Struct Linear 

pub struct Linear { /* private fields */ }

Linear (Fully Connected) layer.

Performs the operation: output = input @ weight^T + bias

Implementations

impl Linear

pub fn new( in_features: usize, out_features: usize, use_bias: bool, ) -> CnnResult<Self>

Creates a new Linear layer with zero-initialized weights.

pub fn with_weights( in_features: usize, out_features: usize, weight: Vec<f32>, bias: Option<Vec<f32>>, ) -> CnnResult<Self>

Creates a Linear layer with provided weights.

pub fn in_features(&self) -> usize

Returns the input features.

pub fn out_features(&self) -> usize

Returns the output features.

pub fn weight(&self) -> &[f32]

Returns a reference to the weight matrix.

pub fn bias(&self) -> Option<&[f32]>

Returns a reference to the bias vector.

pub fn set_weight(&mut self, weight: Vec<f32>) -> CnnResult<()>

Sets the weight matrix.

pub fn set_bias(&mut self, bias: Option<Vec<f32>>) -> CnnResult<()>

Sets the bias vector.

pub fn forward_vec(&self, input: &[f32]) -> CnnResult<Vec<f32>>

Forward pass for a single input vector.

pub fn forward_batch( &self, input: &[f32], batch_size: usize, ) -> CnnResult<Vec<f32>>

Forward pass for a batch of input vectors.

impl Linear

pub fn output_shape(&self, input_shape: &TensorShape) -> TensorShape

Returns the output TensorShape for a given input TensorShape

Trait Implementations

impl Clone for Linear

fn clone(&self) -> Linear

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Linear

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

Formats the value using the given formatter.

impl Layer for Linear

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

Perform the forward pass

fn name(&self) -> &'static str

Get the layer name

fn num_params(&self) -> usize

Get the number of parameters