kaira.models.image.Bourtsoulatze2019DeepJSCCEncoder

Inheritance diagram for Bourtsoulatze2019DeepJSCCEncoder

class kaira.models.image.Bourtsoulatze2019DeepJSCCEncoder(num_transmitted_filters: int, *args: Any, **kwargs: Any)

Bases: BaseModel

DeepJSCC encoder model from [Bourtsoulatze et al., 2019].

This model encodes the input image into a latent representation for transmission.

Parameters:

num_transmitted_filters – Number of filters in the final encoding layer

Methods

__init__	Initialize the Bourtsoulatze2019DeepJSCCEncoder.
forward	Forward pass through the encoder.
from_config	Create model instance from configuration.
from_hydra_config	Create model from Hydra DictConfig.
from_pretrained_config	Create model from Hugging Face PretrainedConfig.

Examples using kaira.models.image.Bourtsoulatze2019DeepJSCCEncoder

Original DeepJSCC Model (Bourtsoulatze 2019) with Training

Original DeepJSCC Model (Bourtsoulatze 2019) with Training

Deep Joint Source-Channel Coding (DeepJSCC) Model - Bourtsoulatze2019 Implementation

Deep Joint Source-Channel Coding (DeepJSCC) Model - Bourtsoulatze2019 Implementation

__init__(num_transmitted_filters: int, *args: Any, **kwargs: Any)

Initialize the Bourtsoulatze2019DeepJSCCEncoder.

Parameters:

• num_transmitted_filters – Number of filters in the final encoding layer.

• *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 – Input image tensor of shape (B, 3, H, W)

• *args – Additional positional arguments (unused).

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

Returns:

Encoded representation of shape (B, num_transmitted_filters, H//4, W//4)

classmethod from_config(config, **kwargs)

Create model instance from configuration.

Parameters:

• config – Configuration object (PretrainedConfig, DictConfig, or dict)

• **kwargs – Additional parameters to override config

Returns:

Model instance

classmethod from_hydra_config(config: DictConfig, **kwargs)

Create model from Hydra DictConfig.

Parameters:

• config – Hydra configuration

• **kwargs – Additional parameters

Returns:

Model instance

classmethod from_pretrained_config(config: PretrainedConfig, **kwargs)

Create model from Hugging Face PretrainedConfig.

Parameters:

• config – PretrainedConfig instance

• **kwargs – Additional parameters

Returns:

Model instance