Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
tensoreflusso:: ops:: ResourceApplyFtrlV2
#include <training_ops.h>
Aggiorna '*var' secondo lo schema Ftrl-prossimale.
Riepilogo
grad_with_shrinkage = grad + 2 * l2_shrinkage * var accum_new = accum + grad_with_shrinkage * grad_with_shrinkage lineare += grad_with_shrinkage + (accum_new^(-lr_power) - accum^(-lr_power)) / lr * varc = 1.0 / (accum_new^(lr_power) * lr) + 2 * l2 var = (segno(lineare) * l1 - lineare) / quadratico if |lineare| > l1 altrimenti 0.0 accum = accum_new
Argomenti:
- scope: un oggetto Scope
- var: dovrebbe provenire da una variabile().
- accum: dovrebbe provenire da una variabile().
- lineare: dovrebbe provenire da una variabile().
- grad: il gradiente.
- lr: fattore di scala. Deve essere uno scalare.
- l1: regolarizzazione L1. Deve essere uno scalare.
- l2: Regolarizzazione del ritiro L2. Deve essere uno scalare.
- lr_power: fattore di scala. Deve essere uno scalare.
Attributi facoltativi (vedi Attrs
):
- use_locking: Se
True
, l'aggiornamento dei tensori var e accum sarà protetto da un lock; altrimenti il comportamento non è definito, ma può mostrare meno contesa.
Resi:
Costruttori e distruttori |
---|
ResourceApplyFtrlV2 (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input linear, :: tensorflow::Input grad, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input l2_shrinkage, :: tensorflow::Input lr_power)
|
ResourceApplyFtrlV2 (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input linear, :: tensorflow::Input grad, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input l2_shrinkage, :: tensorflow::Input lr_power, const ResourceApplyFtrlV2::Attrs & attrs) |
Attributi pubblici
Funzioni pubbliche
ResourceApplyFtrlV2
ResourceApplyFtrlV2(
const ::tensorflow::Scope & scope,
::tensorflow::Input var,
::tensorflow::Input accum,
::tensorflow::Input linear,
::tensorflow::Input grad,
::tensorflow::Input lr,
::tensorflow::Input l1,
::tensorflow::Input l2,
::tensorflow::Input l2_shrinkage,
::tensorflow::Input lr_power,
const ResourceApplyFtrlV2::Attrs & attrs
)
operator::tensorflow::Operazione
operator::tensorflow::Operation() const
Funzioni pubbliche statiche
UsaLocking
Attrs UseLocking(
bool x
)
Salvo quando diversamente specificato, i contenuti di questa pagina sono concessi in base alla licenza Creative Commons Attribution 4.0, mentre gli esempi di codice sono concessi in base alla licenza Apache 2.0. Per ulteriori dettagli, consulta le norme del sito di Google Developers. Java è un marchio registrato di Oracle e/o delle sue consociate.
Ultimo aggiornamento 2025-07-26 UTC.
[null,null,["Ultimo aggiornamento 2025-07-26 UTC."],[],[],null,["# tensorflow::ops::ResourceApplyFtrlV2 Class Reference\n\ntensorflow::ops::ResourceApplyFtrlV2\n====================================\n\n`#include \u003ctraining_ops.h\u003e`\n\nUpdate '\\*var' according to the Ftrl-proximal scheme.\n\nSummary\n-------\n\ngrad_with_shrinkage = grad + 2 \\* l2_shrinkage \\* var accum_new = accum + grad_with_shrinkage \\* grad_with_shrinkage linear += grad_with_shrinkage + (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/r1.15/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- lr: Scaling factor. Must be a scalar.\n- l1: L1 regulariation. Must be a scalar.\n- l2: L2 shrinkage regulariation. Must be a scalar.\n- lr_power: Scaling factor. Must be a scalar.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-ftrl-v2/attrs#structtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_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- 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| [ResourceApplyFtrlV2](#classtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1af0cd2da7fd04b586801c7ff65201b3c6)`(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)` accum, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` linear, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[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)` l1, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2_shrinkage, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr_power)` ||\n| [ResourceApplyFtrlV2](#classtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1a2ddc33ae007578e3d302ff7cd7da72bf)`(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)` accum, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` linear, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[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)` l1, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` l2_shrinkage, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr_power, const `[ResourceApplyFtrlV2::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-ftrl-v2/attrs#structtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|----------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1a055d8d299e112489bb08106d147d44be) | [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_ftrl_v2_1a58cdd4377a81f3e98cc04b4cd0428827)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|---------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [UseLocking](#classtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1a52d5b1bbc4f4f6722afad9df9b5ec209)`(bool x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-ftrl-v2/attrs#structtensorflow_1_1ops_1_1_resource_apply_ftrl_v2_1_1_attrs) |\n\n| ### Structs ||\n|-------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::ResourceApplyFtrlV2::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/resource-apply-ftrl-v2/attrs) | Optional attribute setters for [ResourceApplyFtrlV2](/versions/r1.15/api_docs/cc/class/tensorflow/ops/resource-apply-ftrl-v2#classtensorflow_1_1ops_1_1_resource_apply_ftrl_v2). |\n\nPublic attributes\n-----------------\n\n### operation\n\n```text\nOperation operation\n``` \n\nPublic functions\n----------------\n\n### ResourceApplyFtrlV2\n\n```gdscript\n ResourceApplyFtrlV2(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input accum,\n ::tensorflow::Input linear,\n ::tensorflow::Input grad,\n ::tensorflow::Input lr,\n ::tensorflow::Input l1,\n ::tensorflow::Input l2,\n ::tensorflow::Input l2_shrinkage,\n ::tensorflow::Input lr_power\n)\n``` \n\n### ResourceApplyFtrlV2\n\n```gdscript\n ResourceApplyFtrlV2(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input accum,\n ::tensorflow::Input linear,\n ::tensorflow::Input grad,\n ::tensorflow::Input lr,\n ::tensorflow::Input l1,\n ::tensorflow::Input l2,\n ::tensorflow::Input l2_shrinkage,\n ::tensorflow::Input lr_power,\n const ResourceApplyFtrlV2::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```"]]