T
- data type for out()
output@Operator(group="train") public final class ApplyCenteredRmsProp<T> extends PrimitiveOp implements Operand<T>
The centered RMSProp algorithm uses an estimate of the centered second moment (i.e., the variance) for normalization, as opposed to regular RMSProp, which uses the (uncentered) second moment. This often helps with training, but is slightly more expensive in terms of computation and memory.
Note that in dense implementation of this algorithm, mg, ms, and mom will update even if the grad is zero, but in this sparse implementation, mg, ms, and mom will not update in iterations during which the grad is zero.
mean_square = decay * mean_square + (1-decay) * gradient ** 2 mean_grad = decay * mean_grad + (1-decay) * gradient
Delta = learning_rate * gradient / sqrt(mean_square + epsilon - mean_grad ** 2)
mg <- rho * mg_{t-1} + (1-rho) * grad ms <- rho * ms_{t-1} + (1-rho) * grad * grad mom <- momentum * mom_{t-1} + lr * grad / sqrt(ms - mg * mg + epsilon) var <- var - mom
Modifier and Type | Class and Description |
---|---|
static class |
ApplyCenteredRmsProp.Options
Optional attributes for
ApplyCenteredRmsProp |
operation
Modifier and Type | Method and Description |
---|---|
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static <T> ApplyCenteredRmsProp<T> |
create(Scope scope,
Operand<T> var,
Operand<T> mg,
Operand<T> ms,
Operand<T> mom,
Operand<T> lr,
Operand<T> rho,
Operand<T> momentum,
Operand<T> epsilon,
Operand<T> grad,
ApplyCenteredRmsProp.Options... options)
Factory method to create a class wrapping a new ApplyCenteredRmsProp operation.
|
Output<T> |
out()
Same as "var".
|
static ApplyCenteredRmsProp.Options |
useLocking(Boolean useLocking) |
equals, hashCode, op, toString
public static <T> ApplyCenteredRmsProp<T> create(Scope scope, Operand<T> var, Operand<T> mg, Operand<T> ms, Operand<T> mom, Operand<T> lr, Operand<T> rho, Operand<T> momentum, Operand<T> epsilon, Operand<T> grad, ApplyCenteredRmsProp.Options... options)
scope
- current scopevar
- Should be from a Variable().mg
- Should be from a Variable().ms
- Should be from a Variable().mom
- Should be from a Variable().lr
- Scaling factor. Must be a scalar.rho
- Decay rate. Must be a scalar.momentum
- epsilon
- Ridge term. Must be a scalar.grad
- The gradient.options
- carries optional attributes valuespublic static ApplyCenteredRmsProp.Options useLocking(Boolean useLocking)
useLocking
- If `True`, updating of the var, mg, ms, and mom tensors is
protected by a lock; otherwise the behavior is undefined, but may exhibit less
contention.public Output<T> asOutput()
Operand
Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.
asOutput
in interface Operand<T>
OperationBuilder.addInput(Output)
Copyright © 2022. All rights reserved.