chainer.training.extensions.ExponentialShift

class chainer.training.extensions.ExponentialShift(attr, rate, init=None, target=None, optimizer=None)[source]

Trainer extension to exponentially shift an optimizer attribute.

This extension exponentially increases or decreases the specified attribute of the optimizer. The typical use case is an exponential decay of the learning rate.

This extension is also called before the training loop starts by default.

Parameters:
  • attr (str) – Name of the attribute to shift.
  • rate (float) – Rate of the exponential shift. This value is multiplied to the attribute at each call.
  • init (float) – Initial value of the attribute. If it is None, the extension extracts the attribute at the first call and uses it as the initial value.
  • target (float) – Target value of the attribute. If the attribute reaches this value, the shift stops.
  • optimizer (Optimizer) – Target optimizer to adjust the attribute. If it is None, the main optimizer of the updater is used.

Methods

__call__(trainer)[source]
finalize()[source]

Finalizes the extension.

This method is called at the end of the training loop.

initialize(trainer)[source]
serialize(serializer)[source]

Attributes

default_name

Default name of the extension.

It is the name of the class by default. Implementation can override this property, or provide a class attribute to hide it.

priority = 100
trigger = (1, 'iteration')