Koleksiyonlar ile düzeninizi koruyun
İçeriği tercihlerinize göre kaydedin ve kategorilere ayırın.
tensor akışı:: işlem:: SparseApplyFtrl
#include <training_ops.h> '*var' içindeki ilgili girişleri Ftrl-proximal şemasına göre güncelleyin.
Özet
Yani, derecelendirdiğimiz satırlar için var, accum ve lineer'ı aşağıdaki gibi güncelliyoruz: $$accum_new = accum + grad * grad$$ $$linear += grad + (accum_{new}^{-lr_{power}} - accum^{-lr_{power}} / lr * var$$ $$quadratic = 1.0 / (accum_{new}^{lr_{power}} * lr) + 2 * l2$$ $$var = (sign(linear) * l1 - linear) / quadratic\ if\ |linear| > l1\ else\ 0.0$$ $$accum = accum_{new}$$
Argümanlar:
- kapsam: Bir Kapsam nesnesi
- var: Bir Variable()'dan olmalıdır.
- accum: Bir Variable()'dan olmalıdır.
- doğrusal: Bir Değişken()'den olmalıdır.
- grad: Gradyan.
- indeksler: var ve accum'un ilk boyutuna ait indekslerden oluşan bir vektör.
- lr: Ölçeklendirme faktörü. Bir skaler olmalı.
- l1: L1 düzenlemesi. Bir skaler olmalı.
- l2: L2 düzenlemesi. Bir skaler olmalı.
- lr_power: Ölçeklendirme faktörü. Bir skaler olmalı.
İsteğe bağlı özellikler (bkz. Attrs ):
- use_locking:
True ise, var ve accum tensörlerinin güncellenmesi bir kilitle korunacaktır; aksi takdirde davranış tanımsızdır ancak daha az çekişme sergileyebilir.
İade:
Yapıcılar ve Yıkıcılar |
|---|
SparseApplyFtrl (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input linear, :: tensorflow::Input grad, :: tensorflow::Input indices, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input lr_power)
|
SparseApplyFtrl (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input linear, :: tensorflow::Input grad, :: tensorflow::Input indices, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input lr_power, const SparseApplyFtrl::Attrs & attrs)
|
Genel özellikler
Kamu işlevleri
SparseApplyFtrl
SparseApplyFtrl(
const ::tensorflow::Scope & scope,
::tensorflow::Input var,
::tensorflow::Input accum,
::tensorflow::Input linear,
::tensorflow::Input grad,
::tensorflow::Input indices,
::tensorflow::Input lr,
::tensorflow::Input l1,
::tensorflow::Input l2,
::tensorflow::Input lr_power,
const SparseApplyFtrl::Attrs & attrs
)
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::SparseApplyFtrl Class Reference\n\ntensorflow::ops::SparseApplyFtrl\n================================\n\n`#include \u003ctraining_ops.h\u003e`\n\nUpdate relevant entries in '\\*var' according to the Ftrl-proximal scheme.\n\nSummary\n-------\n\nThat is for rows we have grad for, we update var, accum and linear as follows: $$accum_new = accum + grad \\* grad$$ $$linear += grad + (accum_{new}\\^{-lr_{power}} - accum\\^{-lr_{power}} / lr \\* var$$ $$quadratic = 1.0 / (accum_{new}\\^{lr_{power}} \\* lr) + 2 \\* l2$$ $$var = (sign(linear) \\* l1 - linear) / quadratic\\\\ if\\\\ \\|linear\\| \\\u003e l1\\\\ else\\\\ 0.0$$ $$accum = accum_{new}$$\n\nArguments:\n\n- scope: A [Scope](/versions/r2.0/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- indices: A vector of indices into the first dimension of var and accum.\n- lr: Scaling factor. Must be a scalar.\n- l1: L1 regularization. Must be a scalar.\n- l2: L2 regularization. Must be a scalar.\n- lr_power: Scaling factor. Must be a scalar.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/sparse-apply-ftrl/attrs#structtensorflow_1_1ops_1_1_sparse_apply_ftrl_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- [Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): Same as \"var\".\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [SparseApplyFtrl](#classtensorflow_1_1ops_1_1_sparse_apply_ftrl_1acfbd35749a971ae408ba24c0bb56facd)`(const ::`[tensorflow::Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` var, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` linear, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` indices, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l1, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr_power)` ||\n| [SparseApplyFtrl](#classtensorflow_1_1ops_1_1_sparse_apply_ftrl_1ae80720b9dac0b6801255f556bd27e249)`(const ::`[tensorflow::Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` var, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` linear, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` indices, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l1, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr_power, const `[SparseApplyFtrl::Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/sparse-apply-ftrl/attrs#structtensorflow_1_1ops_1_1_sparse_apply_ftrl_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|-----------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_sparse_apply_ftrl_1ac97a954bbe52219dcd24e48de02f37e2) | [Operation](/versions/r2.0/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [out](#classtensorflow_1_1ops_1_1_sparse_apply_ftrl_1aade91702a26588081047940b922727e9) | `::`[tensorflow::Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|-----------------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_sparse_apply_ftrl_1acd3ec55f3b5d70e30f21395166e3c638)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_sparse_apply_ftrl_1afa8bb71a8583497722ad2240f94c157f)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_sparse_apply_ftrl_1a5964fb493100ead822e39ca5e2ed2710)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|----------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------|\n| [UseLocking](#classtensorflow_1_1ops_1_1_sparse_apply_ftrl_1aa19ce04694959f2590e9a0286d0ff8b9)`(bool x)` | [Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/sparse-apply-ftrl/attrs#structtensorflow_1_1ops_1_1_sparse_apply_ftrl_1_1_attrs) |\n\n| ### Structs ||\n|---------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::SparseApplyFtrl::Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/sparse-apply-ftrl/attrs) | Optional attribute setters for [SparseApplyFtrl](/versions/r2.0/api_docs/cc/class/tensorflow/ops/sparse-apply-ftrl#classtensorflow_1_1ops_1_1_sparse_apply_ftrl). |\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### SparseApplyFtrl\n\n```gdscript\n SparseApplyFtrl(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input accum,\n ::tensorflow::Input linear,\n ::tensorflow::Input grad,\n ::tensorflow::Input indices,\n ::tensorflow::Input lr,\n ::tensorflow::Input l1,\n ::tensorflow::Input l2,\n ::tensorflow::Input lr_power\n)\n``` \n\n### SparseApplyFtrl\n\n```gdscript\n SparseApplyFtrl(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input accum,\n ::tensorflow::Input linear,\n ::tensorflow::Input grad,\n ::tensorflow::Input indices,\n ::tensorflow::Input lr,\n ::tensorflow::Input l1,\n ::tensorflow::Input l2,\n ::tensorflow::Input lr_power,\n const SparseApplyFtrl::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```"]]
