تدفق التوتر:: العمليات:: تطبيقFtrl
#include <training_ops.h>
قم بتحديث '*var' وفقًا لمخطط Ftrl-proximal.
ملخص
accum_new = تراكم + غراد * غراد خطي += غراد + (accum_new^(-lr_power) - تراكم^(-lr_power)) / lr * var تربيعي = 1.0 / (accum_new^(lr_power) * lr) + 2 * l2 var = (علامة(خطي) * l1 - خطي) / من الدرجة الثانية إذا |خطي| > l1 آخر 0.0 تراكم = تراكم_جديد
الحجج:
- النطاق: كائن النطاق
- فار: يجب أن يكون من متغير ().
- تراكم: يجب أن يكون من متغير ().
- خطي: يجب أن يكون من متغير ().
- غراد: التدرج.
- lr: عامل التحجيم. يجب أن يكون العددية.
- l1: تنظيم L1. يجب أن يكون العددية.
- l2: تنظيم L2. يجب أن يكون العددية.
- lr_power: عامل التحجيم. يجب أن يكون العددية.
السمات الاختيارية (انظر Attrs
):
- use_locking: إذا كان
True
، فسيتم حماية تحديث موترتي var وaccum بواسطة قفل؛ وإلا فإن السلوك غير محدد، ولكنه قد يحمل قدرًا أقل من الخلاف.
العوائد:
-
Output
: نفس "فار".
البنائين والمدمرين | |
---|---|
ApplyFtrl (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 lr_power) | |
ApplyFtrl (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 lr_power, const ApplyFtrl::Attrs & attrs) |
الصفات العامة | |
---|---|
operation | |
out |
الوظائف العامة | |
---|---|
node () const | ::tensorflow::Node * |
operator::tensorflow::Input () const | |
operator::tensorflow::Output () const |
وظائف ثابتة العامة | |
---|---|
UseLocking (bool x) |
الهياكل | |
---|---|
Tensorflow:: ops:: ApplyFtrl:: Attrs | محددات السمات الاختيارية لـ ApplyFtrl . |
الصفات العامة
عملية
Operation operation
خارج
::tensorflow::Output out
الوظائف العامة
تطبيقFtrl
ApplyFtrl( 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 lr_power )
تطبيقFtrl
ApplyFtrl( 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 lr_power, const ApplyFtrl::Attrs & attrs )
العقدة
::tensorflow::Node * node() const
المشغل::tensorflow::الإدخال
operator::tensorflow::Input() const
المشغل::tensorflow::الإخراج
operator::tensorflow::Output() const
وظائف ثابتة العامة
UseLocking
Attrs UseLocking( bool x )
إنّ محتوى هذه الصفحة مرخّص بموجب ترخيص Creative Commons Attribution 4.0 ما لم يُنصّ على خلاف ذلك، ونماذج الرموز مرخّصة بموجب ترخيص Apache 2.0. للاطّلاع على التفاصيل، يُرجى مراجعة سياسات موقع Google Developers. إنّ Java هي علامة تجارية مسجَّلة لشركة Oracle و/أو شركائها التابعين.
تاريخ التعديل الأخير: 2025-07-27 (حسب التوقيت العالمي المتفَّق عليه)
[null,null,["تاريخ التعديل الأخير: 2025-07-27 (حسب التوقيت العالمي المتفَّق عليه)"],[],[],null,["# tensorflow::ops::ApplyFtrl Class Reference\n\ntensorflow::ops::ApplyFtrl\n==========================\n\n`#include \u003ctraining_ops.h\u003e`\n\nUpdate '\\*var' according to the Ftrl-proximal scheme.\n\nSummary\n-------\n\naccum_new = accum + grad \\* grad linear += grad + (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/r2.0/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 regulariation. Must be a scalar.\n- l2: L2 regulariation. Must be a scalar.\n- lr_power: Scaling factor. Must be a scalar.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/apply-ftrl/attrs#structtensorflow_1_1ops_1_1_apply_ftrl_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/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): Same as \"var\".\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [ApplyFtrl](#classtensorflow_1_1ops_1_1_apply_ftrl_1aac92c9a511a285b2ba2fd70bb8a9162a)`(const ::`[tensorflow::Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` var, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` linear, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l1, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr_power)` ||\n| [ApplyFtrl](#classtensorflow_1_1ops_1_1_apply_ftrl_1a08ae5f59e96c0806cac695b49d0b7e6c)`(const ::`[tensorflow::Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` var, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` linear, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l1, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr_power, const `[ApplyFtrl::Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/apply-ftrl/attrs#structtensorflow_1_1ops_1_1_apply_ftrl_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|----------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_apply_ftrl_1a60bfef0fb8957ad8ebd90bcc1b17deb5) | [Operation](/versions/r2.0/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [out](#classtensorflow_1_1ops_1_1_apply_ftrl_1a4ce2fdad41c33119e072faa142ab6388) | `::`[tensorflow::Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|----------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_apply_ftrl_1a83ed3b447bb12a6a2026a5ecd546311c)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_apply_ftrl_1a93e6e2aec1e38ede37126e36574daf64)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_apply_ftrl_1aae1ab05c604dfd771e781b62fa213b30)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|---------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------|\n| [UseLocking](#classtensorflow_1_1ops_1_1_apply_ftrl_1a1052290b6434db12d630a2e9d0b1b197)`(bool x)` | [Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/apply-ftrl/attrs#structtensorflow_1_1ops_1_1_apply_ftrl_1_1_attrs) |\n\n| ### Structs ||\n|--------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::ApplyFtrl::Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/apply-ftrl/attrs) | Optional attribute setters for [ApplyFtrl](/versions/r2.0/api_docs/cc/class/tensorflow/ops/apply-ftrl#classtensorflow_1_1ops_1_1_apply_ftrl). |\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### ApplyFtrl\n\n```gdscript\n ApplyFtrl(\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 lr_power\n)\n``` \n\n### ApplyFtrl\n\n```gdscript\n ApplyFtrl(\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 lr_power,\n const ApplyFtrl::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### UseLocking\n\n```text\nAttrs UseLocking(\n bool x\n)\n```"]]