random_noise_distortion

Name	Description
`RandomNoiseDistortion1D`	Random noise distortion 1D

Name

Description

RandomNoiseDistortion1D

Random noise distortion 1D

RandomNoiseDistortion1D(
    sample_rate: float = 1,
    frequency: float | tuple[float, float] = 100,
    amplitude: float | tuple[float, float] = 0.1,
    interpolation: str = 'bilinear',
    noise_type: str = 'normal',
    **kwargs={},
)

Apply random noise distortion to the 1D input. Noise points are first generated at given frequency resolution with amplitude picked based on noise_type. The noise points are then interpolated to match the input duration and added to the input.

Example:

    sample_rate = 100 # Hz
    duration = 3*sample_rate # 3 seconds
    sig_freq = 10 # Hz
    sig_amp = 1 # Signal amplitude
    noise_freq = (1, 2) # Noise frequency range
    noise_amp = (1, 2) # Noise amplitude range
    x = sig_amp*np.sin(2*np.pi*sig_freq*np.arange(duration)/sample_rate).reshape(-1, 1)
    lyr = RandomNoiseDistortion1D(sample_rate=sample_rate, frequency=noise_freq, amplitude=noise_amp)
    y = lyr(x, training=True)

Base class: BaseAugmentation1D.

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

Parameters

Parameters of RandomNoiseDistortion1D
Name	Type	Default	Description
`sample_rate`	`float`	1	Sample rate of the input.
`frequency`	`float \| tuple[float, float]`	100	Frequency of the noise in Hz. If tuple, frequency is randomly picked between the values.
`amplitude`	`float \| tuple[float, float]`	0.1	Amplitude of the noise. If tuple, amplitude is randomly picked between the values.
`interpolation`	`str`	'bilinear'	Interpolation method to use. One of "nearest", "bilinear", or "bicubic".
`noise_type`	`str`	'normal'	Type of noise to generate. Currently only "normal" is supported.

sample_rate: float = sample_rate

frequency: tuple[float, float] = parse_factor(frequency, min_value=None, max_value=sample_rate / 2, param_name='frequency')

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

interpolation: str = interpolation

noise_type: str = noise_type

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

Generate noise distortion 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.

augment_samples(inputs) -> keras.KerasTensor

Augment all samples in the batch as it’s faster.

get_config()

Serialize the layer configuration to a JSON-compatible dictionary.

random_noise_distortion

Random Noise Distortion Layer API