avalanche.training.ParametricBuffer

class avalanche.training.ParametricBuffer(max_size: int, groupby=None, selection_strategy: ExemplarsSelectionStrategy | None = None)

Stores samples for replay using a custom selection strategy and grouping.

__init__(max_size: int, groupby=None, selection_strategy: ExemplarsSelectionStrategy | None = None)

Init.

Parameters:

• max_size – The max capacity of the replay memory.

• groupby – Grouping mechanism. One of {None, ‘class’, ‘task’, ‘experience’}.

• selection_strategy – The strategy used to select exemplars to keep in memory when cutting it off.

Methods

__init__(max_size[, groupby, selection_strategy])	Init.
get_group_lengths(num_groups)	Compute groups lengths given the number of groups num_groups.
post_adapt(agent, exp)	Update self.buffer using the agent state and current experience.
resize(strategy, new_size)	Update the maximum size of the buffers.
update(strategy, **kwargs)	Update self.buffer using the strategy state.

Attributes

buffer	Buffer of samples.
buffer_datasets	Return group buffers as a list of `AvalancheDataset`s.
buffer_groups	Dictionary of buffers.
max_size	Maximum size of the buffer.