avalanche.training.plugins.ReplayPlugin
- class avalanche.training.plugins.ReplayPlugin(mem_size: int = 200, storage_policy: Optional[avalanche.training.storage_policy.ExemplarsBuffer] = None)[source]
Experience replay plugin.
Handles an external memory filled with randomly selected patterns and implementing before_training_exp and after_training_exp callbacks. The before_training_exp callback is implemented in order to use the dataloader that creates mini-batches with examples from both training data and external memory. The examples in the mini-batch is balanced such that there are the same number of examples for each experience.
The after_training_exp callback is implemented in order to add new patterns to the external memory.
The :mem_size: attribute controls the total number of patterns to be stored in the external memory.
- __init__(mem_size: int = 200, storage_policy: Optional[avalanche.training.storage_policy.ExemplarsBuffer] = None)[source]
- Parameters
storage_policy – The policy that controls how to add new exemplars in memory
Methods
__init__
([mem_size, storage_policy])- param storage_policy
The policy that controls how to add new exemplars
after_backward
(strategy, **kwargs)Called after criterion.backward() by the BaseStrategy.
after_eval
(strategy, **kwargs)Called after eval by the BaseStrategy.
after_eval_dataset_adaptation
(strategy, **kwargs)Called after eval_dataset_adaptation by the BaseStrategy.
after_eval_exp
(strategy, **kwargs)Called after eval_exp by the BaseStrategy.
after_eval_forward
(strategy, **kwargs)Called after model.forward() by the BaseStrategy.
after_eval_iteration
(strategy, **kwargs)Called after the end of an iteration by the BaseStrategy.
after_forward
(strategy, **kwargs)Called after model.forward() by the BaseStrategy.
after_train_dataset_adaptation
(strategy, ...)Called after train_dataset_adapatation by the BaseStrategy.
after_training
(strategy, **kwargs)Called after train by the BaseStrategy.
after_training_epoch
(strategy, **kwargs)Called after train_epoch by the BaseStrategy.
after_training_exp
(strategy, **kwargs)Called after train_exp by the BaseStrategy.
after_training_iteration
(strategy, **kwargs)Called after the end of a training iteration by the BaseStrategy.
after_update
(strategy, **kwargs)Called after optimizer.update() by the BaseStrategy.
before_backward
(strategy, **kwargs)Called before criterion.backward() by the BaseStrategy.
before_eval
(strategy, **kwargs)Called before eval by the BaseStrategy.
before_eval_dataset_adaptation
(strategy, ...)Called before eval_dataset_adaptation by the BaseStrategy.
before_eval_exp
(strategy, **kwargs)Called before eval_exp by the BaseStrategy.
before_eval_forward
(strategy, **kwargs)Called before model.forward() by the BaseStrategy.
before_eval_iteration
(strategy, **kwargs)Called before the start of a training iteration by the BaseStrategy.
before_forward
(strategy, **kwargs)Called before model.forward() by the BaseStrategy.
before_train_dataset_adaptation
(strategy, ...)Called before train_dataset_adapatation by the BaseStrategy.
before_training
(strategy, **kwargs)Called before train by the BaseStrategy.
before_training_epoch
(strategy, **kwargs)Called before train_epoch by the BaseStrategy.
before_training_exp
(strategy[, num_workers, ...])Dataloader to build batches containing examples from both memories and the training dataset
before_training_iteration
(strategy, **kwargs)Called before the start of a training iteration by the BaseStrategy.
before_update
(strategy, **kwargs)Called before optimizer.update() by the BaseStrategy.
Attributes
ext_mem