# tensorplay.functional.normal

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

```python
tensorplay.functional.normal(mean, std, *, generator=None, out=None) → Tensor
```

Returns a tensor of random numbers drawn from separate normal distributions
whose mean and standard deviation are given.

The [mean](/docs/generated/tensorplay.functional.mean.html#tensorplay.functional.mean) is a tensor with the mean of
each output element’s normal distribution

The [std](/docs/generated/tensorplay.functional.std.html#tensorplay.functional.std) is a tensor with the standard deviation of
each output element’s normal distribution

The shapes of [mean](/docs/generated/tensorplay.functional.mean.html#tensorplay.functional.mean) and [std](/docs/generated/tensorplay.functional.std.html#tensorplay.functional.std) don’t need to match, but the
total number of elements in each tensor need to be the same.

> **Note**
>
> When the shapes do not match, the shape of mean is used as the shape for the returned output tensor

> **Note**
>
> When std is a CUDA tensor, this function synchronizes its device with the CPU.

Parameters:

- mean ([Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor)) – the tensor of per-element means

- std ([Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor)) – the tensor of per-element standard deviations

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:

```
>>> tensorplay.normal(mean=tensorplay.arange(1., 11.), std=tensorplay.arange(1, 0, -0.1))
tensor([  1.0425,   3.5672,   2.7969,   4.2925,   4.7229,   6.2134,
          8.0505,   8.1408,   9.0563,  10.0566])
```

```python
tensorplay.functional.normal(mean=0.0, std, *, out=None) → Tensor
```

Similar to the function above, but the means are shared among all drawn
elements.

Parameters:

- mean ([float](https://docs.python.org/3/builtins/functions.html#float), optional) – the mean for all distributions

- std ([Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor)) – the tensor of per-element standard deviations

Keyword Arguments:

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

Example:

```
>>> tensorplay.normal(mean=0.5, std=tensorplay.arange(1., 6.))
tensor([-1.2793, -1.0732, -2.0687,  5.1177, -1.2303])
```

```python
tensorplay.functional.normal(mean, std=1.0, *, out=None) → Tensor
```

Similar to the function above, but the standard deviations are shared among
all drawn elements.

Parameters:

- mean ([Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor)) – the tensor of per-element means

- std ([float](https://docs.python.org/3/builtins/functions.html#float), optional) – the standard deviation for all distributions

Keyword Arguments:

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

Example:

```
>>> tensorplay.normal(mean=tensorplay.arange(1., 6.))
tensor([ 1.1552,  2.6148,  2.6535,  5.8318,  4.2361])
```

```python
tensorplay.functional.normal(mean, std, size, *, out=None) → Tensor
```

Similar to the function above, but the means and standard deviations are shared
among all drawn elements. The resulting tensor has size given by size.

Parameters:

- mean ([float](https://docs.python.org/3/builtins/functions.html#float)) – the mean for all distributions

- std ([float](https://docs.python.org/3/builtins/functions.html#float)) – the standard deviation for all distributions

- size ([int](https://docs.python.org/3/builtins/functions.html#int)...) – a sequence of integers defining the shape of the output tensor.

Keyword Arguments:

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

Example:

```
>>> tensorplay.normal(2, 3, size=(1, 4))
tensor([[-1.3987, -1.9544,  3.6048,  0.7909]])
```