avalanche.training.ClosestToCenterSelectionStrategy
- class avalanche.training.ClosestToCenterSelectionStrategy(model: Module, layer_name: str)[source]
A greedy algorithm that selects the remaining exemplar that is the closest to the center of all elements (in feature space).
- __init__(model: Module, layer_name: str)
Methods
__init__(model, layer_name)make_sorted_indices(strategy, data)Should return the sorted list of indices to keep as exemplars.
make_sorted_indices_from_features(features)Should return the sorted list of indices to keep as exemplars.