standard_normal

deeptrack.backend.array_api_compat_ext.torch.random.standard_normal(size: tuple[int, ...] | None = None) → Tensor

Sample from the standard normal distribution.

Mirrors numpy.random.standard_normal.

Parameters

size: tuple[int, …] | None, optional

Output shape. If None, returns a scalar tensor.

Returns

torch.Tensor

Samples drawn from N(0, 1).

Examples

>>> import deeptrack.backend.array_api_compat_ext.torch.random as rnd

>>> rnd.standard_normal((2, 3)).shape
torch.Size([2, 3])

>>> rnd.standard_normal()
tensor(-1.2938)