Struct QuantizationError 

pub struct QuantizationError {
    pub mse: f64,
    pub mae: f64,
    pub max_error: f64,
    pub snr_db: f64,
}

Quantization error metrics for a single vector pair.

Fields

mse: f64

Mean squared error between original and quantized vectors.

mae: f64

Mean absolute error between original and quantized vectors.

max_error: f64

Maximum element-wise absolute error.

snr_db: f64

Signal-to-noise ratio in decibels.

Defined as 10 * log10(signal_power / noise_power) where signal_power = mean(orig²) and noise_power = mse. Returns -∞ when signal power is zero and noise power is also zero (perfect quantization of a zero vector), or +∞ when MSE is zero and signal power is non-zero.

Implementations

impl QuantizationError

pub fn is_acceptable(&self, max_mse: f64) -> bool

Returns true when this error measurement is within an acceptable threshold.

Arguments

• max_mse – the maximum allowable MSE.

Trait Implementations

impl Clone for QuantizationError

fn clone(&self) -> QuantizationError

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantizationError

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

Formats the value using the given formatter.

impl PartialEq for QuantizationError

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

Tests for self and other values to be equal, and is used by ==.

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

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

impl StructuralPartialEq for QuantizationError