¿Tengo una pregunta? Conéctese con la comunidad en el Foro de TensorFlow

# tensorflow:: ops:: ApplyFtrlV2

``` #include <training_ops.h> ```

Update '*var' according to the Ftrl-proximal scheme.

## Summary

grad_with_shrinkage = grad + 2 * l2_shrinkage * var accum_new = accum + grad * grad 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

Args:

• scope: A Scope object
• var: Should be from a Variable().
• accum: Should be from a Variable().
• linear: Should be from a Variable().
• lr: Scaling factor. Must be a scalar.
• l1: L1 regularization. Must be a scalar.
• l2: L2 shrinkage regularization. Must be a scalar.
• lr_power: Scaling factor. Must be a scalar.

Optional attributes (see ``` Attrs ``` ):

• use_locking: 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.

Returns:

• ``` Output ``` : Same as "var".

### Constructors and Destructors

``` ApplyFtrlV2 (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input linear, :: tensorflow::Input grad, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input l2_shrinkage, :: tensorflow::Input lr_power) ```
``` ApplyFtrlV2 (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input linear, :: tensorflow::Input grad, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input l2_shrinkage, :: tensorflow::Input lr_power, const ApplyFtrlV2::Attrs & attrs) ```

### Public attributes

``` operation ```
``` Operation ```
``` out ```
``` :: tensorflow::Output ```

### Public functions

``` node () const ```
``` ::tensorflow::Node * ```
``` operator::tensorflow::Input () const ```
``` ```
``` operator::tensorflow::Output () const ```
``` ```

### Public static functions

``` MultiplyLinearByLr (bool x) ```
``` Attrs ```
``` UseLocking (bool x) ```
``` Attrs ```

### Structs

tensorflow:: ops:: ApplyFtrlV2:: Attrs

Optional attribute setters for ApplyFtrlV2 .

## Public attributes

### operation

`Operation operation`

### out

`::tensorflow::Output out`

## Public functions

### ApplyFtrlV2

``` ApplyFtrlV2(
const ::tensorflow::Scope & scope,
::tensorflow::Input var,
::tensorflow::Input accum,
::tensorflow::Input linear,
::tensorflow::Input lr,
::tensorflow::Input l1,
::tensorflow::Input l2,
::tensorflow::Input l2_shrinkage,
::tensorflow::Input lr_power
)```

### ApplyFtrlV2

``` ApplyFtrlV2(
const ::tensorflow::Scope & scope,
::tensorflow::Input var,
::tensorflow::Input accum,
::tensorflow::Input linear,
::tensorflow::Input lr,
::tensorflow::Input l1,
::tensorflow::Input l2,
::tensorflow::Input l2_shrinkage,
::tensorflow::Input lr_power,
const ApplyFtrlV2::Attrs & attrs
)```

### node

`::tensorflow::Node * node() const `

### operator::tensorflow::Input

` operator::tensorflow::Input() const `

### operator::tensorflow::Output

` operator::tensorflow::Output() const `

## Public static functions

### MultiplyLinearByLr

```Attrs MultiplyLinearByLr(
bool x
)```

### UseLocking

```Attrs UseLocking(
bool x
)```
[{ "type": "thumb-down", "id": "missingTheInformationINeed", "label":"Falta la información que necesito" },{ "type": "thumb-down", "id": "tooComplicatedTooManySteps", "label":"Muy complicado o demasiados pasos" },{ "type": "thumb-down", "id": "outOfDate", "label":"Desactualizado" },{ "type": "thumb-down", "id": "samplesCodeIssue", "label":"Samples / code issue" },{ "type": "thumb-down", "id": "otherDown", "label":"Otro" }]
[{ "type": "thumb-up", "id": "easyToUnderstand", "label":"Fácil de comprender" },{ "type": "thumb-up", "id": "solvedMyProblem", "label":"Resolvió mi problema" },{ "type": "thumb-up", "id": "otherUp", "label":"Otro" }]