tensorflow :: ops :: Terapkan AdagradDA

#include <training_ops.h>

Perbarui '* var' sesuai dengan skema adagrad proksimal.

Ringkasan

Argumen:

• scope: Objek Scope
• var: Harus dari Variabel ().
• gradient_accumulator: Harus dari Variable ().
• gradient_squared_accumulator: Harus dari Variable ().
• grad: Gradien.
• lr: Faktor penskalaan. Harus skalar.
• l1: regularisasi L1. Harus skalar.
• l2: regularisasi L2. Harus skalar.
• global_step: Nomor langkah pelatihan. Harus skalar.

Atribut opsional (lihat Attrs ):

• use_locking: Jika True, pembaruan tensor var dan akumulator akan dilindungi oleh kunci; jika tidak, perilakunya tidak ditentukan, tetapi mungkin menunjukkan lebih sedikit pertentangan.

Pengembalian:

• Output : Sama seperti "var".

Pembangun dan Penghancur
ApplyAdagradDA (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input gradient_accumulator, :: tensorflow::Input gradient_squared_accumulator, :: tensorflow::Input grad, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input global_step)
ApplyAdagradDA (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input gradient_accumulator, :: tensorflow::Input gradient_squared_accumulator, :: tensorflow::Input grad, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input global_step, const ApplyAdagradDA::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

Structs
tensorflow :: ops :: ApplyAdagradDA :: Attrs	Penyetel atribut opsional untuk ApplyAdagradDA .

Atribut publik

operasi

Operation operation

di luar

::tensorflow::Output out

Fungsi publik

Terapkan AdagradDA

 ApplyAdagradDA(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input gradient_accumulator,
  ::tensorflow::Input gradient_squared_accumulator,
  ::tensorflow::Input grad,
  ::tensorflow::Input lr,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input global_step
)

TerapkanAdagradDA

 ApplyAdagradDA(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input gradient_accumulator,
  ::tensorflow::Input gradient_squared_accumulator,
  ::tensorflow::Input grad,
  ::tensorflow::Input lr,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input global_step,
  const ApplyAdagradDA::Attrs & attrs
)

simpul

::tensorflow::Node * node() const 

operator :: tensorflow :: Input

 operator::tensorflow::Input() const 

operator :: tensorflow :: Keluaran

 operator::tensorflow::Output() const 

Fungsi statis publik

UseLocking

Attrs UseLocking(
  bool x
)