注意: 经过实际测试,在ImageNet数据集上并没有达到所说的提升效果,反而会导致代码逻辑混乱,徒增代码量!
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 &