Pytorch torch.empty(a, b) torch.rand(a, b)

torch.empty(a, b)

创建一个axb的未初始化的Tensor

>>> import torch
>>> x = torch.empty(5, 3)
>>> print(x)
tensor([[ 0.0000e+00, -0.0000e+00,  1.0970e+32],
        [-1.0845e-19,  1.1210e-44, -0.0000e+00],
        [ 0.0000e+00,  0.0000e+00,  0.0000e+00],
        [ 1.4013e-45,  0.0000e+00,  0.0000e+00],
        [ 0.0000e+00,  0.0000e+00,  0.0000e+00]])
>>> print(x.stride())	
(3, 1)

torch.rand(a, b)

创建一个axb的随机初始化的Tensor

>>> import torch
>>> x = torch.rand(5, 3)
>>> print(x)
tensor([[0.5351, 0.7316, 0.8640],
        [0.3472, 0.8160, 0.9679],
        [0.2291, 0.5502, 0.2504],
        [0.4305, 0.9878, 0.7043],
        [0.6687, 0.3447, 0.6710]])
>>> print(x.stride())
(3, 1)