mindspore.Tensor.normal_

Tensor.normal_(mean=0, std=1, *, generator=None)[source]

Update the self tensor in place by generating random numbers sampled from the normal distribution which is constructed by the parameters mean and std.

Warning

This is an experimental API that is subject to change or deletion.

Parameters:

mean (Union[bool, int, float], optional) – the mean of normal distribution. Default: 0.
std (Union[bool, int, float], optional) – the std of normal distribution. Default: 1.

Keyword Arguments:

generator (mindspore.Generator, optional) – a pseudorandom number generator. Default: None, uses the default pseudorandom number generator.

Returns:

A tensor that is filled with random numbers that follow a normal distribution and that has the same type and shape as the self tensor.

Raises:

TypeError – If the dtype of mean or std is not one of: bool, int, float.

Supported Platforms:: Ascend

Examples

>>> import mindspore
>>> import numpy as np
>>> x = mindspore.Tensor(np.array([[1, 2], [3, 4]]), dtype=mindspore.float32)
>>> output = x.normal_()
>>> print(output)
[[0.2788825 1.3305743]
 [1.244194 1.16303174]]