通过torch.normal创建四种模式的正态分布张量

1. torch.normal(mean, std, out=None)
2. 功能：生成正态分布（高斯分布）
   • mean: 均值
   • std: 标准差
   • 四种模式：
     • mean为标量，std为标量
     • mean为标量，std为张量
     • mean为张量，std为标量
     • mean为张量，std为张量

       torch.normal(0,1,size=(1,5))
       tensor([[ 0.5548,  0.1402,  0.5849,  1.2391, -0.2564]])
       
       torch.normal(0,std=torch.arange(1, 0, -0.1))
       tensor([-0.6172, -0.1014,  0.0054, -0.0847,  0.2791, -0.0295, -0.1140, -0.3000,
               -0.2172,  0.0075])
       
       torch.normal(mean=torch.arange(1., 11.),std = 10)
       tensor([  0.0548,  33.3666,   6.6326,  -3.3032,  16.0448,  18.3752, -12.6373,
                -0.1594,  16.0896,  12.4073])
       
       torch.normal(mean=torch.arange(1., 11.), std=torch.arange(1, 0, -0.1))
       tensor([-0.1131,  2.1779,  2.9984,  3.9909,  4.2449,  6.1312,  6.7345,  7.6574,
                8.8338, 10.1323])