tensorflow:: ops:: ResourceSparseApplyCenteredRMSProp
#include <training_ops.h>
Update '*var' according to the centered RMSProp algorithm.
Summary
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
Args:
- scope: A Scope object
- 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.
- epsilon: Ridge term. Must be a scalar.
- grad: The gradient.
- indices: A vector of indices into the first dimension of var, ms and mom.
Optional attributes (see Attrs
):
- use_locking: 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.
Returns:
- the created
Operation
Constructors and Destructors |
|
---|---|
ResourceSparseApplyCenteredRMSProp(const ::tensorflow::Scope & scope, ::tensorflow::Input var, ::tensorflow::Input mg, ::tensorflow::Input ms, ::tensorflow::Input mom, ::tensorflow::Input lr, ::tensorflow::Input rho, ::tensorflow::Input momentum, ::tensorflow::Input epsilon, ::tensorflow::Input grad, ::tensorflow::Input indices)
|
|
ResourceSparseApplyCenteredRMSProp(const ::tensorflow::Scope & scope, ::tensorflow::Input var, ::tensorflow::Input mg, ::tensorflow::Input ms, ::tensorflow::Input mom, ::tensorflow::Input lr, ::tensorflow::Input rho, ::tensorflow::Input momentum, ::tensorflow::Input epsilon, ::tensorflow::Input grad, ::tensorflow::Input indices, const ResourceSparseApplyCenteredRMSProp::Attrs & attrs)
|
Public attributes |
|
---|---|
operation
|
Public functions |
|
---|---|
operator::tensorflow::Operation() const
|
|
Public static functions |
|
---|---|
UseLocking(bool x)
|
Structs |
|
---|---|
tensorflow:: |
Optional attribute setters for ResourceSparseApplyCenteredRMSProp. |
Public attributes
operation
Operation operation
Public functions
ResourceSparseApplyCenteredRMSProp
ResourceSparseApplyCenteredRMSProp( const ::tensorflow::Scope & scope, ::tensorflow::Input var, ::tensorflow::Input mg, ::tensorflow::Input ms, ::tensorflow::Input mom, ::tensorflow::Input lr, ::tensorflow::Input rho, ::tensorflow::Input momentum, ::tensorflow::Input epsilon, ::tensorflow::Input grad, ::tensorflow::Input indices )
ResourceSparseApplyCenteredRMSProp
ResourceSparseApplyCenteredRMSProp( const ::tensorflow::Scope & scope, ::tensorflow::Input var, ::tensorflow::Input mg, ::tensorflow::Input ms, ::tensorflow::Input mom, ::tensorflow::Input lr, ::tensorflow::Input rho, ::tensorflow::Input momentum, ::tensorflow::Input epsilon, ::tensorflow::Input grad, ::tensorflow::Input indices, const ResourceSparseApplyCenteredRMSProp::Attrs & attrs )
operator::tensorflow::Operation
operator::tensorflow::Operation() const
Public static functions
UseLocking
Attrs UseLocking( bool x )