Aprenda o que há de mais recente em aprendizado de máquina, IA generativa e muito mais no WiML Symposium 2023
Registre-se
Mantenha tudo organizado com as coleções
Salve e categorize o conteúdo com base nas suas preferências.
tensorflow :: ops :: ApplyAdadelta
#include <training_ops.h>
Atualize '* var' de acordo com o esquema adadelta.
Resumo
acum = rho () * acum + (1 - rho ()) * grad.square (); update = (update_accum + epsilon) .sqrt () * (acum + epsilon ()). rsqrt () * grad; update_accum = rho () * update_accum + (1 - rho ()) * update.square (); var - = atualização;
Argumentos:
- escopo: um objeto Scope
- var: deve ser de uma variável ().
- acum: deve ser de uma variável ().
- acumular_atualização: deve ser de uma variável ().
- lr: Fator de escala. Deve ser um escalar.
- rho: Fator de decaimento. Deve ser um escalar.
- epsilon: Fator constante. Deve ser um escalar.
- grad: O gradiente.
Atributos opcionais (consulte Attrs
):
- use_locking: Se True, a atualização dos tensores var, Accum e update_accum será protegida por uma trava; caso contrário, o comportamento é indefinido, mas pode exibir menos contenção.
Retorna:
Construtores e Destruidores |
---|
ApplyAdadelta (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input accum_update, :: tensorflow::Input lr, :: tensorflow::Input rho, :: tensorflow::Input epsilon, :: tensorflow::Input grad)
|
ApplyAdadelta (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input accum_update, :: tensorflow::Input lr, :: tensorflow::Input rho, :: tensorflow::Input epsilon, :: tensorflow::Input grad, const ApplyAdadelta::Attrs & attrs) |
Atributos públicos
Funções públicas
nó
::tensorflow::Node * node() const
operator::tensorflow::Input() const
operador :: tensorflow :: Saída
operator::tensorflow::Output() const
Funções estáticas públicas
UseLocking
Attrs UseLocking(
bool x
)
Exceto em caso de indicação contrária, o conteúdo desta página é licenciado de acordo com a Licença de atribuição 4.0 do Creative Commons, e as amostras de código são licenciadas de acordo com a Licença Apache 2.0. Para mais detalhes, consulte as políticas do site do Google Developers. Java é uma marca registrada da Oracle e/ou afiliadas.
Última atualização 2020-04-20 UTC.
[null,null,["Última atualização 2020-04-20 UTC."],[],[],null,["# tensorflow::ops::ApplyAdadelta Class Reference\n\ntensorflow::ops::ApplyAdadelta\n==============================\n\n`#include \u003ctraining_ops.h\u003e`\n\nUpdate '\\*var' according to the adadelta scheme.\n\nSummary\n-------\n\naccum = rho() \\* accum + (1 - rho()) \\* grad.square(); update = (update_accum + epsilon).sqrt() \\* (accum + epsilon()).rsqrt() \\* grad; update_accum = rho() \\* update_accum + (1 - rho()) \\* update.square(); var -= update;\n\nArguments:\n\n- scope: A [Scope](/versions/r2.1/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- accum_update: Should be from a Variable().\n- lr: Scaling factor. Must be a scalar.\n- rho: Decay factor. Must be a scalar.\n- epsilon: Constant factor. Must be a scalar.\n- grad: The gradient.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r2.1/api_docs/cc/struct/tensorflow/ops/apply-adadelta/attrs#structtensorflow_1_1ops_1_1_apply_adadelta_1_1_attrs)):\n\n- use_locking: If True, updating of the var, accum and update_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/r2.1/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): Same as \"var\".\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [ApplyAdadelta](#classtensorflow_1_1ops_1_1_apply_adadelta_1aa28344b035c47c459fd0afca95547d97)`(const ::`[tensorflow::Scope](/versions/r2.1/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` var, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum_update, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` rho, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` epsilon, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad)` ||\n| [ApplyAdadelta](#classtensorflow_1_1ops_1_1_apply_adadelta_1a08f5d27287a3064abb5e3b83fadbe887)`(const ::`[tensorflow::Scope](/versions/r2.1/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` var, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` accum_update, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` lr, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` rho, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` epsilon, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, const `[ApplyAdadelta::Attrs](/versions/r2.1/api_docs/cc/struct/tensorflow/ops/apply-adadelta/attrs#structtensorflow_1_1ops_1_1_apply_adadelta_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|--------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_apply_adadelta_1a4bcd49cd72b4103e0041a1231ad7cbfb) | [Operation](/versions/r2.1/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [out](#classtensorflow_1_1ops_1_1_apply_adadelta_1aaa46dd79340e6999dac483165b45499d) | `::`[tensorflow::Output](/versions/r2.1/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|--------------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_apply_adadelta_1a7ab3d73516eacd84efdba9d4c8bb31dd)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_apply_adadelta_1aa0992e4c234bd33403c057425829457c)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_apply_adadelta_1a0d01185e91e72c289949de8ca852c923)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|-------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|\n| [UseLocking](#classtensorflow_1_1ops_1_1_apply_adadelta_1a8545cc26c688935679d0a732a1407986)`(bool x)` | [Attrs](/versions/r2.1/api_docs/cc/struct/tensorflow/ops/apply-adadelta/attrs#structtensorflow_1_1ops_1_1_apply_adadelta_1_1_attrs) |\n\n| ### Structs ||\n|----------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::ApplyAdadelta::Attrs](/versions/r2.1/api_docs/cc/struct/tensorflow/ops/apply-adadelta/attrs) | Optional attribute setters for [ApplyAdadelta](/versions/r2.1/api_docs/cc/class/tensorflow/ops/apply-adadelta#classtensorflow_1_1ops_1_1_apply_adadelta). |\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### ApplyAdadelta\n\n```gdscript\n ApplyAdadelta(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input accum,\n ::tensorflow::Input accum_update,\n ::tensorflow::Input lr,\n ::tensorflow::Input rho,\n ::tensorflow::Input epsilon,\n ::tensorflow::Input grad\n)\n``` \n\n### ApplyAdadelta\n\n```gdscript\n ApplyAdadelta(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input var,\n ::tensorflow::Input accum,\n ::tensorflow::Input accum_update,\n ::tensorflow::Input lr,\n ::tensorflow::Input rho,\n ::tensorflow::Input epsilon,\n ::tensorflow::Input grad,\n const ApplyAdadelta::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```"]]