aliran tensor:: operasi:: Terapkan Adadelta

#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:

• ruang lingkup: Objek Lingkup
• var: Harus dari Variabel().
• accum: Harus dari Variabel().
• accum_update: Harus dari Variabel().
• lr: Faktor penskalaan. Pasti skalar.
• rho : Faktor peluruhan. Pasti skalar.
• epsilon: Faktor konstan. Pasti skalar.
• lulusan: Gradien.

Atribut opsional (lihat Attrs ):

• use_locking: Jika Benar, pembaruan tensor var, accum, dan update_accum akan dilindungi oleh kunci; jika tidak, perilaku tersebut tidak terdefinisikan, namun mungkin menunjukkan lebih sedikit pertentangan.

Pengembalian:

• Output : Sama seperti "var".

Konstruktor dan Destruktor
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)

Atribut publik
operation	Operation
out	:: tensorflow::Output

Fungsi publik
node () const	::tensorflow::Node *
operator::tensorflow::Input () const
operator::tensorflow::Output () const

Fungsi statis publik
UseLocking (bool x)	Attrs

Struktur
tensorflow:: ops:: ApplyAdadelta:: Attrs	Penyetel atribut opsional untuk ApplyAdadelta .

Atribut publik

operasi

Operation operation

keluar

::tensorflow::Output out

Fungsi publik

Terapkan Adadelta

 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
)

Terapkan Adadelta

 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
)

simpul

::tensorflow::Node * node() const 

operator::tensorflow::Masukan

 operator::tensorflow::Input() const 

operator::tensorflow::Keluaran

 operator::tensorflow::Output() const 

Fungsi statis publik

Gunakan Penguncian

Attrs UseLocking(
  bool x
)