normalization_2d

Fixed mean/variance normalization for two-dimensional signals.

Machine-readable model

• Normalization2DclassApply fixed mean/variance normalization to 2D inputs.

class

Normalization2D

Python

Apply fixed mean/variance normalization to 2D inputs.

helia_edge/layers/preprocessing/normalization_2d.py:9

Normalization2D(
    mean: float | list[float] | tuple[float, ...],
    variance: float | list[float] | tuple[float, ...],
    epsilon: float = 1e-06,
    name: str | None = None,
    **kwargs={},
)

Apply fixed mean/variance normalization to 2D inputs.

Base class: BaseAugmentation2D.

Inherited from BaseAugmentation: augment_masks(), augment_sample(), augment_targets(), batch_augment(), call(), get_random_transformations().

Parameters

Parameters of Normalization2D

Name	Type	Default	Description
mean	float | list[float] | tuple[float, ...]	Required	Mean value(s) used for normalization.
variance	float | list[float] | tuple[float, ...]	Required	Variance value(s) used for normalization.
epsilon	float	1e-06	Small value to avoid division by zero.
name	str | None	None	Layer name.

attribute

training_only

Python

helia_edge/layers/preprocessing/normalization_2d.py:11

training_only = False

attribute

mean

Python

helia_edge/layers/preprocessing/normalization_2d.py:33

mean: float | list[float] | tuple[float, ...] = mean

attribute

variance

Python

helia_edge/layers/preprocessing/normalization_2d.py:34

variance: float | list[float] | tuple[float, ...] = variance

attribute

epsilon

Python

helia_edge/layers/preprocessing/normalization_2d.py:35

epsilon: float = epsilon

method

augment_samples

Python

Normalize a batch of samples.

helia_edge/layers/preprocessing/normalization_2d.py:37

augment_samples(inputs) -> keras.KerasTensor

Normalize a batch of samples.

method

get_config

Python

Serialize the configuration.

helia_edge/layers/preprocessing/normalization_2d.py:48

get_config()

Serialize the configuration.