kaira.models.image.Tung2022DeepJSCCQDecoder

Inheritance diagram for Tung2022DeepJSCCQDecoder

class kaira.models.image.Tung2022DeepJSCCQDecoder(N: int, M: int, out_ch: int = 3, *args: Any, **kwargs: Any)

Bases: BaseModel

DeepJSCCQ Decoder Module [Tung et al., 2022].

This module decodes a latent representation into an image using a series of convolutional layers and AFModules.

Methods

__init__	Initialize the DeepJSCCQDecoder.
forward	Forward pass through the decoder.

__init__(N: int, M: int, out_ch: int = 3, *args: Any, **kwargs: Any) → None

Initialize the DeepJSCCQDecoder.

Parameters:

• N (int) – The number of input channels.

• M (int) – The number of output channels.

• out_ch (int, optional) – The number of output channels. Defaults to 3.

• *args – Variable positional arguments passed to the base class.

• **kwargs – Variable keyword arguments passed to the base class.

forward(x: Tensor, *args: Any, **kwargs: Any) → Tensor

Forward pass through the decoder.

Parameters:

• x (torch.Tensor) – The encoded latent representation.

• *args – Additional positional arguments (unused).

• **kwargs – Additional keyword arguments (unused).

Returns:

The decoded image.

Return type:

torch.Tensor