avalanche.training.ParametricBuffer
- class avalanche.training.ParametricBuffer(max_size: int, groupby=None, selection_strategy: Optional[avalanche.training.storage_policy.ExemplarsSelectionStrategy] = None)[source]
Stores samples for replay using a custom selection strategy and grouping.
- __init__(max_size: int, groupby=None, selection_strategy: Optional[avalanche.training.storage_policy.ExemplarsSelectionStrategy] = None)[source]
- Parameters
max_size – The max capacity of the replay memory.
groupby – Grouping mechanism. One of {None, ‘class’, ‘task’,
‘experience’}. :param selection_strategy: The strategy used to select exemplars to
keep in memory when cutting it off.
Methods
__init__
(max_size[, groupby, selection_strategy])- param max_size
The max capacity of the replay memory.
get_group_lengths
(num_groups)Compute groups lengths given the number of groups num_groups.
resize
(strategy, new_size)Update the maximum size of the buffers.
update
(strategy, **kwargs)Update self.buffer_groups using the strategy state.
Attributes
buffer
Buffer of samples.
buffer_datasets
Return group buffers as a list of `AvalancheDataset`s. .