Struct BatchNorm

pub struct BatchNorm { /* private fields */ }

Batch normalization layer.

Implementations

impl BatchNorm

pub fn new( name: &str, scale: Box<dyn ArrayProtocol>, offset: Box<dyn ArrayProtocol>, running_mean: Box<dyn ArrayProtocol>, running_var: Box<dyn ArrayProtocol>, epsilon: f64, _momentum: f64, ) -> Self

Create a new batch normalization layer.

pub fn with_shape( name: &str, num_features: usize, epsilon: Option<f64>, _momentum: Option<f64>, ) -> Self

Create a new batch normalization layer with initialized parameters.

Trait Implementations

impl Layer for BatchNorm

fn forward( &self, inputs: &dyn ArrayProtocol, ) -> Result<Box<dyn ArrayProtocol>, OperationError>

Forward pass through the layer.

fn parameters(&self) -> Vec<Box<dyn ArrayProtocol>>

Get the layer’s parameters.

fn train(&mut self)

Set the layer to training mode.

fn eval(&mut self)

Set the layer to evaluation mode.

fn is_training(&self) -> bool

Check if the layer is in training mode.

fn name(&self) -> &str

Get the layer’s name.

fn as_any(&self) -> &dyn Any

Downcast the layer to Any for type-specific operations.