avalanche.evaluation.metrics.EpochLoss

class avalanche.evaluation.metrics.EpochLoss[source]

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

The loss will be logged after each training epoch by computing the loss on the predicted patterns during the epoch divided by the overall number of patterns encountered in that epoch.

__init__()[source]

Creates an instance of the EpochLoss metric.

Methods

__init__()

Creates an instance of the EpochLoss 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)