mindspore.Tensor.bernoulli_

Tensor.bernoulli_(p=0.5, *, generator=None)

Fills each location of self with an independent sample from Bernoulli(p).

Parameters

p (Union[number.Number, Tensor], optional) – p should either be a scalar or tensor containing probabilities to be used for drawing the binary random number, between 0 and 1 . If it is a tensor, p must be floating point. Default: 0.5 .

Keyword Arguments

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

Returns

The input tensor.

Supported Platforms:

Ascend

Examples

>>> from mindspore import Tensor
>>> x = Tensor([[2, 3, 4], [1, 2, 3]])
>>> p = 0.1
>>> print(x.bernoulli_(p).shape)
(2, 3)