Struct Dropout 

pub struct Dropout {
    pub p: f32,
    pub training: bool,
}

Randomly zeroes elements with probability p during training and scales the rest by 1/(1 − p); the identity in evaluation mode (MLX’s nn.Dropout). The mask is bernoulli(1 − p), drawn from the thread’s key sequence (bit for bit MLX’s for a seed) or from an explicit key (Dropout::forward_with_key).

The mode is switched with Module::train on the whole model, and is part of the model’s structure, so a compiled step retraces when it changes.

Fields

p: f32

The probability of zeroing an element, 0 ≤ p < 1.

training: bool

Training (true, the default) or evaluation mode.

Implementations

impl Dropout

pub fn new(p: f32) -> Self

Dropout with probability p (0 ≤ p < 1; another value makes forward return a failed array), in training mode.

pub fn forward(&self, x: &Array) -> Array

x with dropout (training mode) or unchanged (evaluation mode).

pub fn forward_with_key(&self, x: &Array, key: &Array) -> Array

Dropout::forward with the mask drawn from key.

Trait Implementations

impl Clone for Dropout

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Dropout

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

Formats the value using the given formatter.

impl Leaves for Dropout

fn visit(&self, __v: &mut Visit<'_>)

Reports every leaf (and child tree, enum variant, mode flag and static field) to v, in order.

impl Tree for Dropout

where Self: Clone,

fn visit_mut(&mut self, __v: &mut VisitMut<'_>)

Reports every leaf (and child tree and mode flag) to v mutably, in the order of Leaves::visit.

fn for_each(&self, f: impl FnMut(&str, &Array))

Calls f(path, leaf) for every leaf, in order.

fn map(&self, f: impl FnMut(&str, &Array) -> Array) -> Self

The tree with every leaf replaced by f(path, leaf) (same structure; parameters keep their frozen flag).

fn leaves(&self) -> Vec<Array>

The leaves, in order.

fn paths(&self) -> Vec<String>

The leaves’ paths, in order.

fn flatten(&self) -> Vec<(String, Array)>

The leaves with their paths, in order (MLX’s tree_flatten).

fn unflatten( &self, leaves: impl IntoIterator<Item = Array>, ) -> Result<Self, Error>

A tree of this structure (self is the template) with leaves in order: exactly Tree::len of them, else an error naming both counts.

fn load_flat( &mut self, named: impl IntoIterator<Item = (String, Array)>, mode: LoadMode, ) -> Result<(), Error>

Replaces leaves by path. LoadMode::Strict requires exactly the tree’s paths with matching shapes; LoadMode::Partial assigns the matching names and ignores unknown ones (shapes must still match). Loaded dtypes are kept. On any problem the error lists every one (missing, unknown and mismatched names, sorted) and the tree is unchanged. Duplicate paths (in the tree or in named) are an error.

fn len(&self) -> usize

The number of leaves.

fn is_empty(&self) -> bool

Whether the tree has no leaves.

fn def(&self) -> TreeDef

The tree’s structure.