Struct Dropout3d

pub struct Dropout3d {
    pub one_minus_p: f32,
    pub training: bool,
}

Apply 3D channel-wise dropout during training.

Randomly zero out entire channels independently with probability p. This layer expects the channels to be last, i.e., the input shape should be NDHWC or DHWC where: N is the batch dimension, D is the depth, H is the input image height, W is the input image width, and C is the number of input channels.

The remaining channels are scaled by 1 / (1-p) to maintain the expected value of each element. Unlike traditional dropout, which zeros individual entries, this layer zeros entire channels. This is often beneficial for convolutional layers processing 3D data, like in medical imaging or video processing.

Fields

one_minus_p: f32

1-p, where p is the probability of zeroing a channel. p is default to Dropout3d::DEFAULT_P if not specified.

training: bool

Whether the layer is in training mode. Default to Dropout3d::DEFAULT_TRAINING if not specified.

Implementations

impl Dropout3d

pub fn new() -> Self

Creates a new instance of Dropout3d.

impl Dropout3d

pub const DEFAULT_P: f32 = 0.5f32

Default value for the probability of zeroing a channel.

pub const DEFAULT_TRAINING: bool = true

Default value for the training mode.

Trait Implementations

impl Buildable for Dropout3d

type Builder = Dropout3dBuilder

The builder type for this buildable type

impl Builder<Dropout3d> for Dropout3dBuilder

type Error = DropoutBuildError

Error with building

fn build(self) -> Result<Dropout3d, Self::Error>

Build the type

impl Clone for Dropout3d

fn clone(&self) -> Dropout3d

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for Dropout3d

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

Formats the value using the given formatter.

impl Module<&Array> for Dropout3d

type Error = Exception

Error type for the module.

type Output = Array

Output type of the module.

fn forward(&mut self, x: &Array) -> Result<Array, Self::Error>

Forward pass of the module.

fn training_mode(&mut self, mode: bool)

Set whether the module is in training mode.

impl ModuleParameters for Dropout3d

fn freeze_parameters(&mut self, recursive: bool)

Freeze all parameters in the module.

fn unfreeze_parameters(&mut self, recursive: bool)

Unfreeze all parameters in the module.

fn parameters(&self) -> ModuleParamRef<'_>

Get references to the module parameters.

fn parameters_mut(&mut self) -> ModuleParamMut<'_>

Get mutable references to the module parameters.

fn trainable_parameters(&self) -> ModuleParamRef<'_>

Get references to the trainable parameters. A parameter is trainable if it is NOT frozen.

fn all_frozen(&self) -> Option<bool>

Check if all parameters in the module are frozen. Returns None if there are no parameters.

fn any_frozen(&self) -> Option<bool>

Check if any parameter in the module is frozen. Returns None if there are no parameters.

fn update(&mut self, parameters: ModuleParam)

Update the module parameters.

fn update_flattened(&mut self, flattened_parameters: FlattenedModuleParam)

Update the module parameters from a flattened representation.