mindspore.ops.standard_normal

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

Generates random numbers according to the standard Normal (or Gaussian) random number distribution.

Returns the tensor with the given shape, the random numbers in it drawn from normal distributions whose mean is 0 and standard deviation is 1.

\[f(x)=\frac{1}{\sqrt{2 \pi}} e^{\left(-\frac{x^{2}}{2}\right)}\]

Warning

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

Parameters

  • shape (Union[tuple, Tensor]) – The shape of random tensor to be generated. Only constant value is allowed when the input type is tuple. And the operator supports dynamic shape only when the input type is Tensor.

  • seed (int, optional) – Seed is used as entropy source for Random number engines generating pseudo-random numbers. Default: None , which will be treated as 0.

Returns

Tensor. The shape that the input 'shape' denotes. The dtype is float32.

Raises

  • TypeError – If shape is neither a tuple nor a Tensor.

  • ValueError – If shape is a tuple containing non-positive items.

Supported Platforms:

Ascend GPU CPU

Examples

>>> from mindspore import ops
>>> shape = (4, 4)
>>> output = ops.standard_normal(shape)
>>> result = output.shape
>>> print(result)
(4, 4)