Update relevant entries in '*var' and '*accum' according to the momentum scheme.
Set use_nesterov = True if you want to use Nesterov momentum.
That is for rows we have grad for, we update var and accum as follows:
accum = accum * momentum - lr * grad var += accum
Nested Classes
class | ResourceSparseApplyKerasMomentum.Options | Optional attributes for ResourceSparseApplyKerasMomentum
|
Public Methods
static <T, U extends Number> ResourceSparseApplyKerasMomentum | |
static ResourceSparseApplyKerasMomentum.Options |
useLocking(Boolean useLocking)
|
static ResourceSparseApplyKerasMomentum.Options |
useNesterov(Boolean useNesterov)
|
Inherited Methods
Public Methods
public static ResourceSparseApplyKerasMomentum create (Scope scope, Operand<?> var, Operand<?> accum, Operand<T> lr, Operand<T> grad, Operand<U> indices, Operand<T> momentum, Options... options)
Factory method to create a class wrapping a new ResourceSparseApplyKerasMomentum operation.
Parameters
scope | current scope |
---|---|
var | Should be from a Variable(). |
accum | Should be from a Variable(). |
lr | Learning rate. Must be a scalar. |
grad | The gradient. |
indices | A vector of indices into the first dimension of var and accum. |
momentum | Momentum. Must be a scalar. |
options | carries optional attributes values |
Returns
- a new instance of ResourceSparseApplyKerasMomentum
public static ResourceSparseApplyKerasMomentum.Options useLocking (Boolean useLocking)
Parameters
useLocking | If `True`, updating of the var and accum tensors will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention. |
---|
public static ResourceSparseApplyKerasMomentum.Options useNesterov (Boolean useNesterov)
Parameters
useNesterov | If `True`, the tensor passed to compute grad will be var + momentum * accum, so in the end, the var you get is actually var + momentum * accum. |
---|