avalanche.evaluation.metrics.TrainedExperienceTopkAccuracy

class avalanche.evaluation.metrics.TrainedExperienceTopkAccuracy(top_k)[source]

At the end of each experience, this plugin metric reports the average top-k accuracy for only the experiences that the model has been trained on so far.

This metric only works at eval time.

__init__(top_k)[source]

Creates an instance of the TrainedExperienceTopkAccuracy metric.

Methods

__init__(top_k)

Creates an instance of the TrainedExperienceTopkAccuracy 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)

Only update the top-k accuracy with results from experiences that have been trained on