固定住训练的顺序等变量，使实验可复现
def setup_seed(seed):
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
np.random.seed(seed)
random.seed(seed)
torch.backends.cudnn.deterministic = True
setup_seed(1)http://www.ishenping.com/ArtInfo/3265474.html
https://www.lizenghai.com/archives/30179.html
原文：https://www.cnblogs.com/alilliam/p/12022452.html