Generated with

docs/torch/torch.optim/AdamW

AdamW

torch.optim.AdamW

final class AdamW(params: Iterable[Tensor[_]], lr: Double, betas: (Double, Double), eps: Double, weightDecay: Double, amsgrad: Boolean) extends Optimizer

Implements the AdamW algorithm.

Attributes

Source: AdamW.scala
Graph
Supertypes: class Optimizer

class Object

trait Matchable

class Any

Members list

Value members

Inherited methods

Performs a single optimization step (parameter update).

Performs a single optimization step (parameter update).

Attributes

Note: Unless otherwise specified, this function should not modify the .grad field of the parameters.
Inherited from:: Optimizer
Source: Optimizer.scala

Attributes

Inherited from:: Optimizer
Source: Optimizer.scala

Sets the gradients of all optimized Tensors to zero.

Sets the gradients of all optimized Tensors to zero.

Attributes

Inherited from:: Optimizer
Source: Optimizer.scala

In this article

Generated with