braindecode.training.CroppedTrialEpochScoring

class braindecode.training.CroppedTrialEpochScoring(scoring, lower_is_better=True, on_train=False, name=None, target_extractor=<function to_numpy>, use_caching=True)

Class to compute scores for trials from a model that predicts (super)crops.

Window indices identify overlapping windows belonging to the same trial. Without indices (for example, numpy input), each example is a separate trial: average its temporal predictions, never combine different examples.

Methods

on_batch_end(net, batch, y_pred, training, **kwargs)

Called at the end of each batch.

on_epoch_end(net, dataset_train, dataset_valid, **kwargs)

Called at the end of each epoch.