random_gaussian_noise

Random Gaussian Noise Layer API

This module provides classes to build random Gaussian noise layers.

Classes

Name	Description
RandomGaussianNoise1D	Random Gaussian noise 1D

Machine-readable model

• RandomGaussianNoise1DclassApply additive zero-centered Gaussian noise.

class

RandomGaussianNoise1D

Python

Apply additive zero-centered Gaussian noise.

helia_edge/layers/preprocessing/random_gaussian_noise.py:17

RandomGaussianNoise1D(factor: float | tuple[float, float] = 0.1, **kwargs={})

Apply additive zero-centered Gaussian noise.

Example:

    x = np.sin(2*np.pi*10*np.arange(duration_size)/100)
    lyr = RandomGaussianNoise1D(factor=0.1)
    y = lyr(x)

Base class: BaseAugmentation1D.

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

Parameters

Parameters of RandomGaussianNoise1D

Name	Type	Default	Description
factor	float	0.1	Standard deviation of the Gaussian noise.

attribute

factor

Python

helia_edge/layers/preprocessing/random_gaussian_noise.py:37

factor: tuple[float, float] = parse_factor(factor, min_value=0, max_value=None, param_name='factor')

method

get_random_transformations

Python

Generate noise tensor

helia_edge/layers/preprocessing/random_gaussian_noise.py:39

get_random_transformations(input_shape: tuple[int, ...]) -> dict

Generate noise tensor

Parameters

Parameters of get_random_transformations

Name	Type	Default	Description
input_shape	tuple[int, ...]	Required	Input shape.

Returns

Returns of get_random_transformations

Value	Type	Description
dict	dict	Dictionary containing the noise tensor.

method

augment_samples

Python

Apply sampled noise; inference bypasses sampling and application.

helia_edge/layers/preprocessing/random_gaussian_noise.py:61

augment_samples(inputs) -> keras.KerasTensor

Apply sampled noise; inference bypasses sampling and application.

method

get_config

Python

helia_edge/layers/preprocessing/random_gaussian_noise.py:65

get_config()