Struct ReLU 

pub struct ReLU;

Rectified Linear Unit activation: ReLU(x) = max(0, x)

Shape

• Input: (*) any shape
• Output: (*) same shape as input

Example

use aprender::nn::{Module, ReLU};
use aprender::autograd::Tensor;

let relu = ReLU::new();
let x = Tensor::from_slice(&[-1.0, 0.0, 1.0, 2.0]);
let y = relu.forward(&x);  // [0.0, 0.0, 1.0, 2.0]

Implementations

impl ReLU

pub fn new() -> Self

Create a new ReLU activation.

Trait Implementations

impl Clone for ReLU

fn clone(&self) -> ReLU

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ReLU

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

Formats the value using the given formatter.

impl Default for ReLU

fn default() -> ReLU

Returns the “default value” for a type.

impl Module for ReLU

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.

impl Copy for ReLU