Struct HuberLoss

pub struct HuberLoss {
    pub delta: f32,
    pub reduction: LossReduction,
}

Compute the Huber loss.

Fields

delta: f32

The threshold at which to change between L1 and L2 loss. Default to HuberLoss::DEFAULT_DELTA

reduction: LossReduction

Reduction type. Default to HuberLoss::DEFAULT_REDUCTION

Implementations

impl HuberLoss

pub fn new() -> Self

Creates a new instance of HuberLoss.

impl HuberLoss

pub const DEFAULT_DELTA: f32 = 1f32

Default value for the delta parameter.

pub const DEFAULT_REDUCTION: LossReduction = LossReduction::None

Default value for the reduction parameter.

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

Compute the Huber loss.

Params

• inputs: predicted values
• targets: target values

Trait Implementations

impl Buildable for HuberLoss

type Builder = HuberLossBuilder

The builder type for this buildable type

impl Builder<HuberLoss> for HuberLossBuilder

type Error = Infallible

Error with building

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

Build the type

impl Clone for HuberLoss

fn clone(&self) -> HuberLoss

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for HuberLoss

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

Formats the value using the given formatter.