Avalanche: an End-to-End Library for Continual Learning based on PyTorch.
avalanche.benchmarks.scenarios.deprecated
as a result of the change. #1511support for python 3.11
ER-AML #1472
PackNet #1496
NewClassesCrossEntropy criterion and automatic criterion plugin #1514
CIL Examplar Free components #1528
Feature replay and feature distillation (CIL Exfree) #1535
Continuous Task-Agnostic Scenario #1336
FFCV support for faster dataloading #1439
Full Changelog: https://github.com/ContinualAI/avalanche/compare/v0.4.0...v0.5.0
FromScratchTrainingPlugin
by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1288
higher
dependency by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1326
Full Changelog: https://github.com/ContinualAI/avalanche/compare/v0.3.1...v0.4.0
Fixed minor problem during pip installation
Improved performance for several benchmarks:
training.strategies
fixed in docstring and gitbook by @alexsosn in https://github.com/ContinualAI/avalanche/pull/1072
JointStrategy
and update strategy tests by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1112
class_ids_from_zero_in_each_exp
to classic benchmarks by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1140
Kinetics
dataset wrapper by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1228
Full Changelog: https://github.com/ContinualAI/avalanche/compare/v0.2.0...v0.3.0
Fixed a critical bug in EWC.
We are excited to release the new version of Avalanche (0.2.0). This release brings many new features, including new strategies, benchmarks, and an overall improved support for several settings such as online CL, object detection, reinforcement learning.
We are also focusing on ensuring that Avalanche baselines are correct and reproducible. You can test our repoducible experiments at the continual-learning-baselines repository.
ReduceLROnPlateau
plugin. #859num_workers=0
in all tests by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/911
base_sgd
template by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/915
OnlineSupervisedTemplate
by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1024
Full Changelog: https://github.com/ContinualAI/avalanche/compare/v0.1.0...v0.2.0
Beta release
Avalanche is a framework in constant development and supported by 15+ organizations. Thanks to the support of the ContinualAI community and its active members we plan to extend its features and improve its usability based on the demands of our research community!
A the moment, Avalanche is in Alpha (v0.0.1), but we already support a number of Benchmarks, Strategies and Metrics, that makes it, we believe, the best tool out there for your continual learning research! 💪
Check out what we support for this release in details, and please let us know if you think we are missing out something important! We deeply value your feedback!