Struct QuantizationConfig 

pub struct QuantizationConfig {
    pub num_subspaces: usize,
    pub codes_per_subspace: u8,
    pub max_iterations: usize,
    pub convergence_threshold: f64,
}

Configuration for VectorQuantizer.

Fields

num_subspaces: usize

Number of PQ subspaces M. The input dimension must be divisible by this value.

codes_per_subspace: u8

Number of centroids per codebook (K). Must be ≤ 256 (fits in a u8).

max_iterations: usize

Maximum k-means iterations per subspace.

convergence_threshold: f64

K-means convergence threshold: stop when max centroid shift < this value.

Implementations

impl QuantizationConfig

pub fn new( num_subspaces: usize, codes_per_subspace: u8, max_iterations: usize, convergence_threshold: f64, ) -> Self

Create a new configuration with custom parameters.

Trait Implementations

impl Clone for QuantizationConfig

fn clone(&self) -> QuantizationConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantizationConfig

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

Formats the value using the given formatter.

impl Default for QuantizationConfig

fn default() -> Self

Returns the “default value” for a type.