Оптимизируйте свои подборки
Сохраняйте и классифицируйте контент в соответствии со своими настройками.
тензорный поток:: опс:: ПрименитьFtrlV2
#include <training_ops.h>
Обновите '*var' по схеме Ftrl-proximal.
Краткое содержание
grad_with_shrinkage = град + 2 * l2_shrinkage * var accum_new = аккум + град * град линейный += grad_with_shrinkage - (accum_new^(-lr_power) - accum^(-lr_power)) / lr * var квадратичная = 1.0 / (accum_new^(lr_power) * lr) + 2 * l2 var = (знак(линейный) * l1 - линейный)/квадратичный, если |линейный| > l1 еще 0,0 аккум = аккум_новый
Аргументы:
- область: объект области.
- var: Должно быть из переменной().
- accum: Должно быть из переменной().
- линейный: должен быть из переменной().
- град: Градиент.
- lr: коэффициент масштабирования. Должно быть скаляр.
- l1: регуляризация L1. Должно быть скаляр.
- l2: Регуляризация усадки L2. Должно быть скаляр.
- lr_power: коэффициент масштабирования. Должно быть скаляр.
Необязательные атрибуты (см. Attrs
):
- use_locking: если
True
, обновление тензоров var и accum будет защищено блокировкой; в противном случае поведение не определено, но может вызывать меньше конфликтов.
Возврат:
Конструкторы и деструкторы |
---|
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) |
Публичные атрибуты
Общественные функции
ПрименитьFtrlV2
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
)
узел
::tensorflow::Node * node() const
operator::tensorflow::Input() const
оператор::tensorflow::Выход
operator::tensorflow::Output() const
Публичные статические функции
Умножитьлинейныйполр
Attrs MultiplyLinearByLr(
bool x
)
Использование блокировки
Attrs UseLocking(
bool x
)
Если не указано иное, контент на этой странице предоставляется по лицензии Creative Commons "С указанием авторства 4.0", а примеры кода – по лицензии Apache 2.0. Подробнее об этом написано в правилах сайта. Java – это зарегистрированный товарный знак корпорации Oracle и ее аффилированных лиц.
Последнее обновление: 2025-07-27 UTC.
[null,null,["Последнее обновление: 2025-07-27 UTC."],[],[],null,["# tensorflow::ops::ApplyFtrlV2 Class Reference\n\ntensorflow::ops::ApplyFtrlV2\n============================\n\n`#include \u003ctraining_ops.h\u003e`\n\nUpdate '\\*var' according to the Ftrl-proximal scheme.\n\nSummary\n-------\n\ngrad_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\\| \\\u003e l1 else 0.0 accum = accum_new\n\nArguments:\n\n- scope: A [Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- var: Should be from a Variable().\n- accum: Should be from a Variable().\n- linear: Should be from a Variable().\n- grad: The gradient.\n- lr: Scaling factor. Must be a scalar.\n- l1: L1 regularization. Must be a scalar.\n- l2: L2 shrinkage regularization. Must be a scalar.\n- lr_power: Scaling factor. Must be a scalar.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/apply-ftrl-v2/attrs#structtensorflow_1_1ops_1_1_apply_ftrl_v2_1_1_attrs)):\n\n- 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.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): Same as \"var\".\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [ApplyFtrlV2](#classtensorflow_1_1ops_1_1_apply_ftrl_v2_1add964fb0f6de2aa24265dcd061c72151)`(const ::`[tensorflow::Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` var, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` linear, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l1, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2_shrinkage, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr_power)` ||\n| [ApplyFtrlV2](#classtensorflow_1_1ops_1_1_apply_ftrl_v2_1a0b32d8c13b43426f739ff6590cd07303)`(const ::`[tensorflow::Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` var, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` linear, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l1, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2_shrinkage, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr_power, const `[ApplyFtrlV2::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/apply-ftrl-v2/attrs#structtensorflow_1_1ops_1_1_apply_ftrl_v2_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|-------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_apply_ftrl_v2_1aff11a6d3c5a685a3bce58b6eba270910) | [Operation](/versions/r2.3/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [out](#classtensorflow_1_1ops_1_1_apply_ftrl_v2_1a37c9c6929132980b64306940e4296ed2) | `::`[tensorflow::Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|-------------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_apply_ftrl_v2_1ab2dafdb4818ad20aa0e4eed79cfba879)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_apply_ftrl_v2_1a1aede95dcc376ee0ac6c62cfe06d7314)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_apply_ftrl_v2_1a331dd3212dc856b76c62ccc135c74656)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|--------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------|\n| [MultiplyLinearByLr](#classtensorflow_1_1ops_1_1_apply_ftrl_v2_1aad4be57c71c744c8f188d58e39c7c910)`(bool x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/apply-ftrl-v2/attrs#structtensorflow_1_1ops_1_1_apply_ftrl_v2_1_1_attrs) |\n| [UseLocking](#classtensorflow_1_1ops_1_1_apply_ftrl_v2_1a5c25a36e1a6eef1e216f631e173e3e42)`(bool x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/apply-ftrl-v2/attrs#structtensorflow_1_1ops_1_1_apply_ftrl_v2_1_1_attrs) |\n\n| ### Structs ||\n|-------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::ApplyFtrlV2::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/apply-ftrl-v2/attrs) | Optional attribute setters for [ApplyFtrlV2](/versions/r2.3/api_docs/cc/class/tensorflow/ops/apply-ftrl-v2#classtensorflow_1_1ops_1_1_apply_ftrl_v2). |\n\nPublic attributes\n-----------------\n\n### operation\n\n```text\nOperation operation\n``` \n\n### out\n\n```text\n::tensorflow::Output out\n``` \n\nPublic functions\n----------------\n\n### ApplyFtrlV2\n\n```gdscript\n ApplyFtrlV2(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input accum,\n ::tensorflow::Input linear,\n ::tensorflow::Input grad,\n ::tensorflow::Input lr,\n ::tensorflow::Input l1,\n ::tensorflow::Input l2,\n ::tensorflow::Input l2_shrinkage,\n ::tensorflow::Input lr_power\n)\n``` \n\n### ApplyFtrlV2\n\n```gdscript\n ApplyFtrlV2(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input accum,\n ::tensorflow::Input linear,\n ::tensorflow::Input grad,\n ::tensorflow::Input lr,\n ::tensorflow::Input l1,\n ::tensorflow::Input l2,\n ::tensorflow::Input l2_shrinkage,\n ::tensorflow::Input lr_power,\n const ApplyFtrlV2::Attrs & attrs\n)\n``` \n\n### node\n\n```gdscript\n::tensorflow::Node * node() const \n``` \n\n### operator::tensorflow::Input\n\n```gdscript\n operator::tensorflow::Input() const \n``` \n\n### operator::tensorflow::Output\n\n```gdscript\n operator::tensorflow::Output() const \n``` \n\nPublic static functions\n-----------------------\n\n### MultiplyLinearByLr\n\n```text\nAttrs MultiplyLinearByLr(\n bool x\n)\n``` \n\n### UseLocking\n\n```text\nAttrs UseLocking(\n bool x\n)\n```"]]