View source: R/learning_rate_schedules.R
learning_rate_schedule_exponential_decay | R Documentation |
A LearningRateSchedule that uses an exponential decay schedule
learning_rate_schedule_exponential_decay(
initial_learning_rate,
decay_steps,
decay_rate,
staircase = FALSE,
...,
name = NULL
)
initial_learning_rate |
A scalar |
decay_steps |
A scalar |
decay_rate |
A scalar |
staircase |
Boolean. If |
... |
For backwards and forwards compatibility |
name |
String. Optional name of the operation. Defaults to 'ExponentialDecay'. |
When training a model, it is often useful to lower the learning rate as the training progresses. This schedule applies an exponential decay function to an optimizer step, given a provided initial learning rate.
The schedule is a 1-arg callable that produces a decayed learning rate when passed the current optimizer step. This can be useful for changing the learning rate value across different invocations of optimizer functions. It is computed as:
decayed_learning_rate <- function(step) initial_learning_rate * decay_rate ^ (step / decay_steps)
If the argument staircase
is TRUE
, then step / decay_steps
is
an integer division (%/%
) and the decayed learning rate follows a
staircase function.
You can pass this schedule directly into a optimizer as the learning rate (see example) Example: When fitting a Keras model, decay every 100000 steps with a base of 0.96:
initial_learning_rate <- 0.1 lr_schedule <- learning_rate_schedule_exponential_decay( initial_learning_rate, decay_steps = 100000, decay_rate = 0.96, staircase = TRUE) model %>% compile( optimizer= optimizer_sgd(learning_rate = lr_schedule), loss = 'sparse_categorical_crossentropy', metrics = 'accuracy') model %>% fit(data, labels, epochs = 5)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.