Spaces:
Sleeping
Sleeping
| # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. | |
| # Code is copy-pasted exactly as in torch.utils.data.distributed. | |
| # FIXME remove this once c10d fixes the bug it has | |
| import math | |
| import torch | |
| import torch.distributed as dist | |
| from torch.utils.data.sampler import Sampler | |
| from maskrcnn_benchmark.utils.comm import shared_random_seed | |
| 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, shuffle=True, use_random=False): | |
| 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 | |
| self.shuffle = shuffle | |
| self.use_random = use_random | |
| def __iter__(self): | |
| if self.shuffle: | |
| # deterministically shuffle based on epoch | |
| _seed = self.epoch | |
| if self.use_random: | |
| _seed = int(shared_random_seed()) | |
| g = torch.Generator() | |
| g.manual_seed(_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 | |
| 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 | |