Enum Optimizer 

pub enum Optimizer {
    SGD(SGD),
    SGDM(SGDM),
    Adam(Adam),
    AdamW(AdamW),
    RMSprop(RMSprop),
}

The optimizer function.

Variants

SGD(SGD)

SGDM(SGDM)

Adam(Adam)

AdamW(AdamW)

RMSprop(RMSprop)

Implementations

impl Optimizer

pub fn update( &mut self, layer: usize, filter: usize, bias: bool, stepnr: i32, values: &mut Tensor, gradients: &mut Tensor, )

Updates the weights of the layer.

Arguments

• layer - The layer of the network.
• filter - The filter of the layer. Always 0 if the layer is not a convolutional layer.
• bias - If the current values are the bias.
• stepnr - The step number of the training process (epoch).
• values - The weights of the layer (with optional bias stacked vertically).
• gradients - The gradients of the layer (with optional bias stacked vertically).

pub fn validate(&mut self, vectors: Vec<Vec<Vec<Tensor>>>)

Trait Implementations

impl Clone for Optimizer

fn clone(&self) -> Optimizer

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Display for Optimizer

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

Formats the value using the given formatter.