Struct ModelParams

pub struct ModelParams<A = f64> { /* private fields */ }

This object is an abstraction over the parameters of a deep neural network model. This is done to isolate the necessary parameters from the specific logic within a model allowing us to easily create additional stores for tracking velocities, gradients, and other metrics we may need.

Additionally, this provides us with a way to introduce common creation routines for initializing neural networks.

Implementations

impl<A> ModelParams<A>

pub fn default(features: ModelFeatures) -> Self

where A: Clone + Default,

create a new instance of the model; all parameters are initialized to their defaults (i.e., zero)

pub fn ones(features: ModelFeatures) -> Self

where A: Clone + One,

create a new instance of the model; all parameters are initialized to zero

pub fn zeros(features: ModelFeatures) -> Self

where A: Clone + Zero,

create a new instance of the model; all parameters are initialized to zero

pub fn is_shallow(&self) -> bool

returns true if the stack is shallow

pub const fn input(&self) -> &Params<A>

returns an immutable reference to the input layer of the model

pub fn input_mut(&mut self) -> &mut Params<A>

returns a mutable reference to the input layer of the model

pub const fn hidden(&self) -> &Vec<Params<A>>

returns an immutable reference to the hidden layers of the model

pub fn hidden_as_slice(&self) -> &[Params<A>]

returns an immutable reference to the hidden layers of the model as a slice

pub fn hidden_mut(&mut self) -> &mut Vec<Params<A>>

returns a mutable reference to the hidden layers of the model

pub const fn output(&self) -> &Params<A>

returns an immutable reference to the output layer of the model

pub fn output_mut(&mut self) -> &mut Params<A>

returns a mutable reference to the output layer of the model

pub fn set_input(&mut self, input: Params<A>)

set the input layer of the model

pub fn set_hidden<I>(&mut self, iter: I)

where I: IntoIterator<Item = Params<A>>,

set the hidden layers of the model

pub fn set_output(&mut self, output: Params<A>)

set the output layer of the model

pub fn with_input(self, input: Params<A>) -> Self

consumes the current instance and returns another with the specified input layer

pub fn with_hidden<I>(self, iter: I) -> Self

where I: IntoIterator<Item = Params<A>>,

consumes the current instance and returns another with the specified hidden layers

pub fn with_output(self, output: Params<A>) -> Self

consumes the current instance and returns another with the specified output layer

pub fn dim_input(&self) -> (usize, usize)

pub fn dim_hidden(&self) -> (usize, usize)

pub fn dim_output(&self) -> (usize, usize)

pub fn forward<X, Y>(&self, input: &X) -> Result<Y>

where A: Clone, Params<A>: Forward<X, Output = Y> + Forward<Y, Output = Y>,

Trait Implementations

impl<A: Clone> Clone for ModelParams<A>

fn clone(&self) -> ModelParams<A>

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<A: Debug> Debug for ModelParams<A>

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

Formats the value using the given formatter.