tensorflow :: ops :: ResourceApplyFtrl

#include <training_ops.h>

Perbarui '* var' sesuai dengan skema Ftrl-proksimal.

Ringkasan

akum_new = akum + grad * grad linier + = grad - (acc_new ^ (- lr_power) - acc ^ (- lr_power)) / lr * var kuadrat = 1.0 / (akum_ ^ (lr_power) * lr) + 2 * l2 var = (tanda (linier) * l1 - linier) / kuadrat jika | linier | > l1 lain 0,0 akum = akum_new

Argumen:

• scope: Objek Scope
• var: Harus dari Variabel ().
• akumulasi: Harus dari Variabel ().
• linear: Harus dari Variabel ().
• grad: Gradien.
• lr: Faktor penskalaan. Harus skalar.
• l1: regularisasi L1. Harus skalar.
• l2: regularisasi L2. Harus skalar.
• lr_power: Faktor penskalaan. 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 perselisihan.

Pengembalian:

• Operation dibuat

Pembuat dan Penghancur
ResourceApplyFtrl (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input linear, :: tensorflow::Input grad, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input lr_power)
ResourceApplyFtrl (const :: tensorflow::Scope & scope, :: tensorflow::Input var, :: tensorflow::Input accum, :: tensorflow::Input linear, :: tensorflow::Input grad, :: tensorflow::Input lr, :: tensorflow::Input l1, :: tensorflow::Input l2, :: tensorflow::Input lr_power, const ResourceApplyFtrl::Attrs & attrs)

Atribut publik
operation	Operation

Fungsi publik
operator::tensorflow::Operation () const

Fungsi statis publik
UseLocking (bool x)	Attrs

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

Atribut publik

operasi

Operation operation

Fungsi publik

ResourceApplyFtrl

 ResourceApplyFtrl(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input accum,
  ::tensorflow::Input linear,
  ::tensorflow::Input grad,
  ::tensorflow::Input lr,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input lr_power
)

ResourceApplyFtrl

 ResourceApplyFtrl(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input accum,
  ::tensorflow::Input linear,
  ::tensorflow::Input grad,
  ::tensorflow::Input lr,
  ::tensorflow::Input l1,
  ::tensorflow::Input l2,
  ::tensorflow::Input lr_power,
  const ResourceApplyFtrl::Attrs & attrs
)

operator :: tensorflow :: Operasi

 operator::tensorflow::Operation() const 

Fungsi statis publik

UseLocking

Attrs UseLocking(
  bool x
)