Pytorch 如何加速Dataloader提升数据读取速度

class data_prefetcher():
    def __init__(self, loader):
        self.loader = iter(loader)
        self.stream = torch.cuda.Stream()
        self.mean = torch.tensor([0.485 * 255, 0.456 * 255, 0.406 * 255]).cuda().view(1,3,1,1)
        self.std = torch.tensor([0.229 * 255, 0.224 * 255, 0.225 * 255]).cuda().view(1,3,1,1)
        # With Amp, it isn't necessary to manually convert data to half.
        # if args.fp16:
        #     self.mean = self.mean.half()
        #     self.std = self.std.half()
        self.preload()

    def preload(self):
        try:
            self.next_input, self.next_target = next(self.loader)
        except StopIteration:
            self.next_input = None
            self.next_target = None
            return
        with torch.cuda.stream(self.stream):
            self.next_input = self.next_input.cuda(non_blocking=True)
            self.next_target = self.next_target.cuda(non_blocking=True)
            # With Amp, it isn't necessary to manually convert data to half.
            # if args.fp16:
            #     self.next_input = self.next_input.half()
            # else:
            self.next_input = self.next_input.float()
            self.next_input = self.next_input.sub_(self.mean).div_(self.std)

training_data_loader = DataLoader(
    dataset=train_dataset,
    num_workers=opts.threads,
    batch_size=opts.batchSize,
    pin_memory=True,
    shuffle=True,
)
for iteration, batch in enumerate(training_data_loader, 1):
    # 训练代码

#-------------升级后---------

data, label = prefetcher.next()
iteration = 0
while data is not None:
    iteration += 1
    # 训练代码
    data, label = prefetcher.next()

dataloader = torch.utils.data.DataLoader(COCODataset(config["train_path"],
                                                     (config["img_w"], config["img_h"]),
                                                     is_training=True),
                                         batch_size=config["batch_size"],
                                         shuffle=True, num_workers=32, pin_memory=True)

fuser -v /dev/nvidia*