avalanche.evaluation.metrics.MinibatchMAC
- class avalanche.evaluation.metrics.MinibatchMAC[source]
The minibatch MAC metric. This plugin metric only works at training time.
This metric computes the MAC over 1 pattern from a single minibatch. It reports the result after each iteration.
If a more coarse-grained logging is needed, consider using
EpochMAC
instead.Methods
__init__
()Creates an instance of the MinibatchMAC 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)before_training_iteration
(strategy)before_update
(strategy)reset
(strategy)Resets the metric internal state.
result
(strategy)Obtains the value of the metric.
update
(strategy)