Restez organisé à l'aide des collections
Enregistrez et classez les contenus selon vos préférences.
flux tensoriel : : opérations : : RessourceAppliquerAdam
#include <training_ops.h> Mettez à jour '*var' selon l'algorithme d'Adam.
Résumé
$$lr_t := {learning_rate} * {1 - beta_2^t} / (1 - beta_1^t)$$ $$m_t := beta_1 * m_{t-1} + (1 - beta_1) * g$$ $$v_t := beta_2 * v_{t-1} + (1 - beta_2) * g * g$$ $$variable := variable - lr_t * m_t / ({v_t} + )$$
Arguments :
- scope : un objet Scope
- var : doit provenir d'une variable ().
- m : Doit provenir d’une variable().
- v : doit provenir d'une variable ().
- beta1_power : doit être un scalaire.
- beta2_power : doit être un scalaire.
- lr : facteur d’échelle. Ça doit être un scalaire.
- bêta1 : facteur de dynamique. Ça doit être un scalaire.
- bêta2 : facteur d'élan. Ça doit être un scalaire.
- epsilon : terme de crête. Ça doit être un scalaire.
- grad : Le dégradé.
Attributs facultatifs (voir Attrs ) :
- use_locking : Si
True , la mise à jour des tenseurs var, m et v sera protégée par un verrou ; sinon, le comportement n'est pas défini, mais peut présenter moins de conflits. - use_nesterov : si
True , utilise la mise à jour Nesterov.
Retours :
Constructeurs et Destructeurs |
|---|
ResourceApplyAdam (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input m, :: tensorflow::Input v, :: tensorflow::Input beta1_power, :: tensorflow::Input beta2_power, :: tensorflow::Input lr, :: tensorflow::Input beta1, :: tensorflow::Input beta2, :: tensorflow::Input epsilon, :: tensorflow::Input grad)
|
ResourceApplyAdam (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input m, :: tensorflow::Input v, :: tensorflow::Input beta1_power, :: tensorflow::Input beta2_power, :: tensorflow::Input lr, :: tensorflow::Input beta1, :: tensorflow::Input beta2, :: tensorflow::Input epsilon, :: tensorflow::Input grad, const ResourceApplyAdam::Attrs & attrs)
|
Attributs publics
Fonctions publiques
RessourceAppliquerAdam
ResourceApplyAdam(
const ::tensorflow::Scope & scope,
::tensorflow::Input var,
::tensorflow::Input m,
::tensorflow::Input v,
::tensorflow::Input beta1_power,
::tensorflow::Input beta2_power,
::tensorflow::Input lr,
::tensorflow::Input beta1,
::tensorflow::Input beta2,
::tensorflow::Input epsilon,
::tensorflow::Input grad
)
RessourceAppliquerAdam
ResourceApplyAdam(
const ::tensorflow::Scope & scope,
::tensorflow::Input var,
::tensorflow::Input m,
::tensorflow::Input v,
::tensorflow::Input beta1_power,
::tensorflow::Input beta2_power,
::tensorflow::Input lr,
::tensorflow::Input beta1,
::tensorflow::Input beta2,
::tensorflow::Input epsilon,
::tensorflow::Input grad,
const ResourceApplyAdam::Attrs & attrs
)
opérateur :: tensorflow :: Opération
operator::tensorflow::Operation() const
Fonctions statiques publiques
UtiliserVerrouillage
Attrs UseLocking(
bool x
)
Utiliser Nesterov
Attrs UseNesterov(
bool x
)
Sauf indication contraire, le contenu de cette page est régi par une licence Creative Commons Attribution 4.0, et les échantillons de code sont régis par une licence Apache 2.0. Pour en savoir plus, consultez les Règles du site Google Developers. Java est une marque déposée d'Oracle et/ou de ses sociétés affiliées.
Dernière mise à jour le 2025/07/25 (UTC).
[null,null,["Dernière mise à jour le 2025/07/25 (UTC)."],[],[],null,["# tensorflow::ops::ResourceApplyAdam Class Reference\n\ntensorflow::ops::ResourceApplyAdam\n==================================\n\n`#include \u003ctraining_ops.h\u003e`\n\nUpdate '\\*var' according to the Adam algorithm.\n\nSummary\n-------\n\n$$lr_t := {learning_rate} \\* {1 - beta_2\\^t} / (1 - beta_1\\^t)$$ $$m_t := beta_1 \\* m_{t-1} + (1 - beta_1) \\* g$$ $$v_t := beta_2 \\* v_{t-1} + (1 - beta_2) \\* g \\* g$$ $$variable := variable - lr_t \\* m_t / ({v_t} + )$$\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- m: Should be from a Variable().\n- v: Should be from a Variable().\n- beta1_power: Must be a scalar.\n- beta2_power: Must be a scalar.\n- lr: Scaling factor. Must be a scalar.\n- beta1: Momentum factor. Must be a scalar.\n- beta2: Momentum factor. Must be a scalar.\n- epsilon: Ridge term. Must be a scalar.\n- grad: The gradient.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-adam/attrs#structtensorflow_1_1ops_1_1_resource_apply_adam_1_1_attrs)):\n\n- use_locking: If `True`, updating of the var, m, and v tensors will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.\n- use_nesterov: If `True`, uses the nesterov update.\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| [ResourceApplyAdam](#classtensorflow_1_1ops_1_1_resource_apply_adam_1ac795afbdb2b0b71ee2d2de82cc60f117)`(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)` m, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` v, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` beta1_power, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` beta2_power, ::`[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)` beta1, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` beta2, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` epsilon, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad)` ||\n| [ResourceApplyAdam](#classtensorflow_1_1ops_1_1_resource_apply_adam_1ab1142d9fee53446380bed6cf6ffc3d16)`(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)` m, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` v, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` beta1_power, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` beta2_power, ::`[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)` beta1, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` beta2, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` epsilon, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, const `[ResourceApplyAdam::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-adam/attrs#structtensorflow_1_1ops_1_1_resource_apply_adam_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|-------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_resource_apply_adam_1aabbba4cd6d62166c77e9ac3da3caa0bd) | [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_adam_1aaf87aff51ef168ae2807151dccb08a18)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|-------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------|\n| [UseLocking](#classtensorflow_1_1ops_1_1_resource_apply_adam_1a608016b3becbe65a6899bb3c0d4c1cf4)`(bool x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-adam/attrs#structtensorflow_1_1ops_1_1_resource_apply_adam_1_1_attrs) |\n| [UseNesterov](#classtensorflow_1_1ops_1_1_resource_apply_adam_1aa7ac09e230c73e3ee869c80a9eef764d)`(bool x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-adam/attrs#structtensorflow_1_1ops_1_1_resource_apply_adam_1_1_attrs) |\n\n| ### Structs ||\n|--------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::ResourceApplyAdam::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-adam/attrs) | Optional attribute setters for [ResourceApplyAdam](/versions/r1.15/api_docs/cc/class/tensorflow/ops/resource-apply-adam#classtensorflow_1_1ops_1_1_resource_apply_adam). |\n\nPublic attributes\n-----------------\n\n### operation\n\n```text\nOperation operation\n``` \n\nPublic functions\n----------------\n\n### ResourceApplyAdam\n\n```gdscript\n ResourceApplyAdam(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input m,\n ::tensorflow::Input v,\n ::tensorflow::Input beta1_power,\n ::tensorflow::Input beta2_power,\n ::tensorflow::Input lr,\n ::tensorflow::Input beta1,\n ::tensorflow::Input beta2,\n ::tensorflow::Input epsilon,\n ::tensorflow::Input grad\n)\n``` \n\n### ResourceApplyAdam\n\n```gdscript\n ResourceApplyAdam(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input m,\n ::tensorflow::Input v,\n ::tensorflow::Input beta1_power,\n ::tensorflow::Input beta2_power,\n ::tensorflow::Input lr,\n ::tensorflow::Input beta1,\n ::tensorflow::Input beta2,\n ::tensorflow::Input epsilon,\n ::tensorflow::Input grad,\n const ResourceApplyAdam::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``` \n\n### UseNesterov\n\n```text\nAttrs UseNesterov(\n bool x\n)\n```"]]
