File size: 2,365 Bytes
62a2f1c |
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 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
import torch
from functools import partial
from torch.utils.data import DataLoader
from torch.utils.data import DistributedSampler as _DistributedSampler
from pcdet.utils import common_utils
from .dataset import DatasetTemplate
from .once.once_dataset import ONCEDataset
__all__ = {
'DatasetTemplate': DatasetTemplate,
'ONCEDataset': ONCEDataset
}
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):
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()
indices += indices[:(self.total_size - len(indices))]
assert len(indices) == self.total_size
indices = indices[self.rank:self.total_size:self.num_replicas]
assert len(indices) == self.num_samples
return iter(indices)
def build_dataloader(dataset_cfg, class_names, batch_size, dist, root_path=None, workers=4, seed=None,
logger=None, training=True, merge_all_iters_to_one_epoch=False, total_epochs=0):
dataset = __all__[dataset_cfg.DATASET](
dataset_cfg=dataset_cfg,
class_names=class_names,
root_path=root_path,
training=training,
logger=logger,
)
if merge_all_iters_to_one_epoch:
assert hasattr(dataset, 'merge_all_iters_to_one_epoch')
dataset.merge_all_iters_to_one_epoch(merge=True, epochs=total_epochs)
if dist:
if training:
sampler = torch.utils.data.distributed.DistributedSampler(dataset)
else:
rank, world_size = common_utils.get_dist_info()
sampler = DistributedSampler(dataset, world_size, rank, shuffle=False)
else:
sampler = None
dataloader = DataLoader(
dataset, batch_size=batch_size, pin_memory=True, num_workers=workers,
shuffle=(sampler is None) and training, collate_fn=dataset.collate_batch,
drop_last=False, sampler=sampler, timeout=0, worker_init_fn=partial(common_utils.worker_init_fn, seed=seed)
)
return dataset, dataloader, sampler
|