aliran tensor:: operasi:: JarangTerapkanAdagradDA

#include <training_ops.h>

Perbarui entri di '*var' dan '*accum' sesuai dengan skema adagrad proksimal.

Ringkasan

Argumen:

  • ruang lingkup: Objek Lingkup
  • var: Harus dari Variabel().
  • gradien_akumulator: Harus dari Variabel().
  • gradien_squared_accumulator: Harus dari Variabel().
  • lulusan: Gradien.
  • indeks: Vektor indeks ke dalam dimensi pertama var dan accum.
  • lr: Kecepatan pembelajaran. Pasti skalar.
  • l1: Regularisasi L1. Pasti skalar.
  • l2: Regularisasi L2. Pasti skalar.
  • global_step: Nomor langkah pelatihan. Pasti skalar.

Atribut opsional (lihat Attrs ):

  • use_locking: Jika Benar, pembaruan tensor var dan 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

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

Atribut publik

operation
out

Fungsi publik

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

Fungsi statis publik

UseLocking (bool x)

Struktur

tensorflow:: ops:: SparseApplyAdagradDA:: Attrs

Penyetel atribut opsional untuk SparseApplyAdagradDA .

Atribut publik

operasi 

Operation operation

keluar 

::tensorflow::Output out

Fungsi publik

JarangTerapkanAdagradDA 

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

JarangTerapkanAdagradDA 

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