Struct Diagnostics 

pub struct Diagnostics {
    pub objective: f64,
    pub train_nll: f64,
    pub penalty: f64,
    pub gradient_norm: f64,
    pub nonfinite_gradient_count: usize,
}

Диагностики обучения для кандидата theta.

Содержит значения objective, negative log-likelihood (без штрафов), суммарный штраф, норму градиента и число не-finite компонент градиента.

Fields

objective: f64

Full objective value: training negative log-likelihood plus penalties.

train_nll: f64

Training negative log-likelihood before penalties.

penalty: f64

Total penalty contribution.

gradient_norm: f64

Euclidean norm of the objective gradient.

nonfinite_gradient_count: usize

Number of non-finite gradient entries.

Trait Implementations

impl Clone for Diagnostics

fn clone(&self) -> Diagnostics

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for Diagnostics

impl Debug for Diagnostics

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

Formats the value using the given formatter.

impl PartialEq for Diagnostics

fn eq(&self, other: &Diagnostics) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for Diagnostics