avalanche.evaluation.metrics.MinibatchLoss

class avalanche.evaluation.metrics.MinibatchLoss[source]

The minibatch loss metric. This plugin metric only works at training time.

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

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

__init__()[source]

Creates an instance of the MinibatchLoss metric.

Methods

__init__()

Creates an instance of the MinibatchLoss 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()

Resets the metric internal state.

result()

Obtains the value of the metric.

update(strategy)