tensorflow :: ops :: ApplyProximalGradientDescent

#include <training_ops.h>

Perbarui '* var' sebagai algoritme FOBOS dengan kecepatan pemelajaran tetap.

Ringkasan

prox_v = var - alpha * delta var = tanda (prox_v) / (1 + alpha * l2) * max {| prox_v | -alpha * l1,0}

Argumen:

• scope: Objek Scope
• var: Harus dari Variabel ().
• alpha: Faktor penskalaan. Harus skalar.
• l1: regularisasi L1. Harus skalar.
• l2: regularisasi L2. Harus skalar.
• delta: Perubahan.

Atribut opsional (lihat Attrs ):

• use_locking: Jika True, pengurangan akan dilindungi oleh kunci; jika tidak, perilakunya tidak ditentukan, tetapi mungkin menunjukkan lebih sedikit perselisihan.

Pengembalian:

• Output : Sama seperti "var".

Pembuat dan Penghancur
ApplyProximalGradientDescent (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input alpha, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input delta)
ApplyProximalGradientDescent (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input alpha, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input delta, const ApplyProximalGradientDescent::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 :: ApplyProximalGradientDescent :: Attrs	Penyetel atribut opsional untuk ApplyProximalGradientDescent .

Atribut publik

operasi

Operation operation

di luar

::tensorflow::Output out

Fungsi publik

ApplyProximalGradientDescent

 ApplyProximalGradientDescent(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input alpha,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input delta
)

ApplyProximalGradientDescent

 ApplyProximalGradientDescent(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input alpha,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input delta,
  const ApplyProximalGradientDescent::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
)