Package org.tensorflow.op.train

Class ApplyCenteredRmsProp<T>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.train.ApplyCenteredRmsProp<T>

Type Parameters:

T - data type for out() output

All Implemented Interfaces:

Op, Operand<T>

@Operator(group="train")
public final class ApplyCenteredRmsProp<T>
extends PrimitiveOp
implements Operand<T>

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)

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

Nested Class Summary

Nested Classes

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

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method	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 to wrap a new ApplyCenteredRmsProp operation to the graph.
Output<T>	out()	Same as "var".
static ApplyCenteredRmsProp.Options	useLocking(java.lang.Boolean useLocking)

Methods inherited from class java.lang.Object

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

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Method Detail

create

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)

Factory method to create a class to wrap a new ApplyCenteredRmsProp 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.

options - carries optional attributes values

Returns:

a new instance of ApplyCenteredRmsProp

useLocking

public static ApplyCenteredRmsProp.Options useLocking(java.lang.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.

out

public Output<T> out()

Same as "var".

asOutput

public Output<T> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of a tensor.

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.

Specified by:

asOutput in interface Operand<T>

See Also:

OperationBuilder.addInput(Output)