Object#

class sionna.phy.object.Object(*args: Any, precision: str | None = None, device: str | None = None, **kwargs: Any)[source]#

Bases: torch.nn.modules.module.Module

Base class for Sionna PHY objects.

Parameters:

  • precision (str | None) – Floating-point precision (‘single’ or ‘double’) to be used within the block. If None, precision is used. Defaults to None.

  • device (str | None) – Device for computation (e.g., ‘cpu’, ‘cuda:0’) to be used within the block. If None, device is used. Defaults to None.

  • args (Any)

  • kwargs (Any)

Attributes

property cdtype: torch.dtype#

Get the PyTorch complex-valued dtype based on the current precision.

property device: str#

Get the device for computation (e.g., ‘cpu’, ‘cuda:0’).

property dtype: torch.dtype#

Get the PyTorch real-valued dtype based on the current precision.

property np_cdtype: type#

Get the NumPy complex-valued dtype based on the current precision.

property np_dtype: type#

Get the NumPy real-valued dtype based on the current precision.

property np_rng: numpy.random._generator.Generator#

Get the NumPy random number generator.

property precision: Literal['single', 'double']#

Get the floating-point precision (‘single’ or ‘double’).

property py_rng: random.Random#

Get the Python random number generator.

property torch_rng: torch._C.Generator#

Get the PyTorch random number generator for the object’s device.