File size: 1,310 Bytes
b334e29
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
import math

import torch
from torch.utils.data import DistributedSampler as _DistributedSampler


class DistributedSampler(_DistributedSampler):

    def __init__(self,
                 dataset,
                 num_replicas=None,
                 rank=None,
                 shuffle=True,
                 seed=0):
        super().__init__(
            dataset, num_replicas=num_replicas, rank=rank, shuffle=shuffle)
        # for the compatibility from PyTorch 1.3+
        self.seed = seed if seed is not None else 0

    def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            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
        # in case that indices is shorter than half of total_size
        indices = (indices *
                   math.ceil(self.total_size / len(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)