Koleksiyonlar ile düzeninizi koruyun
İçeriği tercihlerinize göre kaydedin ve kategorilere ayırın.
tensör akışı:: işlem:: RMSProp'u Uygula
#include <training_ops.h>
'*var'ı RMSProp algoritmasına göre güncelleyin.
Özet
Bu algoritmanın yoğun uygulanmasında ms ve mom'in derece sıfır olsa bile güncelleneceğini, ancak bu seyrek uygulamada ms ve mom'in derecenin sıfır olduğu yinelemelerde güncellenmeyeceğini unutmayın.
ortalama_kare = bozunma * ortalama_kare + (1-bozunma) * gradyan ** 2 Delta = öğrenme_oranı * gradyan / sqrt(ortalama_kare + epsilon)
ms <- rho * ms_{t-1} + (1-rho) * grad * grad mom <- momentum * mom_{t-1} + lr * grad / sqrt(ms + epsilon) var <- var - mom
Argümanlar:
- kapsam: Bir Kapsam nesnesi
- var: Bir Variable()'dan olmalıdır.
- ms: Bir Variable()'dan olmalıdır.
- anne: Bir Variable()'dan olmalı.
- lr: Ölçeklendirme faktörü. Bir skaler olmalı.
- rho: Bozunma oranı. Bir skaler olmalı.
- epsilon: Ridge terimi. Bir skaler olmalı.
- grad: Gradyan.
İsteğe bağlı özellikler (bkz. Attrs
):
- use_locking:
True
ise var, ms ve mom tensörlerinin güncellenmesi bir kilitle korunur; aksi takdirde davranış tanımsızdır ancak daha az çekişme sergileyebilir.
İade:
Yapıcılar ve Yıkıcılar |
---|
ApplyRMSProp (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input ms, :: tensorflow::Input mom, :: tensorflow::Input lr, :: tensorflow::Input rho, :: tensorflow::Input momentum, :: tensorflow::Input epsilon, :: tensorflow::Input grad)
|
ApplyRMSProp (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input ms, :: tensorflow::Input mom, :: tensorflow::Input lr, :: tensorflow::Input rho, :: tensorflow::Input momentum, :: tensorflow::Input epsilon, :: tensorflow::Input grad, const ApplyRMSProp::Attrs & attrs) |
Genel özellikler
Kamu işlevleri
düğüm
::tensorflow::Node * node() const
operator::tensorflow::Input() const
operatör::tensorflow::Çıktı
operator::tensorflow::Output() const
Genel statik işlevler
KullanımKilitleme
Attrs UseLocking(
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: 2025-07-26 UTC.
[null,null,["Son güncelleme tarihi: 2025-07-26 UTC."],[],[],null,["# tensorflow::ops::ApplyRMSProp Class Reference\n\ntensorflow::ops::ApplyRMSProp\n=============================\n\n`#include \u003ctraining_ops.h\u003e`\n\nUpdate '\\*var' according to the RMSProp algorithm.\n\nSummary\n-------\n\nNote that in dense implementation of this algorithm, ms and mom will update even if the grad is zero, but in this sparse implementation, ms and mom will not update in iterations during which the grad is zero.\n\nmean_square = decay \\* mean_square + (1-decay) \\* gradient \\*\\* 2 Delta = learning_rate \\* gradient / sqrt(mean_square + epsilon)\n\nms \\\u003c- rho \\* ms_{t-1} + (1-rho) \\* grad \\* grad mom \\\u003c- momentum \\* mom_{t-1} + lr \\* grad / sqrt(ms + epsilon) var \\\u003c- var - mom\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- ms: Should be from a Variable().\n- mom: Should be from a Variable().\n- lr: Scaling factor. Must be a scalar.\n- rho: Decay rate. 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/apply-r-m-s-prop/attrs#structtensorflow_1_1ops_1_1_apply_r_m_s_prop_1_1_attrs)):\n\n- use_locking: If `True`, updating of the var, ms, and mom tensors is protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): Same as \"var\".\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [ApplyRMSProp](#classtensorflow_1_1ops_1_1_apply_r_m_s_prop_1a590f878f7698fa0f56a0b5226d658855)`(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)` ms, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` mom, ::`[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)` rho, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` momentum, ::`[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| [ApplyRMSProp](#classtensorflow_1_1ops_1_1_apply_r_m_s_prop_1a4d5ef1aee8f989dbbe2c16e3538482b2)`(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)` ms, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` mom, ::`[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)` rho, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` momentum, ::`[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 `[ApplyRMSProp::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/apply-r-m-s-prop/attrs#structtensorflow_1_1ops_1_1_apply_r_m_s_prop_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|----------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_apply_r_m_s_prop_1a412619ace9b4ff26ec14ae0ecfb8ac11) | [Operation](/versions/r1.15/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [out](#classtensorflow_1_1ops_1_1_apply_r_m_s_prop_1a72a4daee4e9ef1d2a3f3d4a088ed010f) | `::`[tensorflow::Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|----------------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_apply_r_m_s_prop_1a82fe90ad87c393e443f8459e9b0158db)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_apply_r_m_s_prop_1aabbb7630a5cd439e4694eda0021d694d)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_apply_r_m_s_prop_1a4e664360fbdde8291f80a08b2347fdf0)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|---------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------|\n| [UseLocking](#classtensorflow_1_1ops_1_1_apply_r_m_s_prop_1ae0d5824bd2a81852e1e2185346adb9c3)`(bool x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/apply-r-m-s-prop/attrs#structtensorflow_1_1ops_1_1_apply_r_m_s_prop_1_1_attrs) |\n\n| ### Structs ||\n|------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::ApplyRMSProp::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/apply-r-m-s-prop/attrs) | Optional attribute setters for [ApplyRMSProp](/versions/r1.15/api_docs/cc/class/tensorflow/ops/apply-r-m-s-prop#classtensorflow_1_1ops_1_1_apply_r_m_s_prop). |\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### ApplyRMSProp\n\n```gdscript\n ApplyRMSProp(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input ms,\n ::tensorflow::Input mom,\n ::tensorflow::Input lr,\n ::tensorflow::Input rho,\n ::tensorflow::Input momentum,\n ::tensorflow::Input epsilon,\n ::tensorflow::Input grad\n)\n``` \n\n### ApplyRMSProp\n\n```gdscript\n ApplyRMSProp(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input ms,\n ::tensorflow::Input mom,\n ::tensorflow::Input lr,\n ::tensorflow::Input rho,\n ::tensorflow::Input momentum,\n ::tensorflow::Input epsilon,\n ::tensorflow::Input grad,\n const ApplyRMSProp::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```"]]