kaira.models.binary.soft_bit_thresholding.FixedThresholder

Inheritance diagram for FixedThresholder
- class kaira.models.binary.soft_bit_thresholding.FixedThresholder(threshold: float = 0.5, input_type: InputType = InputType.PROBABILITY, *args: Any, **kwargs: Any)[source]
Bases:
SoftBitThresholderSimple fixed threshold for soft bit values.
Applies a fixed threshold to convert soft bit values to hard decisions. For probability inputs (in range [0,1]), the default threshold is 0.5. For LLR inputs, the default threshold is 0.0.
Example
With threshold=0.5 and input [0.2, 0.7, 0.4, 0.9]: Output will be [0.0, 1.0, 0.0, 1.0]
Methods
Initialize the fixed thresholder.
Apply fixed thresholding to convert soft bit values to hard decisions.
Create model instance from configuration.
Create model from Hydra DictConfig.
Create model from Hugging Face PretrainedConfig.
Move the model to the specified device.
- __init__(threshold: float = 0.5, input_type: InputType = InputType.PROBABILITY, *args: Any, **kwargs: Any)[source]
Initialize the fixed thresholder.
- Parameters:
threshold – The threshold value to use. Default is 0.5 for probabilities.
input_type – Type of soft input, can be ‘prob’ (probabilities between 0 and 1) or ‘llr’ (log-likelihood ratios). Affects the default threshold if not specified.
*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[source]
Apply fixed thresholding to convert soft bit values to hard decisions.
- Parameters:
x – Input tensor of soft bit values.
*args – Additional positional arguments (unused).
**kwargs – Additional keyword arguments (unused).
- Returns:
Tensor of hard bit decisions (0.0 or 1.0).
- 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
- to(device: str | device, *args, **kwargs) SoftBitThresholder
Move the model to the specified device.
- Parameters:
device – The device to move the model to.
*args – Additional positional arguments for nn.Module.to().
**kwargs – Additional keyword arguments for nn.Module.to().
- Returns:
Self for method chaining.