org.platanios.tensorflow.api.ops.training.optimizers.schedules
Composes the provided other
schedule with this schedule and returns the resulting schedule.
Composes the provided other
schedule with this schedule and returns the resulting schedule.
Applies the scheduling method to value
, the current iteration in the optimization loop is step
and returns the
result.
Applies the scheduling method to value
, the current iteration in the optimization loop is step
and returns the
result.
Value to change based on this schedule.
Option containing current iteration in the optimization loop, if one has been provided.
Potentially modified value.
IllegalArgumentException
If the scheduling method requires a value for step
but the provided option is
empty.
Composes this schedule with the provided, other
schedule and returns the resulting schedule.
Composes this schedule with the provided, other
schedule and returns the resulting schedule.
Warm-up learning rate scaling factor.
Number of warm-up steps.
Learning rate schedule that implements a warm-up scheme, similar to the one proposed in [Attention is All You Need (Section 5.3)](https://arxiv.org/pdf/1706.03762.pdf).
For the first
warmUpSteps
steps the learning rate is multiplied by:exp(log(warmUpFactor) / step) ^ (warmUpSteps - step)
.