mindspore.ops.randn_like

mindspore.ops.randn_like(input, seed=None, *, dtype=None)[source]

Return a tensor with the same shape as input, filled with random numbers from the standard normal distribution.

Warning

  • Non-backward-compatible change after version 2.9.0: seed will be removed, and generator and device parameters will be added.

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

Parameters

  • input (Tensor) – The input tensor.

  • seed (int, optional) – Random seed, must be non-negative. Default None .

Keyword Arguments

dtype (mindspore.dtype, optional) – The data type returned. Default None .

Returns

Tensor

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> a = mindspore.tensor([[1, 2, 3], [4, 5, 6]])
>>> print(mindspore.ops.randn_like(a, dtype=mindspore.float32))
[[ 0.30639967 -0.42438635 -0.20454668]
 [-0.4287376   1.3054721   0.64747655]]