Struct tensorflow::train::AdadeltaOptimizer

pub struct AdadeltaOptimizer { /* private fields */ }

Optimizer that implements the Adadelta algorithm.

See M. D. Zeiler.

Implementations

impl AdadeltaOptimizer

pub fn new() -> Self

Creates a new optimizer with default parameters (learning_rate=0.001, rho=0.95, epsilon=1e-8).

pub fn set_learning_rate<T: Into<Output>>(&mut self, learning_rate: T)

Sets the learning rate. Default is 0.001.

pub fn set_rho<T: Into<Output>>(&mut self, rho: T)

Sets rho, the decay rate. Default is 0.95.

pub fn set_epsilon<T: Into<Output>>(&mut self, epsilon: T)

Sets epsilon, the conditioning. Default is 1e-8.

Trait Implementations

impl Debug for AdadeltaOptimizer

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

Formats the value using the given formatter.

impl Default for AdadeltaOptimizer

fn default() -> Self

Returns the “default value” for a type.

impl Optimizer for AdadeltaOptimizer

fn apply_gradients( &self, scope: &mut Scope, opts: ApplyGradientsOptions<'_> ) -> Result<(Vec<Variable>, Operation)>

Applies the given gradients to the variables.

fn compute_gradients( &self, scope: &mut Scope, loss: Output, opts: ComputeGradientsOptions<'_> ) -> Result<Vec<(Option<Output>, Variable)>>

Computes the gradient of a value with respect to the given variables. This adds nodes to the graph, so reuse its results if possible. Any variable whose gradient cannot be calculated will have a None gradient.

fn minimize( &self, scope: &mut Scope, loss: Output, opts: MinimizeOptions<'_> ) -> Result<(Vec<Variable>, Operation)>

Adds operations to the graph to minimize loss with respect to the variables.