
|
|
super().__init__(dataset, num_replicas=num_replicas, rank=rank)
|
||
|
|
self.shuffle = shuffle
|
||
|
|
|
||
|
|
def __iter__(self):
|
||
|
|
# deterministically shuffle based on epoch
|
||
|
|
if self.shuffle:
|
||
|
|
g = torch.Generator()
|
||
|
|
g.manual_seed(self.epoch)
|
||
|
|
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)
|