Struct MaxPool1d 

pub struct MaxPool1d { /* private fields */ }

Max Pooling 1D.

Applies max pooling over a 1D input signal.

Shape

• Input: (N, C, L)
• Output: (N, C, L_out) where L_out = (L - kernel_size) / stride + 1

Implementations

impl MaxPool1d

pub fn new(kernel_size: usize) -> Self

Create a new MaxPool1d layer.

pub fn with_stride(kernel_size: usize, stride: usize) -> Self

Create MaxPool1d with custom stride.

Trait Implementations

impl Debug for MaxPool1d

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

Formats the value using the given formatter.

impl Module for MaxPool1d

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 refresh_caches(&mut self)

Refresh any cached computations after parameters have been modified.

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.