mmsegmentation/mmseg/core/utils/dist_util.py

47 lines
1.5 KiB
Python

# Copyright (c) OpenMMLab. All rights reserved.
import numpy as np
import torch
import torch.distributed as dist
from mmcv.runner import get_dist_info
def check_dist_init():
return dist.is_available() and dist.is_initialized()
def sync_random_seed(seed=None, device='cuda'):
"""Make sure different ranks share the same seed. All workers must call
this function, otherwise it will deadlock. This method is generally used in
`DistributedSampler`, because the seed should be identical across all
processes in the distributed group.
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.
Args:
seed (int, Optional): The seed. Default to None.
device (str): The device where the seed will be put on.
Default to 'cuda'.
Returns:
int: Seed to be used.
"""
if seed is None:
seed = np.random.randint(2**31)
assert isinstance(seed, int)
rank, world_size = get_dist_info()
if world_size == 1:
return seed
if rank == 0:
random_num = torch.tensor(seed, dtype=torch.int32, device=device)
else:
random_num = torch.tensor(0, dtype=torch.int32, device=device)
dist.broadcast(random_num, src=0)
return random_num.item()