Class: AdditiveNoiseAugmenter

Constructor

new AdditiveNoiseAugmenter(sigma)

Parameters:

Name	Type	Description
sigma	Object | Number | Hasard	options, if number, this is sigma Properties Name Type Attributes Default Description mean Number <optional> 0 mean of the gaussian distribution sigma Number sigma of the gaussian distribution scale Number <optional> 1 if scale is defined (0 < scale < 1), then the noise can apply at a less granular scale perChannel Number <optional> false If perChannel is true, then the sampled values may be different per channel (and pixel).

Source:

• additive-truncated-normal-noise.js, line 40

Examples

// Simple usage
ia.additiveNoise(3);
// alias of
ia.additiveTruncatedNormalNoise(3);

//Simple usage with random variable
ia.additiveTruncatedNormalNoise(h.number(0, 3));

// Explicit usage with random variable
ia.additiveTruncatedNormalNoise({
	sigma: 3,
	scale: 0.5,
	perChannel: true,
	mean: 5
});

// Explicit usage with random variable
ia.additiveNoise({
	sigma: h.integer(0, 3),
	scale: h.number(0.2, 1),
	perChannel: h.boolean(),
	mean: h.number(-5, 5)
});