mindspore.ops.normal

View Source On Gitee
mindspore.ops.normal(shape, mean, stddev, seed=None)[source]

Return a random tensor that conforms to the normal (Gaussian) distribution.

Warning

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

Parameters

  • shape (tuple) – The shape of returned tensor.

  • mean (Union[Tensor, int, float]) – The mean of the normal distribution for the returned tensor.

  • stddev (Union[Tensor, int, float]) – The standard deviation of the normal distribution for the returned tensor.

  • seed (int, optional) – Random seed. Default: None , which is equivalent to 0.

Returns

Tensor

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> shape = (3, 1, 2)
>>> mean = mindspore.tensor([[3, 4], [5, 6]], mindspore.float32)
>>> stddev = mindspore.tensor(1.0, mindspore.float32)
>>> output = mindspore.ops.normal(shape, mean, stddev, seed=5)
>>> result = output.shape
>>> print(result)
(3, 2, 2)
>>> shape = (3, 1, 3)
>>> mean = mindspore.tensor([[3, 4, 3], [3, 5, 6]], mindspore.float32)
>>> stddev = mindspore.tensor(1.0, mindspore.float32)
>>> output = mindspore.ops.normal(shape, mean, stddev, seed=5)
>>> result = output.shape
>>> print(result)
(3, 2, 3)
>>> shape = (3, 1, 3)
>>> mean = mindspore.tensor([[1, 2, 3], [3, 4, 3], [3, 5, 6]], mindspore.float32)
>>> stddev = mindspore.tensor(1.0, mindspore.float32)
>>> output = mindspore.ops.normal(shape, mean, stddev, seed=5)
>>> result = output.shape
>>> print(result)
(3, 3, 3)