avalanche.evaluation.metrics.CumulativeForgettingPluginMetric
- class avalanche.evaluation.metrics.CumulativeForgettingPluginMetric(reset_at='stream', emit_at='stream', mode='eval')[source]
The CumulativeForgetting metric, describing the accuracy loss detected for a certain experience.
This plugin metric, computed separately for each experience, is the difference between the cumulative accuracy result obtained after first training on a experience and the accuracy result obtained on the same experience at the end of successive experiences.
This metric is computed during the eval phase only.
- __init__(reset_at='stream', emit_at='stream', mode='eval')[source]
Creates an instance of the CumulativeForgetting metric.
Methods
__init__
([reset_at, emit_at, mode])Creates an instance of the CumulativeForgetting metric.
after_backward
(strategy)after_eval
(strategy)after_eval_dataset_adaptation
(strategy)after_eval_exp
(strategy)after_eval_forward
(strategy)after_eval_iteration
(strategy)after_forward
(strategy)after_train_dataset_adaptation
(strategy)after_training
(strategy)after_training_epoch
(strategy)after_training_exp
(strategy)after_training_iteration
(strategy)after_update
(strategy)before_backward
(strategy)before_eval
(strategy)before_eval_dataset_adaptation
(strategy)before_eval_exp
(strategy)before_eval_forward
(strategy)before_eval_iteration
(strategy)before_forward
(strategy)before_train_dataset_adaptation
(strategy)before_training
(strategy)before_training_epoch
(strategy)before_training_exp
(strategy, **kwargs)before_training_iteration
(strategy)before_update
(strategy)reset
()Resets the metric internal state.
result
()Obtains the value of the metric.
update
(strategy)