mindspore.ops.randn

View Source On Gitee
mindspore.ops.randn(*size, dtype=None, seed=None)[source]

Returns a new Tensor with given shape and dtype, filled with a sample (or samples) from the standard normal distribution.

Warning

The Ascend backend does not support the reproducibility of random numbers, so the seed parameter has no effect.

Parameters

size (Union[int, tuple(int), list(int)]) – Shape of the new tensor, e.g., \((2, 3)\) or \(2\).

Keyword Arguments

  • dtype (mindspore.dtype, optional) – Designated tensor dtype, it must be float type. If None, mindspore.float32 will be used. Default: None .

  • seed (int, optional) – Random seed, must be greater or equal to 0. Default: None , and 0 will be used.

Returns

Tensor, with the designated shape and dtype, filled with a sample (or samples) from the "standard normal" distribution.

Raises

  • TypeError – seed is not a non-negative integer.

  • ValueError – If dtype is not a mstype.float_type.

  • ValueError – If size contains invalid number.

Supported Platforms:

Ascend GPU CPU

Examples

>>> from mindspore import ops
>>> print(ops.randn((2, 2)))
[[ 0.30639967 -0.42438635]
 [-0.4287376   1.3054721 ]]