Struct ScalarQuantizer 

pub struct ScalarQuantizer {
    pub dmin: Vec<f32>,
    pub dscale: Vec<f32>,
}

Per-dimension linear int8 quantizer. Codes are i8 in [-128, 127].

Fields

dmin: Vec<f32>

Per-dimension minimum value seen during fit.

dscale: Vec<f32>

Per-dimension step size: (max - min) / 255. Zero-range dims use 1.0.

Implementations

impl ScalarQuantizer

pub fn fit(dimension: usize, sample: &[Vector]) -> Self

Learn per-dimension min/scale from a sample of vectors.

pub fn dimension(&self) -> usize

pub fn quantize(&self, v: &[f32]) -> Vec<i8>

Quantize one full-precision vector to int8 codes.

pub fn reconstruct_at(&self, code: i8, i: usize) -> f32

Reconstruct dimension i of a code back to full precision.

pub fn dequantize(&self, codes: &[i8]) -> Vec<f32>

Reconstruct a full code slice into a float vector.

Trait Implementations

impl Clone for ScalarQuantizer

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ScalarQuantizer

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

Formats the value using the given formatter.

impl Default for ScalarQuantizer

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ScalarQuantizer

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ScalarQuantizer

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.