def __iter__(self) -> Iterator[T_co]:
        if self.shuffle:
            # deterministically shuffle based on epoch and seed
            g = torch.Generator()
            g.manual_seed(self.seed + self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()  # type: ignore
        else:
            indices = list(range(len(self.dataset)))  # type: ignore

for epoch in range(start_epoch, n_epochs):
    if is_distributed:
        sampler.set_epoch(epoch)
    train(loader)

# copy from https://github.com/ildoonet/pytorch-gradual-warmup-lr/blob/master/warmup_scheduler/scheduler.py
from torch.optim.lr_scheduler import _LRScheduler
from torch.optim.lr_scheduler import ReduceLROnPlateau
class GradualWarmupScheduler(_LRScheduler):
    """ Gradually warm-up(increasing) learning rate in optimizer.
    Proposed in 'Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour'.
    Args:
        optimizer (Optimizer): Wrapped optimizer.
        multiplier: target learning rate = base lr * multiplier if multiplier > 1.0. if multiplier = 1.0, lr starts from 0 and ends up with the base_lr.
        total_epoch: target learning rate is reached at total_epoch, gradually
        after_scheduler: after target_epoch, use this scheduler(eg. ReduceLROnPlateau)
    """
    def __init__(self, optimizer, multiplier, total_epoch, after_scheduler=None):
        self.multiplier = multiplier
        if self.multiplier < 1.:
            raise ValueError('multiplier should be greater thant or equal to 1.')
        self.total_epoch = total_epoch
        self.after_scheduler = after_scheduler
        self.finished = False
        super(GradualWarmupScheduler, self).__init__(optimizer)
    def get_lr(self):
        if self.last_epoch > self.total_epoch:
            if self.after_scheduler:
                if not self.finished:
                    self.after_scheduler.base_lrs = [base_lr * self.multiplier for base_lr in self.base_lrs]
                    self.finished = True
                return self.after_scheduler.get_last_lr()
            return [base_lr * self.multiplier for base_lr in self.base_lrs]
        if self.multiplier == 1.0:
            return [base_lr * (float(self.last_epoch) / self.total_epoch) for base_lr in self.base_lrs]
        else:
            return [base_lr * ((self.multiplier - 1.) * self.last_epoch / self.total_epoch + 1.) for base_lr in self.base_lrs]
    def step_ReduceLROnPlateau(self, metrics, epoch=None):
        if epoch is None:
            epoch = self.last_epoch + 1
        self.last_epoch = epoch if epoch != 0 else 1  # ReduceLROnPlateau is called at the end of epoch, whereas others are called at beginning
        if self.last_epoch <= self.total_epoch:
            warmup_lr = [base_lr * ((self.multiplier - 1.) * self.last_epoch / self.total_epoch + 1.) for base_lr in self.base_lrs]
            for param_group, lr in zip(self.optimizer.param_groups, warmup_lr):
                param_group['lr'] = lr
        else:
            if epoch is None:
                self.after_scheduler.step(metrics, None)
            else:
                self.after_scheduler.step(metrics, epoch - self.total_epoch)
    def step(self, epoch=None, metrics=None):
        if type(self.after_scheduler) != ReduceLROnPlateau:
            if self.finished and self.after_scheduler:
                if epoch is None:
                    self.after_scheduler.step(None)
                else:
                    self.after_scheduler.step(epoch - self.total_epoch)
                self._last_lr = self.after_scheduler.get_last_lr()
            else:
                return super(GradualWarmupScheduler, self).step(epoch)
        else:
            self.step_ReduceLROnPlateau(metrics, epoch)

from torch.nn import DataParallel
 
device = torch.device("cuda")
?；蛘遜evice = torch.device("cuda:0" if True else "cpu")
 
model = MyModel()
model = model.to(device)
model = DataParallel(model)
?；蛘適odel = nn.DataParallel(model,device_ids=[0,1，2,3])

    from torch.utils.data.distributed import DistributedSampler
    import torch.distributed as dist
    import torch
 
    # Initialize Process Group
    dist_backend = 'nccl'
    print('args.local_rank: ', opt.local_rank)
    torch.cuda.set_device(opt.local_rank)
    dist.init_process_group(backend=dist_backend)
 
    model = yourModel()＃自己的模型
    if torch.cuda.device_count() > 1:
        print("Let's use", torch.cuda.device_count(), "GPUs!")
        # 5) 封裝
        # model = torch.nn.parallel.DistributedDataParallel(model,
        #                                                   device_ids=[opt.local_rank],
        #                                                   output_device=opt.local_rank)
        model = torch.nn.parallel.DistributedDataParallel(model.cuda(), device_ids=[opt.local_rank])
    device = torch.device(opt.local_rank)
    model.to(device)
    dataset = ListDataset(train_path, augment=True, multiscale=opt.multiscale_training, img_size=opt.img_size, normalized_labels=True)#自己的讀取數(shù)據(jù)的代碼
    world_size = torch.cuda.device_count()
    datasampler = DistributedSampler(dataset, num_replicas=dist.get_world_size(), rank=opt.local_rank)
 
    dataloader = torch.utils.data.DataLoader(
        dataset,
        batch_size=opt.batch_size,
        shuffle=False,
        num_workers=opt.n_cpu,
        pin_memory=True,
        collate_fn=dataset.collate_fn,
        sampler=datasampler
    )＃在原始讀取數(shù)據(jù)中加sampler參數(shù)就行
 
 
.....
 
訓(xùn)練過程中，數(shù)據(jù)轉(zhuǎn)cuda
      imgs = imgs.to(device)
      targets = targets.to(device)

CUDA_VISIBLE_DEVICES=0,1 python3 -m torch.distributed.launch --nproc_per_node=2 train.py

python３ -m torch.distributed.launch --nproc_per_node=NUM_GPUS_YOU_HAVE --nnodes=2 --node_rank=0
＃兩個節(jié)點(diǎn)，在０號節(jié)點(diǎn)

torch.save(model.module.state_dict(), path)

torch.save(model.module,path)

model = Yourmodel()
if opt.pretrained_weights:
        if opt.pretrained_weights.endswith(".pth"):
            model.load_state_dict(torch.load(opt.pretrained_weights))
        else:
            model.load_darknet_weights(opt.pretrained_weights)

model = Yourmodel()
if opt.pretrained_weights:
        if opt.pretrained_weights.endswith(".pth"):
            model.load_state_dict(torch.load(opt.pretrained_weights，map_location="cuda:0"))
        else:
            model.load_darknet_weights(opt.pretrained_weights)

model = torch.load(opt.weights_path, map_location="cuda:0")

model.img_size　　要改成　　model.module.img_size

parser.add_argument("--local_rank", type=int, default=-1, help="number of cpu threads to use during batch generation")