T
- data type for out()
output@Operator(group="train") public final class ApplyFtrl<T> extends PrimitiveOp implements Operand<T>
grad_with_shrinkage = grad + 2 * l2_shrinkage * var accum_new = accum + grad_with_shrinkage * grad_with_shrinkage linear += grad_with_shrinkage + (accum_new^(-lr_power) - accum^(-lr_power)) / lr * var quadratic = 1.0 / (accum_new^(lr_power) * lr) + 2 * l2 var = (sign(linear) * l1 - linear) / quadratic if |linear| > l1 else 0.0 accum = accum_new
Modifier and Type | Class and Description |
---|---|
static class |
ApplyFtrl.Options
Optional attributes for
ApplyFtrl |
operation
Modifier and Type | Method and Description |
---|---|
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static <T> ApplyFtrl<T> |
create(Scope scope,
Operand<T> var,
Operand<T> accum,
Operand<T> linear,
Operand<T> grad,
Operand<T> lr,
Operand<T> l1,
Operand<T> l2,
Operand<T> l2Shrinkage,
Operand<T> lrPower,
ApplyFtrl.Options... options)
Factory method to create a class wrapping a new ApplyFtrl operation.
|
Output<T> |
out()
Same as "var".
|
static ApplyFtrl.Options |
useLocking(Boolean useLocking) |
equals, hashCode, op, toString
public static <T> ApplyFtrl<T> create(Scope scope, Operand<T> var, Operand<T> accum, Operand<T> linear, Operand<T> grad, Operand<T> lr, Operand<T> l1, Operand<T> l2, Operand<T> l2Shrinkage, Operand<T> lrPower, ApplyFtrl.Options... options)
scope
- current scopevar
- Should be from a Variable().accum
- Should be from a Variable().linear
- Should be from a Variable().grad
- The gradient.lr
- Scaling factor. Must be a scalar.l1
- L1 regulariation. Must be a scalar.l2
- L2 shrinkage regulariation. Must be a scalar.l2Shrinkage
- lrPower
- Scaling factor. Must be a scalar.options
- carries optional attributes valuespublic static ApplyFtrl.Options useLocking(Boolean useLocking)
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 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.