tfaddons (version 0.10.0)

optimizer_yogi: Yogi

Description

Yogi

Usage

optimizer_yogi(
  learning_rate = 0.01,
  beta1 = 0.9,
  beta2 = 0.999,
  epsilon = 0.001,
  l1_regularization_strength = 0,
  l2_regularization_strength = 0,
  initial_accumulator_value = 1e-06,
  activation = "sign",
  name = "Yogi",
  clipnorm = NULL,
  clipvalue = NULL,
  decay = NULL,
  lr = NULL
)

Arguments

learning_rate

A Tensor or a floating point value. The learning rate.

beta1

A float value or a constant float tensor. The exponential decay rate for the 1st moment estimates.

beta2

A float value or a constant float tensor. The exponential decay rate for the 2nd moment estimates.

epsilon

A constant trading off adaptivity and noise.

l1_regularization_strength

A float value, must be greater than or equal to zero.

l2_regularization_strength

A float value, must be greater than or equal to zero.

initial_accumulator_value

The starting value for accumulators. Only positive values are allowed.

activation

Use hard sign or soft tanh to determin sign.

name

Optional name for the operations created when applying gradients. Defaults to "Yogi".

clipnorm

is clip gradients by norm.

clipvalue

is clip gradients by value.

decay

is included for backward compatibility to allow time inverse decay of learning rate.

lr

is included for backward compatibility, recommended to use learning_rate instead.

Value

Optimizer for use with `keras::compile()`