avalanche.evaluation.metrics.AccuracyPerTaskPluginMetric

class avalanche.evaluation.metrics.AccuracyPerTaskPluginMetric(reset_at, emit_at, mode)[source]

Base class for all accuracies plugin metrics

__init__(reset_at, emit_at, mode)[source]

Creates the Accuracy plugin

Parameters:

  • reset_at –

  • emit_at –

  • mode –

  • split_by_task – whether to compute task-aware accuracy or not.

Methods

__init__(reset_at, emit_at, mode)

Creates the Accuracy plugin

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()

Resets the metric internal state.

result()

Obtains the value of the metric.

update(strategy)