Struct MarginRankingLoss

pub struct MarginRankingLoss {
    pub margin: f32,
    pub reduction: LossReduction,
}

Computes the margin ranking loss.

Fields

margin: f32

The margin by which the scores should be separated. Default to MarginRankingLoss::DEFAULT_MARGIN

reduction: LossReduction

Reduction type. Default to MarginRankingLoss::DEFAULT_REDUCTION

Implementations

impl MarginRankingLoss

pub fn new() -> Self

Creates a new instance of MarginRankingLoss.

impl MarginRankingLoss

pub const DEFAULT_MARGIN: f32 = 0f32

Default value for the margin parameter.

pub const DEFAULT_REDUCTION: LossReduction = LossReduction::None

Default value for the reduction parameter.

pub fn apply( &self, inputs1: impl AsRef<Array>, inputs2: impl AsRef<Array>, targets: impl AsRef<Array>, ) -> Result<Array, Exception>

Computes the margin ranking loss.

Params

• inputs1: Scores for the first input.
• inputs2: Scores for the second input.
• targets: Labels indicating whether samples in inputs1 should be ranked higher than samples in inputs2. Values should be 1 or -1.

Trait Implementations

impl Buildable for MarginRankingLoss

type Builder = MarginRankingLossBuilder

The builder type for this buildable type

impl Builder<MarginRankingLoss> for MarginRankingLossBuilder

type Error = Infallible

Error with building

fn build(self) -> Result<MarginRankingLoss, Self::Error>

Build the type

impl Clone for MarginRankingLoss

fn clone(&self) -> MarginRankingLoss

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for MarginRankingLoss

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

Formats the value using the given formatter.