コレクションでコンテンツを整理
必要に応じて、コンテンツの保存と分類を行います。
テンソルフロー::作戦::リソースApplyAdadelta
#include <training_ops.h>
adadelta スキームに従って「*var」を更新します。
まとめ
accum = rho() * accum + (1 - rho()) * grad.square(); update = (update_accum + epsilon).sqrt() * (accum + epsilon()).rsqrt() * grad; update_accum = rho() * update_accum + (1 - rho()) * update.square(); var -= 更新;
引数:
- スコープ:スコープオブジェクト
- var: Variable() から取得する必要があります。
- accum: Variable() から取得する必要があります。
- accum_update: Variable() から取得する必要があります。
- lr: スケーリング係数。スカラーでなければなりません。
- rho: 減衰係数。スカラーでなければなりません。
- ε: 定数係数。スカラーでなければなりません。
- grad: グラデーション。
オプションの属性 ( Attrs
を参照):
- use_locking: True の場合、var、accum、update_accum テンソルの更新はロックによって保護されます。それ以外の場合、動作は未定義ですが、競合が少なくなる可能性があります。
戻り値:
コンストラクターとデストラクター |
---|
ResourceApplyAdadelta (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input accum_update, :: tensorflow::Input lr, :: tensorflow::Input rho, :: tensorflow::Input epsilon, :: tensorflow::Input grad)
|
ResourceApplyAdadelta (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input accum_update, :: tensorflow::Input lr, :: tensorflow::Input rho, :: tensorflow::Input epsilon, :: tensorflow::Input grad, const ResourceApplyAdadelta::Attrs & attrs) |
パブリック属性
公共機能
演算子::tensorflow::オペレーション
operator::tensorflow::Operation() const
パブリック静的関数
ロックを使用する
Attrs UseLocking(
bool x
)
特に記載のない限り、このページのコンテンツはクリエイティブ・コモンズの表示 4.0 ライセンスにより使用許諾されます。コードサンプルは Apache 2.0 ライセンスにより使用許諾されます。詳しくは、Google Developers サイトのポリシーをご覧ください。Java は Oracle および関連会社の登録商標です。
最終更新日 2025-07-27 UTC。
[null,null,["最終更新日 2025-07-27 UTC。"],[],[],null,["# tensorflow::ops::ResourceApplyAdadelta Class Reference\n\ntensorflow::ops::ResourceApplyAdadelta\n======================================\n\n`#include \u003ctraining_ops.h\u003e`\n\nUpdate '\\*var' according to the adadelta scheme.\n\nSummary\n-------\n\naccum = rho() \\* accum + (1 - rho()) \\* grad.square(); update = (update_accum + epsilon).sqrt() \\* (accum + epsilon()).rsqrt() \\* grad; update_accum = rho() \\* update_accum + (1 - rho()) \\* update.square(); var -= update;\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- accum_update: Should be from a Variable().\n- lr: Scaling factor. Must be a scalar.\n- rho: Decay factor. Must be a scalar.\n- epsilon: Constant factor. Must be a scalar.\n- grad: The gradient.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/resource-apply-adadelta/attrs#structtensorflow_1_1ops_1_1_resource_apply_adadelta_1_1_attrs)):\n\n- use_locking: If True, updating of the var, accum and update_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/r2.3/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation)\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [ResourceApplyAdadelta](#classtensorflow_1_1ops_1_1_resource_apply_adadelta_1a4f85dc7a030d3e04af02dbcbb59ce1a9)`(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)` accum_update, ::`[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)` rho, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` epsilon, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad)` ||\n| [ResourceApplyAdadelta](#classtensorflow_1_1ops_1_1_resource_apply_adadelta_1a883cc46b972fbf81192d699ee52def56)`(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)` accum_update, ::`[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)` rho, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` epsilon, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, const `[ResourceApplyAdadelta::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/resource-apply-adadelta/attrs#structtensorflow_1_1ops_1_1_resource_apply_adadelta_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|-----------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_resource_apply_adadelta_1a4dd0008d30f0e32e1221225a4be2a2f2) | [Operation](/versions/r2.3/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_adadelta_1ac80f2bfde898d7a7c247161e484d603f)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|----------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [UseLocking](#classtensorflow_1_1ops_1_1_resource_apply_adadelta_1afbd53a1956a5e15a96e9872d680893fc)`(bool x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/resource-apply-adadelta/attrs#structtensorflow_1_1ops_1_1_resource_apply_adadelta_1_1_attrs) |\n\n| ### Structs ||\n|---------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::ResourceApplyAdadelta::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/resource-apply-adadelta/attrs) | Optional attribute setters for [ResourceApplyAdadelta](/versions/r2.3/api_docs/cc/class/tensorflow/ops/resource-apply-adadelta#classtensorflow_1_1ops_1_1_resource_apply_adadelta). |\n\nPublic attributes\n-----------------\n\n### operation\n\n```text\nOperation operation\n``` \n\nPublic functions\n----------------\n\n### ResourceApplyAdadelta\n\n```gdscript\n ResourceApplyAdadelta(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input accum,\n ::tensorflow::Input accum_update,\n ::tensorflow::Input lr,\n ::tensorflow::Input rho,\n ::tensorflow::Input epsilon,\n ::tensorflow::Input grad\n)\n``` \n\n### ResourceApplyAdadelta\n\n```gdscript\n ResourceApplyAdadelta(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input accum,\n ::tensorflow::Input accum_update,\n ::tensorflow::Input lr,\n ::tensorflow::Input rho,\n ::tensorflow::Input epsilon,\n ::tensorflow::Input grad,\n const ResourceApplyAdadelta::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```"]]