Struct neuro::layers::BatchNorm

pub struct BatchNorm { /* fields omitted */ }

Defines a batch normalization layer.

Methods

impl BatchNorm

pub fn new() -> Box<BatchNorm>

Creates a batch normalization layer.

By default, the momentum used by the running averages is set to 0.99 and the epsilon value used for numerical stability to 1e-5.

pub fn with_param(momentum: PrimitiveType, eps: PrimitiveType) -> Box<BatchNorm>

Creates a batch normalization layers with the given momentum.

Arguments

• momentum - The momentum used by the running averages to compute the mean and standard deviation of the data set.
• eps - A small constant used for numerical stability.

pub fn mean(&self) -> Tensor

Returns the current estimate of the dataset mean.

pub fn variance(&self) -> Tensor

Returns the current estimate of the dataset variance.

Trait Implementations

impl Display for BatchNorm

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

Formats the value using the given formatter.

impl Layer for BatchNorm

fn name(&self) -> &str

Returns the name of the layer.

fn initialize_parameters(&mut self, input_shape: Dim4)

Initializes the parameters of the layer.

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

Computes the activation of the layer during the forward pass.

fn compute_activation_mut(&mut self, input: &Tensor) -> Tensor

Computes the forward pass and stores intermediate values for efficient backpropagation.

fn compute_dactivation_mut(&mut self, dz: &Tensor) -> Tensor

Computes the backward pass through the layer.

fn output_shape(&self) -> Dim4

Returns the shape of the output.

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

Returns the trainable parameters of the layer.

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

Returns the trainable parameters of the layer and their derivatives.

fn save(&self, group: &Group, layer_number: usize) -> Result<(), Error>

Writes the parameters of the layer in the HDF5 group.

fn set_regularizer(&mut self, _regularizer: Option<Regularizer>)

Sets the regularizer for the layer.

fn print(&self)

Displays the properties of the layer.