Struct Conv2D

pub struct Conv2D { /* private fields */ }

Convolutional layer.

Implementations

impl Conv2D

pub fn new( name: &str, filters: Box<dyn ArrayProtocol>, bias: Option<Box<dyn ArrayProtocol>>, stride: (usize, usize), padding: (usize, usize), activation: Option<ActivationFunc>, ) -> Self

Create a new convolutional layer.

pub fn with_shape( name: &str, filter_height: usize, filter_width: usize, in_channels: usize, out_channels: usize, stride: (usize, usize), padding: (usize, usize), with_bias: bool, activation: Option<ActivationFunc>, ) -> Self

Create a new convolutional layer with randomly initialized weights.

Trait Implementations

impl Layer for Conv2D

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.