pytorch的linspace, rand, randn, normal

Posted 2021-03-08 picassooo

torch.linspace

torch.linspace(start, end, steps) returns a one-dimensional tensor of equally spaced points between [start, end]。steps默认值是100。

torch.rand

 torch.rand(size) returns a tensor filled with random numbers from a uniform distribution on the interval [0, 1).

torch.randn

torch.randn(size) returns a tensor filled with random numbers from a normal distribution with mean `0` and variance `1` (also called the standard normal distribution).

torch.normal

torch.normal returns a tensor of random numbers drawn from separate normal distributions whose mean and standard deviation are given.

The arguments `mean` is a tensor with the mean of each output element‘s normal distribution.

The arguments `std` is a tensor with the standard deviation of each output element‘s normal distribution.

torch.normal的参数给定方法有很多种：

第一种：给定mean (Tensor)和std (Tensor)

 第二种：给定mean(float)和std (Tensor)

第三种：给定mean (Tensor)和std (float)，std也可不给，若不给定，则默认为1.0

 第四种：给定mean (float)、std (float)和size(int...)

 参考文献：PyTorch帮助文档