# tensorplay.functional.bernoulli

Source: https://www.tensorplay.cn/docs/generated/tensorplay.functional.bernoulli.html

```python
tensorplay.functional.bernoulli(input: Tensor, *, generator: Generator | None, out: Tensor | None) → Tensor
```

Draws binary random numbers (0 or 1) from a Bernoulli distribution.

The input tensor should be a tensor containing probabilities
to be used for drawing the binary random number.
Hence, all values in input have to be in the range:
$0 \leq \text{input}_i \leq 1$.

The $\text{i}^{th}$ element of the output tensor will draw a
value $1$ according to the $\text{i}^{th}$ probability value given
in input.

$$\text{out}_{i} \sim \mathrm{Bernoulli}(p = \text{input}_{i})$$

The returned out tensor only has values 0 or 1 and is of the same
shape as input.

out can have integral dtype, but input must have floating
point dtype.

Parameters:

input ([Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor)) – the input tensor of probability values for the Bernoulli distribution

Keyword Arguments:

- generator ([tensorplay.Generator](/docs/generated/tensorplay.Generator.html#tensorplay.Generator), optional) – a pseudorandom number generator for sampling

- out ([Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor), optional) – the output tensor.

Example:

```
>>> a = tensorplay.empty(3, 3).uniform_(0, 1)  # generate a uniform random matrix with range [0, 1]
>>> a
tensor([[ 0.1737,  0.0950,  0.3609],
        [ 0.7148,  0.0289,  0.2676],
        [ 0.9456,  0.8937,  0.7202]])
>>> tensorplay.bernoulli(a)
tensor([[ 1.,  0.,  0.],
        [ 0.,  0.,  0.],
        [ 1.,  1.,  1.]])

>>> a = tensorplay.ones(3, 3) # probability of drawing "1" is 1
>>> tensorplay.bernoulli(a)
tensor([[ 1.,  1.,  1.],
        [ 1.,  1.,  1.],
        [ 1.,  1.,  1.]])
>>> a = tensorplay.zeros(3, 3) # probability of drawing "1" is 0
>>> tensorplay.bernoulli(a)
tensor([[ 0.,  0.,  0.],
        [ 0.,  0.,  0.],
        [ 0.,  0.,  0.]])
```