Struct ContrastiveLoss 

pub struct ContrastiveLoss {
    pub margin: f64,
}

Contrastive loss for metric learning. Used to learn embeddings where similar pairs are close and dissimilar pairs are far apart.

Fields

margin: f64

Margin for dissimilar pairs.

Trait Implementations

impl Clone for ContrastiveLoss

fn clone(&self) -> ContrastiveLoss

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ContrastiveLoss

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

Formats the value using the given formatter.

impl Default for ContrastiveLoss

fn default() -> Self

Returns the “default value” for a type.

impl Loss for ContrastiveLoss

fn compute( &self, predictions: &ArrayView<'_, f64, Ix2>, targets: &ArrayView<'_, f64, Ix2>, ) -> TrainResult<f64>

Compute loss value.

fn gradient( &self, predictions: &ArrayView<'_, f64, Ix2>, targets: &ArrayView<'_, f64, Ix2>, ) -> TrainResult<Array<f64, Ix2>>

Compute loss gradient with respect to predictions.

fn name(&self) -> &str

Get the name of the loss function.