Struct BatchNormConfig

pub struct BatchNormConfig {
    pub eps: f64,
    pub remove_mean: bool,
    pub affine: bool,
    pub momentum: f64,
}

Fields

eps: f64

remove_mean: bool

affine: bool

The meaning of affine here is different from LayerNorm: when false there is no learnable parameter at all, 1 used for gamma and 0 for beta.

momentum: f64

Controls exponential moving average of running stats. Defaults to 0.1

running_stat * (1.0 - momentum) + stat * momentum.

Trait Implementations

impl Clone for BatchNormConfig

fn clone(&self) -> BatchNormConfig

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for BatchNormConfig

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

Formats the value using the given formatter.

impl Default for BatchNormConfig

fn default() -> Self

Returns the “default value” for a type.

impl From<f64> for BatchNormConfig

fn from(eps: f64) -> Self

Converts to this type from the input type.

impl PartialEq for BatchNormConfig

fn eq(&self, other: &BatchNormConfig) -> 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 Copy for BatchNormConfig

impl StructuralPartialEq for BatchNormConfig