weight_decay: Weight_decay

View source: R/optimizers.R

weight_decayR Documentation

Weight_decay

Description

Weight decay as decaying 'p' with 'lr*wd'

Usage

weight_decay(p, lr, wd, do_wd = TRUE, ...)

Arguments

p

p

lr

learning rate

wd

weight decay

do_wd

do_wd

...

additional args to pass

Value

None

Examples


## Not run: 

tst_param = function(val, grad = NULL) {
  "Create a tensor with `val` and a gradient of `grad` for testing"
  res = tensor(val) %>% float()

  if(is.null(grad)) {
    grad = tensor(val / 10)
  } else {
    grad = tensor(grad)
  }

  res$grad = grad %>% float()
  res
}
p = tst_param(1., 0.1)
weight_decay(p, 1., 0.1)


## End(Not run)


fastai documentation built on March 21, 2022, 9:07 a.m.