Pytorch数据读取加速方法

1. 方法一：使用prefetcher

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)
            
    def next(self):
        torch.cuda.current_stream().wait_stream(self.stream)
        input = self.next_input
        target = self.next_target
        self.preload()
        return input, target

使用方式：

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

---

参考：

1. zhihu 给pytorch 读取数据加速;
2. Github NVIDIA apex