torch.rand 和 torch.randn

torch.rand(*size)

生成在区间 [0,1) 之间的呈均匀分布的随机数

torch.rand(*size, *, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) → Tensor
Returns a tensor filled with random numbers from a uniform distribution on the interval [0, 1)[0,1)

The shape of the tensor is defined by the variable argument size.

Example:

>>>torch.rand(4)
tensor([ 0.5204,  0.2503,  0.3525,  0.5673])
>>>torch.rand(2, 3)
tensor([[ 0.8237,  0.5781,  0.6879],
        [ 0.3816,  0.7249,  0.0998]])

torch.randn(*size)

生成形状为size的标准正态分布

Returns a tensor filled with random numbers from a normal distribution with mean 0 and variance 1 (also called the standard normal distribution).

\text{out}_{i} \sim \mathcal{N}(0, 1)
out 
i
​
 ∼N(0,1)
The shape of the tensor is defined by the variable argument size.

Example

>>> torch.randn(4)
tensor([-2.1436,  0.9966,  2.3426, -0.6366])
>>> torch.randn(2, 3)
tensor([[ 1.5954,  2.8929, -1.0923],
        [ 1.1719, -0.4709, -0.1996]])