Struct BatchNorm1d 

pub struct BatchNorm1d { /* private fields */ }

Batch Normalization for 1D inputs (Ioffe & Szegedy, 2015).

Normalizes across the batch dimension during training. Uses running statistics during evaluation.

Implementations

impl BatchNorm1d

pub fn new(num_features: usize) -> Self

Create a new BatchNorm1d layer.

Arguments

• num_features - Number of features (channels)

pub fn with_momentum(self, momentum: f32) -> Self

Set momentum for running statistics update.

pub fn with_eps(self, eps: f32) -> Self

Set epsilon for numerical stability.

Trait Implementations

impl Debug for BatchNorm1d

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

Formats the value using the given formatter.

impl Module for BatchNorm1d

fn forward(&self, input: &Tensor) -> Tensor

Perform forward computation.

fn parameters(&self) -> Vec<&Tensor>

Get references to all learnable parameters.

fn parameters_mut(&mut self) -> Vec<&mut Tensor>

Get mutable references to all learnable parameters.

fn train(&mut self)

Set the module to training mode.

fn eval(&mut self)

Set the module to evaluation mode.

fn training(&self) -> bool

Check if the module is in training mode.

fn refresh_caches(&mut self)

Refresh any cached computations after parameters have been modified.

fn zero_grad(&mut self)

Zero out gradients for all parameters.

fn num_parameters(&self) -> usize

Get the number of learnable parameters.