org.tensorflow.op.core

Class ResourceSparseApplyCenteredRMSProp

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.core.ResourceSparseApplyCenteredRMSProp

All Implemented Interfaces:

Op

@Operator
public final class ResourceSparseApplyCenteredRMSProp
extends PrimitiveOp

Update '*var' according to the centered RMSProp algorithm.

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)

ms <- rho * ms_{t-1} + (1-rho) * grad * grad mom <- momentum * mom_{t-1} + lr * grad / sqrt(ms + epsilon) var <- var - mom

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	ResourceSparseApplyCenteredRMSProp.Options Optional attributes for ResourceSparseApplyCenteredRMSProp

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
static <T,U extends Number> ResourceSparseApplyCenteredRMSProp	create(Scope scope, Operand<?> var, Operand<?> mg, Operand<?> ms, Operand<?> mom, Operand<T> lr, Operand<T> rho, Operand<T> momentum, Operand<T> epsilon, Operand<T> grad, Operand<U> indices, ResourceSparseApplyCenteredRMSProp.Options... options) Factory method to create a class to wrap a new ResourceSparseApplyCenteredRMSProp operation to the graph.
static ResourceSparseApplyCenteredRMSProp.Options	useLocking(Boolean useLocking)

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Method Detail

create

public static <T,U extends Number> ResourceSparseApplyCenteredRMSProp create(Scope scope,
                                                                             Operand<?> var,
                                                                             Operand<?> mg,
                                                                             Operand<?> ms,
                                                                             Operand<?> mom,
                                                                             Operand<T> lr,
                                                                             Operand<T> rho,
                                                                             Operand<T> momentum,
                                                                             Operand<T> epsilon,
                                                                             Operand<T> grad,
                                                                             Operand<U> indices,
                                                                             ResourceSparseApplyCenteredRMSProp.Options... options)

Factory method to create a class to wrap a new ResourceSparseApplyCenteredRMSProp operation to the graph.

Parameters:

scope - current graph scope

var - 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.

indices - A vector of indices into the first dimension of var, ms and mom.

options - carries optional attributes values

Returns:

a new instance of ResourceSparseApplyCenteredRMSProp

useLocking

public static ResourceSparseApplyCenteredRMSProp.Options useLocking(Boolean useLocking)

Parameters:

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.