public final class ResourceApplyAdaMax extends PrimitiveOp
m_t <- beta1 * m_{t-1} + (1 - beta1) * g v_t <- max(beta2 * v_{t-1}, abs(g)) variable <- variable - learning_rate / (1 - beta1^t) * m_t / (v_t + epsilon)
Modifier and Type | Class and Description |
---|---|
static class |
ResourceApplyAdaMax.Options
Optional attributes for
ResourceApplyAdaMax |
operation
Modifier and Type | Method and Description |
---|---|
static <T> ResourceApplyAdaMax |
create(Scope scope,
Operand<?> var,
Operand<?> m,
Operand<?> v,
Operand<T> beta1Power,
Operand<T> lr,
Operand<T> beta1,
Operand<T> beta2,
Operand<T> epsilon,
Operand<T> grad,
ResourceApplyAdaMax.Options... options)
Factory method to create a class wrapping a new ResourceApplyAdaMax operation.
|
static ResourceApplyAdaMax.Options |
useLocking(Boolean useLocking) |
equals, hashCode, op, toString
public static <T> ResourceApplyAdaMax create(Scope scope, Operand<?> var, Operand<?> m, Operand<?> v, Operand<T> beta1Power, Operand<T> lr, Operand<T> beta1, Operand<T> beta2, Operand<T> epsilon, Operand<T> grad, ResourceApplyAdaMax.Options... options)
scope
- current scopevar
- Should be from a Variable().m
- Should be from a Variable().v
- Should be from a Variable().beta1Power
- Must be a scalar.lr
- Scaling factor. Must be a scalar.beta1
- Momentum factor. Must be a scalar.beta2
- Momentum factor. Must be a scalar.epsilon
- Ridge term. Must be a scalar.grad
- The gradient.options
- carries optional attributes valuespublic static ResourceApplyAdaMax.Options useLocking(Boolean useLocking)
useLocking
- If `True`, updating of the var, m, and v tensors will be protected
by a lock; otherwise the behavior is undefined, but may exhibit less
contention.Copyright © 2022. All rights reserved.