# helia_edge.layers.preprocessing.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. |

## helia_edge.layers.preprocessing.normalization.Normalization1D

`class` · `python`

```python
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](/helia-edge/reference/api/helia_edge/layers/preprocessing/base_augmentation/#helia_edge.layers.preprocessing.base_augmentation.BaseAugmentation1D).

Inherited from [BaseAugmentation](/helia-edge/reference/api/helia_edge/layers/preprocessing/base_augmentation/#helia_edge.layers.preprocessing.base_augmentation.BaseAugmentation): [augment_masks()](/helia-edge/reference/api/helia_edge/layers/preprocessing/base_augmentation/#helia_edge.layers.preprocessing.base_augmentation.BaseAugmentation.augment_masks), [augment_sample()](/helia-edge/reference/api/helia_edge/layers/preprocessing/base_augmentation/#helia_edge.layers.preprocessing.base_augmentation.BaseAugmentation.augment_sample), [augment_targets()](/helia-edge/reference/api/helia_edge/layers/preprocessing/base_augmentation/#helia_edge.layers.preprocessing.base_augmentation.BaseAugmentation.augment_targets), [batch_augment()](/helia-edge/reference/api/helia_edge/layers/preprocessing/base_augmentation/#helia_edge.layers.preprocessing.base_augmentation.BaseAugmentation.batch_augment), [call()](/helia-edge/reference/api/helia_edge/layers/preprocessing/base_augmentation/#helia_edge.layers.preprocessing.base_augmentation.BaseAugmentation.call), [get_random_transformations()](/helia-edge/reference/api/helia_edge/layers/preprocessing/base_augmentation/#helia_edge.layers.preprocessing.base_augmentation.BaseAugmentation.get_random_transformations).

**Parameters**

| 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. |

Source: `helia_edge/layers/preprocessing/normalization.py:17`

### helia_edge.layers.preprocessing.normalization.Normalization1D.training_only

`attribute` · `python`

```python
training_only = False
```

Source: `helia_edge/layers/preprocessing/normalization.py:19`

### helia_edge.layers.preprocessing.normalization.Normalization1D.mean

`attribute` · `python`

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

Source: `helia_edge/layers/preprocessing/normalization.py:41`

### helia_edge.layers.preprocessing.normalization.Normalization1D.variance

`attribute` · `python`

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

Source: `helia_edge/layers/preprocessing/normalization.py:42`

### helia_edge.layers.preprocessing.normalization.Normalization1D.epsilon

`attribute` · `python`

```python
epsilon: float = epsilon
```

Source: `helia_edge/layers/preprocessing/normalization.py:43`

### helia_edge.layers.preprocessing.normalization.Normalization1D.augment_samples

`method` · `python`

```python
augment_samples(inputs) -> keras.KerasTensor
```

Normalize a batch of samples.

Source: `helia_edge/layers/preprocessing/normalization.py:45`

### helia_edge.layers.preprocessing.normalization.Normalization1D.get_config

`method` · `python`

```python
get_config()
```

Serialize the configuration.

Source: `helia_edge/layers/preprocessing/normalization.py:56`