public final class
ResourceApplyAdamWithAmsgrad
Update '*var' according to the Adam algorithm.
$$\text{lr}_t := \mathrm{learning_rate} * \sqrt{1 - \beta_2^t} / (1 - \beta_1^t)$$
$$m_t := \beta_1 * m_{t-1} + (1 - \beta_1) * g$$
$$v_t := \beta_2 * v_{t-1} + (1 - \beta_2) * g * g$$
$$\hat{v}_t := max{\hat{v}_{t-1}, v_t}$$
$$\text{variable} := \text{variable} - \text{lr}_t * m_t / (\sqrt{\hat{v}_t} + \epsilon)$$
Nested Classes
class | ResourceApplyAdamWithAmsgrad.Options | Optional attributes for ResourceApplyAdamWithAmsgrad
|
Public Methods
static <T> ResourceApplyAdamWithAmsgrad |
create(Scope scope, Operand<?> var, Operand<?> m, Operand<?> v, Operand<?> vhat, Operand<T> beta1Power, Operand<T> beta2Power, Operand<T> lr, Operand<T> beta1, Operand<T> beta2, Operand<T> epsilon, Operand<T> grad, Options... options)
Factory method to create a class wrapping a new ResourceApplyAdamWithAmsgrad operation.
|
static ResourceApplyAdamWithAmsgrad.Options |
useLocking(Boolean useLocking)
|
Inherited Methods
Public Methods
public static ResourceApplyAdamWithAmsgrad create (Scope scope, Operand<?> var, Operand<?> m, Operand<?> v, Operand<?> vhat, Operand<T> beta1Power, Operand<T> beta2Power, Operand<T> lr, Operand<T> beta1, Operand<T> beta2, Operand<T> epsilon, Operand<T> grad, Options... options)
Factory method to create a class wrapping a new ResourceApplyAdamWithAmsgrad operation.
Parameters
scope | current scope |
---|---|
var | Should be from a Variable(). |
m | Should be from a Variable(). |
v | Should be from a Variable(). |
vhat | Should be from a Variable(). |
beta1Power | Must be a scalar. |
beta2Power | 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 values |
Returns
- a new instance of ResourceApplyAdamWithAmsgrad
public static ResourceApplyAdamWithAmsgrad.Options useLocking (Boolean useLocking)
Parameters
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. |
---|