kaira.modulations.PAMDemodulator

Inheritance diagram of PAMDemodulator — Inheritance diagram for PAMDemodulator

class kaira.modulations.PAMDemodulator(order: Literal[2, 4, 8, 16, 32, 64], gray_coding: bool = True, normalize: bool = True, *args, **kwargs)[source]

Bases: BaseDemodulator

Pulse Amplitude Modulation (PAM) demodulator.

Demodulates PAM symbols using either: 1. Hard decisions - finding the closest constellation point 2. Soft decisions - computing log-likelihood ratios (LLRs)

Methods

`__init__`	Initialize the PAM demodulator.
`forward`	Demodulate PAM symbols.
`reset_state`	Reset any stateful components.

Attributes

bits_per_symbol

Number of bits per symbol.

__init__(order: Literal[2, 4, 8, 16, 32, 64], gray_coding: bool = True, normalize: bool = True, *args, **kwargs) → None[source]

Initialize the PAM demodulator.

Parameters:

order – Modulation order (must be a power of 2)
gray_coding – Whether Gray coding was used for mapping
normalize – If True, assumes normalized constellation
*args – Variable length argument list.
**kwargs – Arbitrary keyword arguments.

forward(y: Tensor, noise_var: float | Tensor | None = None, *args, **kwargs) → Tensor[source]

Demodulate PAM symbols.

Parameters:

y – Received tensor of PAM symbols (complex, but only real part is used)
noise_var – Noise variance for soft demodulation (optional)
*args – Variable length argument list.
**kwargs – Arbitrary keyword arguments.

Returns:

If noise_var is provided, returns LLRs; otherwise, returns hard bit decisions

property bits_per_symbol: int: Number of bits per symbol.

reset_state() → None

Reset any stateful components.

For demodulators with memory.