File size: 5,812 Bytes
663494c |
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 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 |
# Copyright (c) OpenMMLab. All rights reserved.
import copy
import platform
import random
from functools import partial
import warnings
import numpy as np
from mmcv.parallel import collate
from mmcv.runner import get_dist_info
from mmcv.utils import Registry, build_from_cfg
from torch.utils.data import DataLoader
from mmdet.datasets.samplers import GroupSampler
from mmdet3d_plugin.datasets.samplers.group_sampler import (
DistributedGroupSampler,
)
from mmdet3d_plugin.datasets.samplers.distributed_sampler import (
DistributedSampler,
)
from mmdet3d_plugin.datasets.samplers.sampler import build_sampler
from mmdet3d_plugin.utils import get_logger
logger = get_logger(__name__)
def build_dataloader(
dataset,
samples_per_gpu,
workers_per_gpu,
num_gpus=1,
dist=True,
shuffle=True,
seed=None,
shuffler_sampler=None,
nonshuffler_sampler=None,
**kwargs
):
"""Build PyTorch DataLoader.
In distributed training, each GPU/process has a dataloader.
In non-distributed training, there is only one dataloader for all GPUs.
Args:
dataset (Dataset): A PyTorch dataset.
samples_per_gpu (int): Number of training samples on each GPU, i.e.,
batch size of each GPU.
workers_per_gpu (int): How many subprocesses to use for data loading
for each GPU.
num_gpus (int): Number of GPUs. Only used in non-distributed training.
dist (bool): Distributed training/test or not. Default: True.
shuffle (bool): Whether to shuffle the data at every epoch.
Default: True.
kwargs: any keyword argument to be used to initialize DataLoader
Returns:
DataLoader: A PyTorch dataloader.
"""
rank, world_size = get_dist_info()
if dist:
# DistributedGroupSampler will definitely shuffle the data to satisfy
# that images on each GPU are in the same group
if shuffle:
logger.info('Use shuffle sampler')
sampler = build_sampler(
shuffler_sampler,
# if shuffler_sampler is not None
# else dict(type="DistributedGroupSampler"),
dict(
dataset=dataset,
samples_per_gpu=samples_per_gpu,
num_replicas=world_size,
rank=rank,
seed=seed,
),
)
else:
sampler = build_sampler(
nonshuffler_sampler
if nonshuffler_sampler is not None
else dict(type="DistributedSampler"),
dict(
dataset=dataset,
num_replicas=world_size,
rank=rank,
shuffle=shuffle,
seed=seed,
),
)
batch_size = samples_per_gpu
num_workers = workers_per_gpu
else:
warnings.warn("Only can be used for obtain inference speed!!!!")
sampler = GroupSampler(dataset, samples_per_gpu) if shuffle else None
batch_size = num_gpus * samples_per_gpu
num_workers = num_gpus * workers_per_gpu
init_fn = (
partial(worker_init_fn, num_workers=num_workers, rank=rank, seed=seed)
if seed is not None
else None
)
# print(f'\n\n\nworkers per gpu is {num_workers}')
data_loader = DataLoader(
dataset,
batch_size=batch_size,
sampler=sampler,
num_workers=num_workers,
collate_fn=partial(collate, samples_per_gpu=samples_per_gpu),
pin_memory=False,
worker_init_fn=init_fn,
**kwargs
)
return data_loader
def worker_init_fn(worker_id, num_workers, rank, seed):
# The seed of each worker equals to
# num_worker * rank + worker_id + user_seed
worker_seed = num_workers * rank + worker_id + seed
np.random.seed(worker_seed)
random.seed(worker_seed)
# Copyright (c) OpenMMLab. All rights reserved.
import platform
from mmcv.utils import Registry, build_from_cfg
from mmdet.datasets import DATASETS
from mmdet.datasets.builder import _concat_dataset
if platform.system() != "Windows":
# https://github.com/pytorch/pytorch/issues/973
import resource
rlimit = resource.getrlimit(resource.RLIMIT_NOFILE)
base_soft_limit = rlimit[0]
hard_limit = rlimit[1]
soft_limit = min(max(4096, base_soft_limit), hard_limit)
resource.setrlimit(resource.RLIMIT_NOFILE, (soft_limit, hard_limit))
OBJECTSAMPLERS = Registry("Object sampler")
def custom_build_dataset(cfg, default_args=None):
from mmdet3d.datasets.dataset_wrappers import CBGSDataset
from mmdet.datasets.dataset_wrappers import (
ClassBalancedDataset,
ConcatDataset,
RepeatDataset,
)
if isinstance(cfg, (list, tuple)):
dataset = ConcatDataset([custom_build_dataset(c, default_args) for c in cfg])
elif cfg["type"] == "ConcatDataset":
dataset = ConcatDataset(
[custom_build_dataset(c, default_args) for c in cfg["datasets"]],
cfg.get("separate_eval", True),
)
elif cfg["type"] == "RepeatDataset":
dataset = RepeatDataset(
custom_build_dataset(cfg["dataset"], default_args), cfg["times"]
)
elif cfg["type"] == "ClassBalancedDataset":
dataset = ClassBalancedDataset(
custom_build_dataset(cfg["dataset"], default_args), cfg["oversample_thr"]
)
elif cfg["type"] == "CBGSDataset":
dataset = CBGSDataset(custom_build_dataset(cfg["dataset"], default_args))
elif isinstance(cfg.get("ann_file"), (list, tuple)):
dataset = _concat_dataset(cfg, default_args)
else:
dataset = build_from_cfg(cfg, DATASETS, default_args)
return dataset
|