Struct RecallMetric

pub struct RecallMetric<B>
where
    B: Backend,
{ /* private fields */ }

The Recall Metric

Implementations

impl<B> RecallMetric<B>

where B: Backend,

pub fn binary(threshold: f64) -> RecallMetric<B>

Recall metric for binary classification.

Arguments

• threshold - The threshold to transform a probability into a binary prediction.

pub fn multiclass( top_k: usize, class_reduction: ClassReduction, ) -> RecallMetric<B>

Recall metric for multiclass classification.

Arguments

• top_k - The number of highest predictions considered to find the correct label (typically 1).
• class_reduction - Class reduction type.

pub fn multilabel( threshold: f64, class_reduction: ClassReduction, ) -> RecallMetric<B>

Recall metric for multi-label classification.

Arguments

• threshold - The threshold to transform a probability into a binary prediction.
• class_reduction - Class reduction type.

Trait Implementations

impl<B> Default for RecallMetric<B>

where B: Default + Backend,

fn default() -> RecallMetric<B>

Returns the “default value” for a type.

impl<B> Metric for RecallMetric<B>

where B: Backend,

const NAME: &'static str = "Recall"

The name of the metric.

type Input = ConfusionStatsInput<B>

The input type of the metric.

fn update( &mut self, input: &<RecallMetric<B> as Metric>::Input, _metadata: &MetricMetadata, ) -> MetricEntry

Update the metric state and returns the current metric entry.

fn clear(&mut self)

Clear the metric state.

impl<B> Numeric for RecallMetric<B>

where B: Backend,

fn value(&self) -> f64

Returns the numeric value of the metric.