Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of avalanche-lib

avalanche-lib - v0.6.0

What's Changed

  • Started development version for 0.5.0a by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1607
  • Changes in Dynamic Modules by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1600
  • Add support for multiple param groups by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1609
  • Updatable objects by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1633
  • PNN adapter arguement missing in the init() method #1625 by @Chillthrower in https://github.com/ContinualAI/avalanche/pull/1637
  • task_labels experience attribute type fix: now it is a list, not a set by @vlomonaco in https://github.com/ContinualAI/avalanche/pull/1646
  • Improved Efficiency of the DiskUsage Metric by @vlomonaco in https://github.com/ContinualAI/avalanche/pull/1647
  • Generative Replay with weighted loss for replayed data by @gogamid in https://github.com/ContinualAI/avalanche/pull/1596
  • support benchmark without task labels in avalanche.strategies by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1652

New Contributors

  • @Chillthrower made their first contribution in https://github.com/ContinualAI/avalanche/pull/1637

Full Changelog: https://github.com/ContinualAI/avalanche/compare/v0.5.0...v0.6.0

- Python
Published by AntonioCarta over 1 year ago

avalanche-lib - v0.5.0

Breaking Changes

  • removed support for python 3.7 #1521
  • A simplified benchmarks API. Some of the old benchmark constructors are now under avalanche.benchmarks.scenarios.deprecated as a result of the change. #1511

New Features

  • support 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

What's Changed

  • Updated avalanche main version to latest by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1484
  • Earlystopping patch by @scumatteo in https://github.com/ContinualAI/avalanche/pull/1487
  • er-aml implementation by @GeremiaPompei in https://github.com/ContinualAI/avalanche/pull/1472
  • FFCV support by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1439
  • slightly faster and easier doc build by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1488
  • Update clear_data.py by @linzhiqiu in https://github.com/ContinualAI/avalanche/pull/1499
  • Implement PackNet by @tachyonicClock in https://github.com/ContinualAI/avalanche/pull/1496
  • Some minor fixes in batch_observation and utils by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1513
  • Ffcv improvements by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1516
  • WIP: New benchmarks API by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1511
  • remove py 3.7 from CI by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1521
  • Update FZTH tutorials by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1522
  • Update gitbook assets by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1523
  • Added NewClassesCrossEntropy criterion and automatic criterion plugin by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1514
  • proper conversion of Tensor to list by @malashinroman in https://github.com/ContinualAI/avalanche/pull/1524
  • Continuous Task-Agnostic Scenario by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1336
  • Update Documentation by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1527
  • CIL Examplar Free components by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1528
  • Update clear_data.py by @viajeraune in https://github.com/ContinualAI/avalanche/pull/1545
  • fix dataloadingbuffersreplay.ipynb notebook by @gogamid in https://github.com/ContinualAI/avalanche/pull/1555
  • update python version requirements by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1559
  • Update 3 11 by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1562
  • Major BiC fix/reimplementation by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1550
  • install all dependencies with pip by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1568
  • Improve support for PyTorch 2.* and Python>=3.8 by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1571
  • Improvements of the checkpoint functionality and memory occupation of DER by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1567
  • Feature replay and feature distillation (CIL Exfree) by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1535
  • WIP: Remove conda files by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1561
  • Fix install issue of quadprog when using Python 3.11 by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1574
  • Fix quadrprog dependency in CI by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1575
  • FZTH Notebooks for the New Release by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1589
  • Fix multiple inheritance in Python 3.11 by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1587

New Contributors

  • @GeremiaPompei made their first contribution in https://github.com/ContinualAI/avalanche/pull/1472
  • @malashinroman made their first contribution in https://github.com/ContinualAI/avalanche/pull/1524
  • @viajeraune made their first contribution in https://github.com/ContinualAI/avalanche/pull/1545
  • @gogamid made their first contribution in https://github.com/ContinualAI/avalanche/pull/1555

Full Changelog: https://github.com/ContinualAI/avalanche/compare/v0.4.0...v0.5.0

- Python
Published by AntonioCarta over 2 years ago

avalanche-lib - v0.4.0

New Features

Strategies

  • L2P #1302
  • DER #1314
  • Add Expert Gate #1048
  • Supervised Contrastive Replay #1356
  • RAR #1424

Metrics

  • Matrix acc by #1376
  • Cumulative accuracies #1339

Performance Improvements

  • long benchmarks are now faster #1464 #1416 #1414 #1383

What's Changed

  • Fixed cope plugin by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1285
  • Add FromScratchTrainingPlugin by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1288
  • Fixed TensorImage being treated as an unsupported logging type by @BenCrulis in https://github.com/ContinualAI/avalanche/pull/1293
  • Update benchmarks.md by @eltociear in https://github.com/ContinualAI/avalanche/pull/1294
  • replay fix proposition by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1287
  • Update OnlineObservation and Template Docstrings by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1297
  • ER-ACE criterion simplification by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1313
  • L2p by @JuliousHurtado in https://github.com/ContinualAI/avalanche/pull/1302
  • replace lambda functions with pickle compatible equivalent. by @DanielAnthes in https://github.com/ContinualAI/avalanche/pull/1311
  • Allow setting prefetch_factor for multiprocessing by @DanielAnthes in https://github.com/ContinualAI/avalanche/pull/1320
  • Removed cope warning after bug fix by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1321
  • Storage patch by @scumatteo in https://github.com/ContinualAI/avalanche/pull/1334
  • Added DER strategy by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1314
  • Remove higher dependency by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1326
  • fixed mir unused subsample argument by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1341
  • Faster checkpointing and simpler API by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1338
  • greatly speeed up logging by disabling flushing by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1344
  • Refactor CLEAR Benchmark based on the official webpage by @jd730 in https://github.com/ContinualAI/avalanche/pull/1345
  • Fix for Issue #1353 by @HeLehm in https://github.com/ContinualAI/avalanche/pull/1354
  • New Question Answering example. New wrapper for Huggingface Datasets by @MickHardins in https://github.com/ContinualAI/avalanche/pull/1350
  • Update .gitignore by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1358
  • Typing system overhaul. Improve support for object detection scenarios. by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1333
  • Forward classidfromzeroineachexp to nc_benchmark in classical benchmarks by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1367
  • Cumulative accuracies by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1339
  • Fix issue #1371 by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1372
  • Fix issue #1232. Added unit tests. by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1375
  • Add base elements to support distributed comms. Add supports_distributed plugin flag. by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1370
  • Speed up nc_scenario for larger datasets by @niniack in https://github.com/ContinualAI/avalanche/pull/1381
  • Sample Order in OnlineCLScenario by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1385
  • remove OnlineSupervisedTemplate by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1362
  • Add Expert Gate to Avalanche by @niniack in https://github.com/ContinualAI/avalanche/pull/1048
  • Matrix acc by @JuliousHurtado in https://github.com/ContinualAI/avalanche/pull/1376
  • Add a variable to control whether to retain the graph or not in the backward pass by @BenCrulis in https://github.com/ContinualAI/avalanche/pull/1388
  • Faster attributes by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1383
  • FIX: Make optimizer now changes optimizedparamid in place by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1394
  • BugFix OnlineTemplate missing model adaptation call by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1396
  • Supervised Contrastive Replay implementation. by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1356
  • NCM Classifier uses dictionary and can update means by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1405
  • Shuffling dataset when updating GEM memory by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1407
  • removed droplast forwarding from makeeval_dataloader by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1408
  • Minor Fix for EWC by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1409
  • Replay flattening by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1414
  • faster indices for FlatData with lazy operations by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1416
  • change to cumulative accuracy by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1419
  • Added NCM replace dictionary and used in icarl by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1427
  • small refactor and cumulative accuracy fix by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1426
  • Fixed icarl by converting back TrainEvalModel to DynamicModule by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1428
  • Streamline data loaders by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1429
  • Fixed issues with 0 length samplers by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1437
  • switch to black formatting by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1398
  • Rar merge by @JuliousHurtado in https://github.com/ContinualAI/avalanche/pull/1424
  • add a momentum parameter for the class mean update by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1438
  • Fix integration with IncrementalClassifier by @JuliousHurtado in https://github.com/ContinualAI/avalanche/pull/1447
  • Fix MER by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1446
  • turn ncm to dynamic module that adapts with 0 vectors at evaluation by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1458
  • Various fixes and improvements by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1463
  • Speedup for long benchmarks iteration by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1464
  • Fix setup.py and environment files by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1471
  • Release fixes by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1473
  • Extend unit tests to confirm resolution of #1104 by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1475

New Contributors

  • @eltociear made their first contribution in https://github.com/ContinualAI/avalanche/pull/1294
  • @DanielAnthes made their first contribution in https://github.com/ContinualAI/avalanche/pull/1311
  • @scumatteo made their first contribution in https://github.com/ContinualAI/avalanche/pull/1334
  • @jd730 made their first contribution in https://github.com/ContinualAI/avalanche/pull/1345
  • @HeLehm made their first contribution in https://github.com/ContinualAI/avalanche/pull/1354
  • @MickHardins made their first contribution in https://github.com/ContinualAI/avalanche/pull/1350

Full Changelog: https://github.com/ContinualAI/avalanche/compare/v0.3.1...v0.4.0

- Python
Published by AntonioCarta almost 3 years ago

avalanche-lib - Beta v0.3.1

Fixed minor problem during pip installation

- Python
Published by AndreaCossu over 3 years ago

avalanche-lib - Beta v0.3.0

Improved performance for several benchmarks: - Permuted MNIST #1129 - Online Continual Learning scenarios #1217 Refactoring of the AvalancheDataset (see related how-to) - better support for non-vision data such as Huggingface datasets (see nlp.py) - optional task labels and class labels - performance improvements New strategies: - BiC #1193 - MER #1227 - MIR #1201 - ER-ACE General strategy improvements: - general meta-learning support - Checkpointing support Continual-Learning-Baselines: increased number of baselines and fixed most of the performance issues. All the new strategies will be reproduced at continual-learning-baselines.

What's Changed

  • Added release process description by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1064
  • Fixed extra dependencies build by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1066
  • Outdated imports of training.strategies fixed in docstring and gitbook by @alexsosn in https://github.com/ContinualAI/avalanche/pull/1072
  • Update online strategy profiler by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1082
  • FIX MultiTaskDecorator by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1085
  • AvalancheDatasetType removal, dataset collate_fn used in dataloading during training and eval, sequential benchmark by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1089
  • Packaged csv files for mini imagenet by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1091
  • Implement sampler-based dataloading logic by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1095
  • MultiTask Improvements by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1090
  • Minor fix to a unittest that left text files in the project directory. by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1102
  • Fixed EWC bug in importances, converted Permuted and Rotated MNIST targets in 0-9 by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1101
  • Fix JointStrategy and update strategy tests by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1112
  • Removed warning about SI by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1120
  • Add class_ids_from_zero_in_each_exp to classic benchmarks by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1140
  • Drop support for Python 3.6 by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1143
  • Optional task and class labels in AvalancheDataset #1118 by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1142
  • FIX multitask Lwf and add regularization method interface by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1149
  • Fixed lwf bug for alpha and prev classes per task dict by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1155
  • New mixin-based template structure by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1092
  • Add repr and str special methods to DataAttribute by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1160
  • Fix bug, avoid OOM by @Cocoxili in https://github.com/ContinualAI/avalanche/pull/1167
  • Checkpointing support by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1122
  • huggingface and dictionary datasets support by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1173
  • Add ParamData to manage expansion of data associated to model parameters by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1161
  • Temporary workaround for unit test issues by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1187
  • Ensures rmax and dmax are on the same device as the rest of the variables in BatchRenorm2D by @BenCrulis in https://github.com/ContinualAI/avalanche/pull/1188
  • Make AR1 closer to the original implementation by @BenCrulis in https://github.com/ContinualAI/avalanche/pull/1196
  • ADD function to set dataset root by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1202
  • Add checkpointing tests for environment update action. by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1206
  • FIX eval_streams by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1216
  • Bic by @JuliousHurtado in https://github.com/ContinualAI/avalanche/pull/1193
  • Maximally Interfered Retrieval plugin by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1201
  • speed up dataset concat in OCL scenarios by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1217
  • MER Strategy + OnlineSupervisedMetaLearning Template by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1227
  • Issue Fix for OCL by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1225
  • Remove Kinetics dataset wrapper by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1228
  • Added TensorMNIST to speed up computation, minor fix in agem and mas by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1229
  • update avalanche-datasets how-to by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1234
  • First update of apidoc by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1235
  • Updated evaluation and logging notebooks to release 0.3.0 by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1236
  • update apidoc by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1237
  • add init.py to determinism by @Cocoxili in https://github.com/ContinualAI/avalanche/pull/1222
  • Update FZTH notebooks by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1240
  • Modernization/fix of examples for upcoming release. by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1244
  • Adding ER-ACE strategy by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1230
  • update benchmarks notebook to 0.0.3 by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1245
  • Modernization of examples for v0.0.3 release (part 2) by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1250
  • Fix MIR potential infinite loop by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1251
  • update and fix avl examples by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1252
  • Checkpointing notebook and better InteractiveLogger resume by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1253

New Contributors

  • @alexsosn made their first contribution in https://github.com/ContinualAI/avalanche/pull/1072
  • @Cocoxili made their first contribution in https://github.com/ContinualAI/avalanche/pull/1167
  • @BenCrulis made their first contribution in https://github.com/ContinualAI/avalanche/pull/1188

Full Changelog: https://github.com/ContinualAI/avalanche/compare/v0.2.0...v0.3.0

- Python
Published by AntonioCarta over 3 years ago

avalanche-lib - Beta 0.2.1

Fixed a critical bug in EWC.

- Python
Published by AntonioCarta almost 4 years ago

avalanche-lib - Beta 0.2.0

Release Statement

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.

New Features

Benchmarks

  • CLEAR-10 benchmark #965 #972 #975 #1029
  • CTrL benchmark #561
  • ExML scenarios #977
  • Reinforcement Learning Scenarios #984
  • Online Continual Learning Scenarios #977
  • Object Detection Scenarios
  • New generic scenarios definition #977 #1011

Training - Strategies

  • RWalk #962
  • LaMAML #968
  • Generative Replay #931
  • Memory Aware Synapses #945

Training - Plugins and API

  • ReduceLROnPlateau plugin. #859
  • Improved support for Online Continual Learning. #880 #894 #1024
  • Early stopping & model checkpoint on iterations #887
  • Feat/add margin to early stopping #993
  • LR Scheduler: added iteration granularity, exp0 and epoch0-only options #946
  • New base strategy templates #902 #915 #1002
  • Update ReplayPlugin and ReplayDataLoader #905
  • Object Detection support #916 #917 #922 #933 #939 #947 #963 #920

Logging and Evaluation

  • Add Experience-Change Logging to WandBLogger #875
  • evaluation can log metric values from anywhere #877
  • added the possibility to call the periodic evaluation after iterations instead of epochs. #843
  • Implementation of the top-k accuracy for Avalanche #941

Documentation

  • Improved API documentation. #852 #1019 #1031
  • Improved main avalanche website and FZTH notebooks #866 #871 #914 #1031
  • Added how-to notebooks.

What's Changed

  • periodic eval after eval_every iteration by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/843
  • Support for ReduceLROnPlateau scheduler by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/859
  • GitBook: fixed a bug in documentation by @zalakbhalani in https://github.com/ContinualAI/avalanche/pull/866
  • Prevent TensorboardLogger from blocking the process exit by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/865
  • Fixing issue#771: concatdatasetssequentially discards classes by @ashok-arjun in https://github.com/ContinualAI/avalanche/pull/844
  • add CTrL integration by @TomVeniat in https://github.com/ContinualAI/avalanche/pull/561
  • Fix bug in Zero to Hero Benchmarks Tutorial by @niniack in https://github.com/ContinualAI/avalanche/pull/871
  • Add forcedatabatch_size to ReplayPlugin for manual assignment of data-mem ratio by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/834
  • Add Experience-Change Logging to WandBLogger by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/875
  • evaluation can receive metric values from anywhere by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/877
  • Initialize BaseOnlineStrategy by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/880
  • Early stopping & model checkpoint on iterations by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/887
  • Pnn fix by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/882
  • Fixed periodic eval in joint training by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/893
  • Initialize profiling + online strategy profiler by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/894
  • MLP dropout rate by @zaf-stojano in https://github.com/ContinualAI/avalanche/pull/896
  • New base strategy templates by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/902
  • ADD new test by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/908
  • Update ReplayPlugin and ReplayDataLoader by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/905
  • Set num_workers=0 in all tests by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/911
  • Modified avalanche installation in notebooks to beta version by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/914
  • Minor bug fix in the base_sgd template by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/915
  • Fix target transform bug by @tachyonicClock in https://github.com/ContinualAI/avalanche/pull/923
  • fix raise AttributeError inside evaluation by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/924
  • Fix bugs in CORe50 and openloris datasets by @ggraffieti in https://github.com/ContinualAI/avalanche/pull/929
  • fix EWC with dynamic models by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/925
  • Added lvis dependency by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/939
  • Removed plugin metric tests by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/940
  • Various fixes and enhancements for the data loading process by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/938
  • LR Scheduler: added iteration granularity, exp0 and epoch0-only options by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/946
  • Add torchmetrics dependency. Align lines in environment(-dev).yml by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/947
  • Set num workers to 0 in AGEM buffer dataloader by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/951
  • Memory Aware Synapses by @rmassidda in https://github.com/ContinualAI/avalanche/pull/945
  • Implementation of the top-k accuracy for Avalanche by @rudysemola in https://github.com/ContinualAI/avalanche/pull/941
  • Consolidating changes from the detection branch by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/933
  • Support for persistent workers in object detection template. by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/963
  • Add RWalk implementation and example by @flandolfi in https://github.com/ContinualAI/avalanche/pull/962
  • LaMAML Strategy by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/968
  • Adding CLEAR-10 benchmark to Avalanche by @linzhiqiu in https://github.com/ContinualAI/avalanche/pull/965
  • Updated packages in doc by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/973
  • Generative Replay by @travela in https://github.com/ContinualAI/avalanche/pull/931
  • Add training example for CLEAR benchmark and fix root path issue by @linzhiqiu in https://github.com/ContinualAI/avalanche/pull/972
  • Update benchmark.rst for CLEAR benchmark by @linzhiqiu in https://github.com/ContinualAI/avalanche/pull/975
  • Proposal: New generic scenarios & ExML scenarios by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/977
  • Deterministic test accuracy by @ggraffieti in https://github.com/ContinualAI/avalanche/pull/980
  • Fixed task label bug in metric name by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/986
  • Add RLScenario for Avalanche RL by @NickLucche in https://github.com/ContinualAI/avalanche/pull/984
  • Feat/add margin to early stopping by @evertonaleixo in https://github.com/ContinualAI/avalanche/pull/993
  • Fix Templates type hints by @NickLucche in https://github.com/ContinualAI/avalanche/pull/1002
  • Enable single experience training in JointTraining by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1006
  • Add Generics for new benchmark components by @NickLucche in https://github.com/ContinualAI/avalanche/pull/1011
  • Fix bug in cwr star plugin by @ggraffieti in https://github.com/ContinualAI/avalanche/pull/1008
  • Fix bug in periodic eval - number of worker not passed to the eval method by @ggraffieti in https://github.com/ContinualAI/avalanche/pull/1012
  • Refactor the CLEAR training example by @linzhiqiu in https://github.com/ContinualAI/avalanche/pull/1015
  • apidoc improvements by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1019
  • [add] clear100_cvpr2022 workshop split by @ElvishElvis in https://github.com/ContinualAI/avalanche/pull/1029
  • Evaluation and Logging: Updated FZTH and APIDoc for release 0.2.0 by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1031
  • Output mask for IncrementalClassifier and MultiHeadClassifier by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1027
  • Adapt some FZTH notebooks by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1034
  • Fix apidoc by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1033
  • Examples in docs by @niniack in https://github.com/ContinualAI/avalanche/pull/1022
  • Minor Fix in Examples by @JuliousHurtado in https://github.com/ContinualAI/avalanche/pull/1035
  • Fix "training" and "putting it all together" notebooks from the FZTH tutorial by @ggraffieti in https://github.com/ContinualAI/avalanche/pull/1036
  • Removed edit on github button and fixed default shuffle description by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1042
  • Update OnlineSupervisedTemplate by @HamedHemati in https://github.com/ContinualAI/avalanche/pull/1024
  • FIX examples and lwf by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1045
  • Optional Depencencies by @ggraffieti in https://github.com/ContinualAI/avalanche/pull/1043
  • FIX exml benchmarks by @AntonioCarta in https://github.com/ContinualAI/avalanche/pull/1046
  • Fixed ewc plugin for growing multitask head by @AlbinSou in https://github.com/ContinualAI/avalanche/pull/1047
  • Added learn avalanche in 5 minutes notebook by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1049
  • Fake commit to copy notebook by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1052
  • Added link to colab by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1053
  • Support py3.10 and warning for cope by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1056
  • AMCA metric by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1051
  • Removed duplicated cell by @AndreaCossu in https://github.com/ContinualAI/avalanche/pull/1058
  • Add class accuracy/AMCA to doc. Enable methods doc generation. by @lrzpellegrini in https://github.com/ContinualAI/avalanche/pull/1059

New Contributors

  • @zalakbhalani made their first contribution in https://github.com/ContinualAI/avalanche/pull/866
  • @niniack made their first contribution in https://github.com/ContinualAI/avalanche/pull/871
  • @zaf-stojano made their first contribution in https://github.com/ContinualAI/avalanche/pull/896
  • @rmassidda made their first contribution in https://github.com/ContinualAI/avalanche/pull/945
  • @rudysemola made their first contribution in https://github.com/ContinualAI/avalanche/pull/941
  • @flandolfi made their first contribution in https://github.com/ContinualAI/avalanche/pull/962
  • @linzhiqiu made their first contribution in https://github.com/ContinualAI/avalanche/pull/965
  • @travela made their first contribution in https://github.com/ContinualAI/avalanche/pull/931
  • @evertonaleixo made their first contribution in https://github.com/ContinualAI/avalanche/pull/993
  • @ElvishElvis made their first contribution in https://github.com/ContinualAI/avalanche/pull/1029
  • @JuliousHurtado made their first contribution in https://github.com/ContinualAI/avalanche/pull/1035

Full Changelog: https://github.com/ContinualAI/avalanche/compare/v0.1.0...v0.2.0

- Python
Published by AntonioCarta almost 4 years ago

avalanche-lib - Beta release

Beta release

- Python
Published by AndreaCossu over 4 years ago

avalanche-lib - Alpha 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!

- Python
Published by vlomonaco about 5 years ago