avalanche.benchmarks.scenarios.OnlineCLExperience

class avalanche.benchmarks.scenarios.OnlineCLExperience(current_experience: int | None = None, origin_stream=None, origin_experience=None, subexp_size: int = 1, is_first_subexp: bool = False, is_last_subexp: bool = False, sub_stream_length: int | None = None, access_task_boundaries: bool = False)[source]

Online CL (OCL) Experience.

OCL experiences are created by splitting a larger experience. Therefore, they keep track of the original experience for logging purposes.

__init__(current_experience: int | None = None, origin_stream=None, origin_experience=None, subexp_size: int = 1, is_first_subexp: bool = False, is_last_subexp: bool = False, sub_stream_length: int | None = None, access_task_boundaries: bool = False)[source]

Init.

Parameters:
  • current_experience – experience identifier.

  • origin_stream – origin stream.

  • origin_experience – origin experience used to create self.

  • is_first_subexp – whether self is the first in the sub-experiences stream.

  • sub_stream_length – the sub-stream length.

Methods

__init__([current_experience, ...])

Init.

eval()

Return inference experience.

logging()

Return logging experience.

train()

Return training experience.

Attributes