normalization

Mean/Variance Normalization Layer API

This module provides classes to build fixed mean/variance normalization layers.

Classes

Name	Description
Normalization1D	Mean/variance normalization for 1D data.
Normalization2D	Mean/variance normalization for 2D data.

Machine-readable model

• Normalization1DclassApply fixed mean/variance normalization to 1D inputs.

class

Normalization1D

Python

Apply fixed mean/variance normalization to 1D inputs.

helia_edge/layers/preprocessing/normalization.py:17

Normalization1D(
    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 1D inputs.

Base class: BaseAugmentation1D.

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

Parameters

Parameters of Normalization1D

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.py:19

training_only = False

attribute

mean

Python

helia_edge/layers/preprocessing/normalization.py:41

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

attribute

variance

Python

helia_edge/layers/preprocessing/normalization.py:42

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

attribute

epsilon

Python

helia_edge/layers/preprocessing/normalization.py:43

epsilon: float = epsilon

method

augment_samples

Python

Normalize a batch of samples.

helia_edge/layers/preprocessing/normalization.py:45

augment_samples(inputs) -> keras.KerasTensor

Normalize a batch of samples.

method

get_config

Python

Serialize the configuration.

helia_edge/layers/preprocessing/normalization.py:56

get_config()

Serialize the configuration.