avalanche.evaluation.metrics.RunningEpochClassAccuracy

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

The average class accuracy across all minibatches up to the current epoch iteration. This plugin metric only works at training time.

At each iteration, this metric logs the accuracy averaged over all patterns seen so far in the current epoch (separately for each class). The metric resets its state after each training epoch.

__init__(classes=None)[source]

Creates an instance of the RunningEpochClassAccuracy metric.

Methods

__init__([classes])

Creates an instance of the RunningEpochClassAccuracy 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)