avalanche.evaluation.metrics.MinibatchClassAccuracy

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

The minibatch plugin class accuracy metric. This metric only works at training time.

This metric computes the average accuracy over patterns from a single minibatch. It reports the result after each iteration.

If a more coarse-grained logging is needed, consider using EpochClassAccuracy instead.

__init__(classes=None)[source]

Creates an instance of the MinibatchClassAccuracy metric.

Methods

__init__([classes])

Creates an instance of the MinibatchClassAccuracy 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()

Resets the metric internal state.

result()

Obtains the value of the metric.

update(strategy)