tensorflow::ops::ResourceApplyAdadelta

#include <training_ops.h>

Perbarui '*var' sesuai dengan skema adadelta.

Ringkasan

accum = rho() * accum + (1 - rho()) * lulusan.persegi(); pembaruan = (update_accum + epsilon).sqrt() * (accum + epsilon()).rsqrt() * lulusan; update_accum = rho() * update_accum + (1 - rho()) * update.square(); var -= perbarui;

Argumen:

  • Cakupan: Objek Cakupan
  • var: Seharusnya berasal dari Variable().
  • accum: Seharusnya berasal dari Variable().
  • accum_update: Seharusnya berasal dari Variable().
  • lr: Faktor skala. Harus berupa besaran skalar.
  • rho: Faktor peluruhan. Harus berupa besaran skalar.
  • epsilon: Faktor konstanta. Harus berupa skalar.
  • grad: Gradien.

Atribut opsional (lihat Attrs ):

  • use_locking: Jika True, pembaruan tensor var, accum, dan update_accum akan dilindungi oleh kunci; jika tidak, perilakunya tidak terdefinisi, tetapi mungkin menunjukkan persaingan yang lebih sedikit.

Mengembalikan:

Konstruktor dan Destruktor

ResourceApplyAdadelta (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)
ResourceApplyAdadelta (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 ResourceApplyAdadelta::Attrs & attrs)

Atribut publik

operation

Fungsi publik

operator::tensorflow::Operation () const

Fungsi statis publik

UseLocking (bool x)

Struktur

tensorflow::ops::ResourceApplyAdadelta::Attrs

Pengaturan atribut opsional untuk ResourceApplyAdadelta .

Atribut publik

operasi 

Operation operation

Fungsi publik

Sumber DayaTerapkanAdadelta 

 ResourceApplyAdadelta(
  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
)

Sumber DayaTerapkanAdadelta 

 ResourceApplyAdadelta(
  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 ResourceApplyAdadelta::Attrs & attrs
)

operator::tensorflow::Operasi 

 operator::tensorflow::Operation() const

Fungsi statis publik

GunakanPenguncian 

Attrs UseLocking(
  bool x
)