kaira.models.image.Tung2022DeepJSCCQEncoder

Inheritance diagram for Tung2022DeepJSCCQEncoder

class kaira.models.image.Tung2022DeepJSCCQEncoder(N: int, M: int, in_ch: int = 3, *args: Any, **kwargs: Any)

Bases: BaseModel

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

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

Methods

__init__	Initialize the DeepJSCCQEncoder.
forward	Forward pass through the encoder.

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

Initialize the DeepJSCCQEncoder.

Parameters:

• N (int) – The number of output channels for the ResidualBlocks in the g_a module.

• M (int) – The number of output channels in the last convolutional layer of the network.

• in_ch (int, optional) – The number of input 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 encoder.

Parameters:

• x (torch.Tensor) – The input image.

• *args – Additional positional arguments (unused).

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

Returns:

The encoded latent representation.

Return type:

torch.Tensor