Struct Dropout 

pub struct Dropout { /* private fields */ }

Dropout: randomly zeros elements with probability p during training.

During training, each element is independently set to zero with probability p, and the remaining elements are scaled by 1 / (1 - p) to preserve the expected value. In eval mode, the input is passed through unchanged.

Implementations

impl Dropout

pub fn new(p: f32) -> Self

Create a new Dropout with drop probability p.

pub fn train(&mut self)

Set to training mode.

pub fn eval(&mut self)

Set to eval mode (no dropout).

Trait Implementations

impl Module for Dropout

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

Run the forward pass.