Skip to main content

PqCode

Struct PqCode 

Source
pub struct PqCode { /* private fields */ }
Expand description

A product-quantized (PQ) code: one u8 centroid index per subvector.

Produced by Quantizer::quantize on a trained ProductQuantizer. The byte at position m is the index (in 0..n_centroids, where n_centroids <= 256) of the centroid in subvector codebook m that best approximates the m-th subvector of the encoded vector. Decode it with Quantizer::dequantize (lossy) or compare it against a query through Quantizer::distance.

§Examples

use iqdb_quantize::{ProductQuantizer, Quantizer};

let mut pq = ProductQuantizer::with_config(2, 4, 42);
let training: Vec<Vec<f32>> = (0..8)
    .map(|i| vec![i as f32, (i * 2) as f32, (i * 3) as f32, (i * 4) as f32])
    .collect();
let refs: Vec<&[f32]> = training.iter().map(Vec::as_slice).collect();
pq.train(&refs).expect("training succeeds");

let code = pq.quantize(&[1.0_f32, 2.0, 3.0, 4.0]).expect("quantize");
assert_eq!(code.n_subvectors(), 2);
assert_eq!(code.dim(), 4);
assert_eq!(code.as_bytes().len(), 2);

Implementations§

Source§

impl PqCode

Source

pub fn dim(&self) -> usize

Returns the original vector dimension this code was produced from.

§Examples
use iqdb_quantize::{ProductQuantizer, Quantizer};

let mut pq = ProductQuantizer::with_config(2, 4, 7);
let training: Vec<Vec<f32>> = (0..8)
    .map(|i| vec![i as f32, (i + 1) as f32, (i + 2) as f32, (i + 3) as f32])
    .collect();
let refs: Vec<&[f32]> = training.iter().map(Vec::as_slice).collect();
pq.train(&refs).expect("training succeeds");
let code = pq.quantize(&[1.0_f32, 2.0, 3.0, 4.0]).expect("quantize");
assert_eq!(code.dim(), 4);
Source

pub fn n_subvectors(&self) -> usize

Returns the number of subvectors M this code was produced under.

Equal to self.as_bytes().len() and to the ProductQuantizer::n_subvectors the code was produced with.

§Examples
use iqdb_quantize::{ProductQuantizer, Quantizer};

let mut pq = ProductQuantizer::with_config(2, 4, 7);
let training: Vec<Vec<f32>> = (0..8)
    .map(|i| vec![i as f32, (i + 1) as f32, (i + 2) as f32, (i + 3) as f32])
    .collect();
let refs: Vec<&[f32]> = training.iter().map(Vec::as_slice).collect();
pq.train(&refs).expect("training succeeds");
let code = pq.quantize(&[1.0_f32, 2.0, 3.0, 4.0]).expect("quantize");
assert_eq!(code.n_subvectors(), 2);
Source

pub fn len(&self) -> usize

Returns the number of bytes in the code (equal to PqCode::n_subvectors).

§Examples
use iqdb_quantize::{ProductQuantizer, Quantizer};

let mut pq = ProductQuantizer::with_config(2, 4, 7);
let training: Vec<Vec<f32>> = (0..8)
    .map(|i| vec![i as f32, (i + 1) as f32, (i + 2) as f32, (i + 3) as f32])
    .collect();
let refs: Vec<&[f32]> = training.iter().map(Vec::as_slice).collect();
pq.train(&refs).expect("training succeeds");
let code = pq.quantize(&[1.0_f32, 2.0, 3.0, 4.0]).expect("quantize");
assert_eq!(code.len(), 2);
Source

pub fn is_empty(&self) -> bool

Returns true if the code holds no centroid indices.

A PqCode produced by Quantizer::quantize on a trained ProductQuantizer is never empty (empty inputs and n_subvectors == 0 are rejected at the boundary); this method exists for API symmetry with PqCode::len.

§Examples
use iqdb_quantize::{ProductQuantizer, Quantizer};

let mut pq = ProductQuantizer::with_config(2, 4, 7);
let training: Vec<Vec<f32>> = (0..8)
    .map(|i| vec![i as f32, (i + 1) as f32, (i + 2) as f32, (i + 3) as f32])
    .collect();
let refs: Vec<&[f32]> = training.iter().map(Vec::as_slice).collect();
pq.train(&refs).expect("training succeeds");
let code = pq.quantize(&[1.0_f32, 2.0, 3.0, 4.0]).expect("quantize");
assert!(!code.is_empty());
Source

pub fn as_bytes(&self) -> &[u8]

Borrow the raw centroid-index bytes.

§Examples
use iqdb_quantize::{ProductQuantizer, Quantizer};

let mut pq = ProductQuantizer::with_config(2, 4, 7);
let training: Vec<Vec<f32>> = (0..8)
    .map(|i| vec![i as f32, (i + 1) as f32, (i + 2) as f32, (i + 3) as f32])
    .collect();
let refs: Vec<&[f32]> = training.iter().map(Vec::as_slice).collect();
pq.train(&refs).expect("training succeeds");
let code = pq.quantize(&[1.0_f32, 2.0, 3.0, 4.0]).expect("quantize");
assert_eq!(code.as_bytes().len(), 2);

Trait Implementations§

Source§

impl Clone for PqCode

Source§

fn clone(&self) -> PqCode

Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§

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

Performs copy-assignment from source. Read more
Source§

impl Debug for PqCode

Source§

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

Formats the value using the given formatter. Read more
Source§

impl Eq for PqCode

Source§

impl PartialEq for PqCode

Source§

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

Tests for self and other values to be equal, and is used by ==.
1.0.0 (const: unstable) · Source§

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

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

impl StructuralPartialEq for PqCode

Auto Trait Implementations§

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<T> CloneToUninit for T
where T: Clone,

Source§

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)
Performs copy-assignment from self to dest. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

Source§

impl<T> Instrument for T

Source§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more
Source§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> ToOwned for T
where T: Clone,

Source§

type Owned = T

The resulting type after obtaining ownership.
Source§

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more
Source§

fn clone_into(&self, target: &mut T)

Uses borrowed data to replace owned data, usually by cloning. Read more
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
Source§

impl<E> WithErrorCode<E> for E

Source§

fn with_code(self, code: impl Into<String>) -> CodedError<E>

Attach an error code to an error
Source§

impl<T> WithSubscriber for T

Source§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more
Source§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more