Struct MeanIoU 

pub struct MeanIoU {
    pub threshold: f64,
    pub epsilon: f64,
}

Mean Intersection over Union (mIoU) metric for multi-class segmentation.

Computes IoU for each class separately and returns the mean. This is the standard evaluation metric for semantic segmentation.

Fields

threshold: f64

Threshold for converting predictions to binary

epsilon: f64

Small epsilon to avoid division by zero

Trait Implementations

impl Clone for MeanIoU

fn clone(&self) -> MeanIoU

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for MeanIoU

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

Formats the value using the given formatter.

impl Default for MeanIoU

fn default() -> Self

Returns the “default value” for a type.

impl Metric for MeanIoU

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

Compute metric value.

fn name(&self) -> &str

Get metric name.

fn reset(&mut self)

Reset metric state (for stateful metrics).