Koleksiyonlar ile düzeninizi koruyun
İçeriği tercihlerinize göre kaydedin ve kategorilere ayırın.
tensor akışı:: işlem:: KaynakUygulaAdam
#include <training_ops.h>
'*var'ı Adam algoritmasına göre güncelleyin.
Özet
$$lr_t := {learning_rate} * {1 - beta_2^t} / (1 - beta_1^t)$$ $$m_t := beta_1 * m_{t-1} + (1 - beta_1) * g$$ $$v_t := beta_2 * v_{t-1} + (1 - beta_2) * g * g$$ $$variable := variable - lr_t * m_t / ({v_t} + )$$
Argümanlar:
- kapsam: Bir Kapsam nesnesi
- var: Bir Variable()'dan olmalıdır.
- m: Bir Variable()'dan olmalıdır.
- v: Bir Variable()'dan olmalıdır.
- beta1_power: Skaler olmalı.
- beta2_power: Skaler olmalı.
- lr: Ölçeklendirme faktörü. Bir skaler olmalı.
- beta1: Momentum faktörü. Bir skaler olmalı.
- beta2: Momentum faktörü. Bir skaler olmalı.
- epsilon: Ridge terimi. Bir skaler olmalı.
- grad: Gradyan.
İsteğe bağlı özellikler (bkz. Attrs
):
- use_locking:
True
ise var, m ve v tensörlerinin güncellenmesi bir kilitle korunacaktır; aksi takdirde davranış tanımsızdır ancak daha az çekişme sergileyebilir. - use_nesterov:
True
ise nesterov güncellemesini kullanır.
İade:
Yapıcılar ve Yıkıcılar |
---|
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) |
Genel özellikler
Kamu işlevleri
KaynakUygulaAdam
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
)
KaynakUygulaAdam
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
)
operatör::tensorflow::İşlem
operator::tensorflow::Operation() const
Genel statik işlevler
KullanımKilitleme
Attrs UseLocking(
bool x
)
KullanımNesterov
Attrs UseNesterov(
bool x
)
Aksi belirtilmediği sürece bu sayfanın içeriği Creative Commons Atıf 4.0 Lisansı altında ve kod örnekleri Apache 2.0 Lisansı altında lisanslanmıştır. Ayrıntılı bilgi için Google Developers Site Politikaları'na göz atın. Java, Oracle ve/veya satış ortaklarının tescilli ticari markasıdır.
Son güncelleme tarihi: 2025-07-25 UTC.
[null,null,["Son güncelleme tarihi: 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```"]]