mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-07 00:21:07 +01:00
0988bbad2d
Summary: The old `torch.distributed` will go to `torch.distributed.deprecated` The old DDP will go to `torch.nn.parallel.deprecated` Now `torch.nn.parallel.DDP` will use c10d DDP Now `torch.distributed` will use C10d frontend API Pull Request resolved: https://github.com/pytorch/pytorch/pull/11405 Reviewed By: pietern Differential Revision: D9733733 Pulled By: teng-li fbshipit-source-id: d6a3f3e73f8d3a7fcb1f4baef53c78063b8cbb08
63 lines
2.1 KiB
Python
63 lines
2.1 KiB
Python
import math
|
|
import torch
|
|
from . import Sampler
|
|
import torch.distributed as dist
|
|
|
|
|
|
class DistributedSampler(Sampler):
|
|
"""Sampler that restricts data loading to a subset of the dataset.
|
|
|
|
It is especially useful in conjunction with
|
|
:class:`torch.nn.parallel.DistributedDataParallel`. In such case, each
|
|
process can pass a DistributedSampler instance as a DataLoader sampler,
|
|
and load a subset of the original dataset that is exclusive to it.
|
|
|
|
.. note::
|
|
Dataset is assumed to be of constant size.
|
|
|
|
Arguments:
|
|
dataset: Dataset used for sampling.
|
|
num_replicas (optional): Number of processes participating in
|
|
distributed training.
|
|
rank (optional): Rank of the current process within num_replicas.
|
|
"""
|
|
|
|
def __init__(self, dataset, num_replicas=None, rank=None):
|
|
if num_replicas is None:
|
|
if not dist.is_available():
|
|
raise RuntimeError("Requires distributed package to be available")
|
|
num_replicas = dist.get_world_size()
|
|
if rank is None:
|
|
if not dist.is_available():
|
|
raise RuntimeError("Requires distributed package to be available")
|
|
rank = dist.get_rank()
|
|
self.dataset = dataset
|
|
self.num_replicas = num_replicas
|
|
self.rank = rank
|
|
self.epoch = 0
|
|
self.num_samples = int(math.ceil(len(self.dataset) * 1.0 / self.num_replicas))
|
|
self.total_size = self.num_samples * self.num_replicas
|
|
|
|
def __iter__(self):
|
|
# deterministically shuffle based on epoch
|
|
g = torch.Generator()
|
|
g.manual_seed(self.epoch)
|
|
indices = torch.randperm(len(self.dataset), generator=g).tolist()
|
|
|
|
# add extra samples to make it evenly divisible
|
|
indices += indices[:(self.total_size - len(indices))]
|
|
assert len(indices) == self.total_size
|
|
|
|
# subsample
|
|
offset = self.num_samples * self.rank
|
|
indices = indices[offset:offset + self.num_samples]
|
|
assert len(indices) == self.num_samples
|
|
|
|
return iter(indices)
|
|
|
|
def __len__(self):
|
|
return self.num_samples
|
|
|
|
def set_epoch(self, epoch):
|
|
self.epoch = epoch
|