Table Of Contents
Table Of Contents

FactorScheduler

class mxnet.lr_scheduler.FactorScheduler(step, factor=1, stop_factor_lr=1e-08)[source]

Reduce the learning rate by a factor for every n steps.

It returns a new learning rate by:

base_lr * pow(factor, floor(num_update/step))
Parameters:
  • step (int) – Changes the learning rate for every n updates.
  • factor (float, optional) – The factor to change the learning rate.
  • stop_factor_lr (float, optional) – Stop updating the learning rate if it is less than this value.
__init__(step, factor=1, stop_factor_lr=1e-08)[source]

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__(step[, factor, stop_factor_lr]) Initialize self.