avalanche.training.plugins.LwFPlugin

class avalanche.training.plugins.LwFPlugin(alpha=1, temperature=2)[source]

A Learning without Forgetting plugin. LwF uses distillation to regularize the current loss with soft targets taken from a previous version of the model. This plugin does not use task identities. When used with multi-headed models, all heads are distilled.

__init__(alpha=1, temperature=2)[source]
Parameters
  • alpha – distillation hyperparameter. It can be either a float number or a list containing alpha for each experience.

  • temperature – softmax temperature for distillation

Methods

__init__([alpha, temperature])

param alpha

distillation hyperparameter. It can be either a float

after_backward(strategy, *args, **kwargs)

Called after criterion.backward() by the BaseTemplate.

after_eval(strategy, *args, **kwargs)

Called after eval by the BaseTemplate.

after_eval_dataset_adaptation(strategy, ...)

Called after eval_dataset_adaptation by the BaseTemplate.

after_eval_exp(strategy, *args, **kwargs)

Called after eval_exp by the BaseTemplate.

after_eval_forward(strategy, *args, **kwargs)

Called after model.forward() by the BaseTemplate.

after_eval_iteration(strategy, *args, **kwargs)

Called after the end of an iteration by the BaseTemplate.

after_forward(strategy, *args, **kwargs)

Called after model.forward() by the BaseTemplate.

after_train_dataset_adaptation(strategy, ...)

Called after train_dataset_adapatation by the BaseTemplate.

after_training(strategy, *args, **kwargs)

Called after train by the BaseTemplate.

after_training_epoch(strategy, *args, **kwargs)

Called after train_epoch by the BaseTemplate.

after_training_exp(strategy, **kwargs)

Save a copy of the model after each experience and update self.prev_classes to include the newly learned classes.

after_training_iteration(strategy, *args, ...)

Called after the end of a training iteration by the BaseTemplate.

after_update(strategy, *args, **kwargs)

Called after optimizer.update() by the BaseTemplate.

before_backward(strategy, **kwargs)

Add distillation loss

before_eval(strategy, *args, **kwargs)

Called before eval by the BaseTemplate.

before_eval_dataset_adaptation(strategy, ...)

Called before eval_dataset_adaptation by the BaseTemplate.

before_eval_exp(strategy, *args, **kwargs)

Called before eval_exp by the BaseTemplate.

before_eval_forward(strategy, *args, **kwargs)

Called before model.forward() by the BaseTemplate.

before_eval_iteration(strategy, *args, **kwargs)

Called before the start of a training iteration by the BaseTemplate.

before_forward(strategy, *args, **kwargs)

Called before model.forward() by the BaseTemplate.

before_train_dataset_adaptation(strategy, ...)

Called before train_dataset_adapatation by the BaseTemplate.

before_training(strategy, *args, **kwargs)

Called before train by the BaseTemplate.

before_training_epoch(strategy, *args, **kwargs)

Called before train_epoch by the BaseTemplate.

before_training_exp(strategy, *args, **kwargs)

Called before train_exp by the BaseTemplate.

before_training_iteration(strategy, *args, ...)

Called before the start of a training iteration by the BaseTemplate.

before_update(strategy, *args, **kwargs)

Called before optimizer.update() by the BaseTemplate.

penalty(out, x, alpha, curr_model)

Compute weighted distillation loss.

Attributes

prev_classes

In Avalanche, targets of different experiences are not ordered.