Struct MixupAugmenter 

pub struct MixupAugmenter {
    pub alpha: f64,
}

Mixup augmentation.

Creates new training samples by linearly interpolating between pairs of samples: x’ = λ * x₁ + (1 - λ) * x₂, y’ = λ * y₁ + (1 - λ) * y₂

Reference: Zhang et al., “mixup: Beyond Empirical Risk Minimization”, ICLR 2018

Fields

alpha: f64

Alpha parameter for Beta distribution (controls mixing strength).

Implementations

impl MixupAugmenter

pub fn new(alpha: f64) -> TrainResult<Self>

Create a new mixup augmenter.

Arguments

• alpha - Alpha parameter for Beta distribution

pub fn augment_batch( &self, data: &ArrayView2<'_, f64>, labels: &ArrayView2<'_, f64>, rng: &mut StdRng, ) -> TrainResult<(Array2<f64>, Array2<f64>)>

Apply mixup to a batch of data.

Arguments

• data - Input data batch [N, features]
• labels - Corresponding labels [N, classes]
• rng - Random number generator

Returns

Tuple of (augmented_data, augmented_labels)

Trait Implementations

impl Clone for MixupAugmenter

fn clone(&self) -> MixupAugmenter

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl DataAugmenter for MixupAugmenter

fn augment( &self, data: &ArrayView2<'_, f64>, _rng: &mut StdRng, ) -> TrainResult<Array2<f64>>

Augment the given data.

impl Debug for MixupAugmenter

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for MixupAugmenter

fn default() -> Self

Returns the “default value” for a type.