CRCDecoder#

class sionna.phy.fec.crc.CRCDecoder(crc_encoder: sionna.phy.fec.crc.CRCEncoder, *, precision: str | None = None, device: str | None = None, **kwargs)[source]#

Bases: sionna.phy.block.Block

Allows Cyclic Redundancy Check (CRC) verification and removes parity bits.

The CRC polynomials from Sec. 5.1 in [3GPPTS38212] are available: {CRC24A, CRC24B, CRC24C, CRC16, CRC11, CRC6}.

Parameters:

  • crc_encoder (sionna.phy.fec.crc.CRCEncoder) – An instance of CRCEncoder associated with the CRCDecoder.

  • precision (str | None) – Precision used for internal calculations and outputs. If None, precision is used.

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

Inputs:

x_crc – […, k + crc_length], torch.float. Binary tensor containing the CRC-encoded bits (the last crc_length bits are parity bits).

Outputs:

  • bits – […, k], torch.float. Binary tensor containing the information bit sequence without CRC parity bits.

  • crc_valid – […, 1], torch.bool. Boolean tensor containing the result of the CRC check per codeword.

Examples

import torch
from sionna.phy.fec.crc import CRCEncoder, CRCDecoder

encoder = CRCEncoder("CRC24A")
decoder = CRCDecoder(encoder)

bits = torch.randint(0, 2, (10, 100), dtype=torch.float32)
encoded = encoder(bits)
decoded, crc_valid = decoder(encoded)
print(decoded.shape, crc_valid.all())
# torch.Size([10, 100]) tensor(True)

Attributes

property crc_degree: str#

CRC degree as string.

property encoder: sionna.phy.fec.crc.CRCEncoder#

CRC Encoder used for internal validation.

Methods

build(input_shape: Tuple[int, ...]) → None[source]#

Check shapes.

Parameters:

input_shape (Tuple[int, ...])