Struct Dropout 

pub struct Dropout { /* private fields */ }

Applies dropout regularization.

During training: randomly zeros elements with probability p, scales remaining by 1/(1-p).

During eval: identity (no-op).

Implementations

impl Dropout

pub fn new(p: f64) -> Dropout

Create a new Dropout layer.

pub fn set_training(&self, training: bool)

Set training/eval mode directly (works without specifying backend).

pub fn is_training(&self) -> bool

Whether module is in training mode (works without specifying backend).

pub fn forward_t<B>(&self, x: &Tensor<B>) -> Result<Tensor<B>, Error>

where B: Backend,

Apply dropout: randomly zero elements during training.

Trait Implementations

impl<B> Module<B> for Dropout

where B: Backend,

fn forward(&self, x: &Tensor<B>) -> Result<Tensor<B>, Error>

Compute the output tensor from the input tensor. This defines the layer’s computation (forward pass).

fn parameters(&self) -> Vec<Tensor<B>>

Return all trainable parameters of this module. The optimizer uses these to update weights during training.

fn set_training(&self, training: bool)

Set training or evaluation mode.

fn is_training(&self) -> bool

Whether the module is in training mode (default: true).

fn train(&self)

Convenience: set training mode.

fn eval(&self)

Convenience: set evaluation mode.

fn num_parameters(&self) -> usize

Total number of scalar parameters in this module.

fn trainable_params_count(&self) -> usize

Number of trainable (variable) parameters.

fn frozen_parameters(&self) -> Vec<Tensor<B>>

Freeze all parameters: returns new parameter tensors with is_variable = false, preventing gradient accumulation.

fn named_parameters(&self) -> Vec<(String, Tensor<B>)>

Return all trainable parameters with human-readable names.

fn state_dict(&self) -> Vec<(String, Tensor<B>)>

Returns a state_dict-style map of parameter name → tensor.