Struct Sequential 

pub struct Sequential { /* private fields */ }

Sequential container for chaining modules.

Modules are executed in order, with each module’s output becoming the next module’s input.

Example

use aprender::nn::{Sequential, Linear, ReLU, Dropout};

let model = Sequential::new()
    .add(Linear::new(784, 256))
    .add(ReLU::new())
    .add(Dropout::new(0.5))
    .add(Linear::new(256, 10));

let x = Tensor::randn(&[32, 784]);
let output = model.forward(&x);  // [32, 10]

Implementations

impl Sequential

pub fn new() -> Self

Create an empty Sequential container.

pub fn add<M: Module + 'static>(self, module: M) -> Self

Add a module to the sequence.

Returns self for method chaining.

pub fn add_boxed(self, module: Box<dyn Module>) -> Self

Add a module by boxed trait object.

pub fn len(&self) -> usize

Get the number of modules.

pub fn is_empty(&self) -> bool

Check if the container is empty.

Trait Implementations

impl Debug for Sequential

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

Formats the value using the given formatter.

impl Default for Sequential

fn default() -> Self

Returns the “default value” for a type.

impl Module for Sequential

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 zero_grad(&mut self)

Zero out gradients for all parameters.

fn num_parameters(&self) -> usize

Get the number of learnable parameters.