컬렉션을 사용해 정리하기
내 환경설정을 기준으로 콘텐츠를 저장하고 분류하세요.
텐서플로우:: 작전:: 리소스ApplyFtrlV2
#include <training_ops.h>
Ftrl-proximal 체계에 따라 '*var'를 업데이트합니다.
요약
grad_with_shrinkage = grad + 2 * l2_shrinkage * var accum_new = accum + grad_with_shrinkage * grad_with_shrinkage 선형 += grad_with_shrinkage + (accum_new^(-lr_power) - accum^(-lr_power)) / lr * var 2차 = 1.0 / (accum_new^(lr_power) * lr) + 2 * l2 var = (sign(linear) * l1 - 선형) / 2차 if |linear| > l1 else 0.0 accum = accum_new
인수:
- 범위: 범위 개체
- var: Variable()에서 가져와야 합니다.
- accum: Variable()에서 가져와야 합니다.
- 선형: Variable()에서 가져와야 합니다.
- grad: 그라데이션입니다.
- lr: 스케일링 팩터. 스칼라여야 합니다.
- l1: L1 정규화. 스칼라여야 합니다.
- l2: L2 수축 정규화. 스칼라여야 합니다.
- lr_power: 스케일링 팩터. 스칼라여야 합니다.
선택적 속성( Attrs
참조):
- use_locking:
True
인 경우 var 및 accum 텐서 업데이트는 잠금으로 보호됩니다. 그렇지 않으면 동작이 정의되지 않지만 경합이 덜 나타날 수 있습니다.
보고:
생성자와 소멸자 |
---|
ResourceApplyFtrlV2 (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)
|
ResourceApplyFtrlV2 (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 ResourceApplyFtrlV2::Attrs & attrs) |
공개 속성
공공 기능
리소스ApplyFtrlV2
ResourceApplyFtrlV2(
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 ResourceApplyFtrlV2::Attrs & attrs
)
연산자::텐서플로우::작업
operator::tensorflow::Operation() const
공개 정적 함수
사용잠금
Attrs UseLocking(
bool x
)
달리 명시되지 않는 한 이 페이지의 콘텐츠에는 Creative Commons Attribution 4.0 라이선스에 따라 라이선스가 부여되며, 코드 샘플에는 Apache 2.0 라이선스에 따라 라이선스가 부여됩니다. 자세한 내용은 Google Developers 사이트 정책을 참조하세요. 자바는 Oracle 및/또는 Oracle 계열사의 등록 상표입니다.
최종 업데이트: 2025-07-26(UTC)
[null,null,["최종 업데이트: 2025-07-26(UTC)"],[],[],null,["# tensorflow::ops::ResourceApplyFtrlV2 Class Reference\n\ntensorflow::ops::ResourceApplyFtrlV2\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_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\\| \\\u003e l1 else 0.0 accum = accum_new\n\nArguments:\n\n- scope: A [Scope](/versions/r1.15/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 shrinkage regulariation. Must be a scalar.\n- lr_power: Scaling factor. Must be a scalar.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-ftrl-v2/attrs#structtensorflow_1_1ops_1_1_resource_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- the created [Operation](/versions/r1.15/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation)\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [ResourceApplyFtrlV2](#classtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1af0cd2da7fd04b586801c7ff65201b3c6)`(const ::`[tensorflow::Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` var, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` linear, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l1, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2_shrinkage, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr_power)` ||\n| [ResourceApplyFtrlV2](#classtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1a2ddc33ae007578e3d302ff7cd7da72bf)`(const ::`[tensorflow::Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` var, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` linear, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l1, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2_shrinkage, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr_power, const `[ResourceApplyFtrlV2::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-ftrl-v2/attrs#structtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|----------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1a055d8d299e112489bb08106d147d44be) | [Operation](/versions/r1.15/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n\n| ### Public functions ||\n|-------------------------------------------------------------------------------------------------------------------------------------|---------|\n| [operator::tensorflow::Operation](#classtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1a58cdd4377a81f3e98cc04b4cd0428827)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|---------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [UseLocking](#classtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1a52d5b1bbc4f4f6722afad9df9b5ec209)`(bool x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-ftrl-v2/attrs#structtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1_1_attrs) |\n\n| ### Structs ||\n|-------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::ResourceApplyFtrlV2::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-ftrl-v2/attrs) | Optional attribute setters for [ResourceApplyFtrlV2](/versions/r1.15/api_docs/cc/class/tensorflow/ops/resource-apply-ftrl-v2#classtensorflow_1_1ops_1_1_resource_apply_ftrl_v2). |\n\nPublic attributes\n-----------------\n\n### operation\n\n```text\nOperation operation\n``` \n\nPublic functions\n----------------\n\n### ResourceApplyFtrlV2\n\n```gdscript\n ResourceApplyFtrlV2(\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### ResourceApplyFtrlV2\n\n```gdscript\n ResourceApplyFtrlV2(\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 ResourceApplyFtrlV2::Attrs & attrs\n)\n``` \n\n### operator::tensorflow::Operation\n\n```gdscript\n operator::tensorflow::Operation() const \n``` \n\nPublic static functions\n-----------------------\n\n### UseLocking\n\n```text\nAttrs UseLocking(\n bool x\n)\n```"]]