kaira.models.ConfigurableModel

Inheritance diagram for ConfigurableModel

class kaira.models.ConfigurableModel(config=None, *args: Any, **kwargs: Any)

Bases: BaseModel

Model that supports dynamically adding and removing steps.

This class extends the basic model functionality with methods to add, remove, and manage model steps during runtime.

Methods

__init__	Initialize the configurable model.
add_step	Add a processing step to the model.
forward	Process input through all steps sequentially.
from_config	Create model instance from configuration.
from_hydra_config	Create model from Hydra DictConfig.
from_pretrained_config	Create model from Hugging Face PretrainedConfig.
remove_step	Remove a processing step from the model.

Examples using kaira.models.ConfigurableModel

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__(config=None, *args: Any, **kwargs: Any)

Initialize the configurable model.

add_step(step: Callable) → ConfigurableModel

Add a processing step to the model.

Parameters:

step – A callable that will be added to the processing pipeline. Must accept and return tensor-like objects.

Returns:

Self for method chaining

remove_step(index: int) → ConfigurableModel

Remove a processing step from the model.

Parameters:

index – The index of the step to remove

Returns:

Self for method chaining

Raises:

IndexError – If the index is out of range

forward(input_data: Any, *args: Any, **kwargs: Any) → Any

Process input through all steps sequentially.

Parameters:

• input_data (Any) – The input to process

• *args (Any) – Positional arguments passed to each step

• **kwargs (Any) – Additional keyword arguments passed to each step

Returns:

The result after applying all steps

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