avalanche.evaluation.metrics.EpochClassAccuracy

class avalanche.evaluation.metrics.EpochClassAccuracy(classes=None)[source]

The average class accuracy over a single training epoch. This plugin metric only works at training time.

The accuracy will be logged after each training epoch by computing the number of correctly predicted patterns during the epoch divided by the overall number of patterns encountered in that epoch (separately for each class).

__init__(classes=None)[source]

Creates an instance of the EpochClassAccuracy metric.

Methods

__init__([classes])

Creates an instance of the EpochClassAccuracy 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)

metric_value_name(m_value)

reset(strategy)

Resets the metric internal state.

result(strategy)

Obtains the value of the metric.

update(strategy)