Struct Node

pub struct Node<T> { /* private fields */ }

Implementations

impl<T> Node<T>

pub fn new( node_id: String, operation: fn(Vec<Tensor<T>>) -> Tensor<T>, operation_prime: fn(&Tensor<T>, Vec<&Tensor<T>>) -> Vec<Tensor<T>>, parameter: Vec<Arc<dyn Graph<T>>>, calc_dim: fn(Vec<Vec2>) -> Vec2, ) -> Node<T>

where T: Copy,

computation node

Arguments

if this node is z = f(x, y):

• node_id
• operation - f
• operation_train
• operation_prime - f_x,y which takes in a gradient dC/dz and inputs x, y; outputs gradients dC/dx, dC/dy
• parameter - Vec<(x, y)>

pub fn with_dim( node_id: String, operation: fn(Vec<Tensor<T>>) -> Tensor<T>, operation_prime: fn(&Tensor<T>, Vec<&Tensor<T>>) -> Vec<Tensor<T>>, parameter: Vec<Arc<dyn Graph<T>>>, dimension: Vec2, ) -> Node<T>

Trait Implementations

impl<T> Graph<T> for Node<T>

where T: Copy + Mul<Output = T> + Add<Output = T>,

fn get_id(&self) -> String

fn get_dim(&self) -> Vec2

fn run(&self, state: &Context<T>, variable: &Context<T>) -> Tensor<T>

fn forward_pass( &self, state: &Context<T>, variable: &Context<T>, history: &mut Context<T>, ) -> Tensor<T>

fn backward_pass( &self, state: &mut Context<T>, variable: &Context<T>, history: &Context<T>, gradient: &Tensor<T>, learning_rate: T, )

fn train( &self, state: &Context<T>, variable: &Context<T>, history: &mut Context<T>, ) -> Tensor<T>