Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

License

NotificationsYou must be signed in to change notification settings

gned0/avalanche

 
 

Repository files navigation

Avalanche is anend-to-end Continual Learning library based onPytorch, born withinContinualAI with the unique goal of providing a shared and collaborativeopen-source (MIT licensed) codebase for fast prototyping, training and reproducible evaluation of continual learning algorithms.

⚠️ Looking forcontinual learning baselines? In theCL-Baseline sibling project based on Avalanche we reproduce seminal papers results you can directly use inyour experiments!

Avalanche can help Continual Learning researchers in several ways:

  • Write less code, prototype faster & reduce errors
  • Improve reproducibility, modularity and reusability
  • Increase code efficiency, scalability & portability
  • Augment impact and usability of your research products

The library is organized into four main modules:

  • Benchmarks: This module maintains a uniform API for data handling: mostly generating a stream of data from one or more datasets. It contains all the major CL benchmarks (similar to what has been done for torchvision).
  • Training: This module provides all the necessary utilities concerning model training. This includes simple and efficient ways of implement new continual learning strategies as well as a set of pre-implemented CL baselines and state-of-the-art algorithms you will be able to use for comparison!
  • Evaluation: This module provides all the utilities and metrics that can help evaluate a CL algorithm with respect to all the factors we believe to be important for a continually learning system. It also includes advanced logging and plotting features, including native Tensorboard support.
  • Models: This module provides utilities to implement model expansion and task-aware models, along with a set of pre-trained models and popular architectures that can be used for your continual learning experiment (similar to what has been done in torchvision.models).
  • Logging: It includes advanced logging and plotting features, including native stdout, file and TensorBoard support (How cool it is to have a complete, interactive dashboard, tracking your experiment metrics in real-time with a single line of code?)

Avalanche the first experiment of anEnd-to-end Library for reproducible continual learning research & development where you can find benchmarks, algorithms, evaluation metrics and much more, in the same place.

Let's make it together 🧑‍🤝‍🧑 a wonderful ride! 🎈

Check out below how you can start using Avalanche! 👇

Quick Example

importtorchfromtorch.nnimportCrossEntropyLossfromtorch.optimimportSGDfromavalanche.benchmarks.classicimportPermutedMNISTfromavalanche.modelsimportSimpleMLPfromavalanche.trainingimportNaive# Configdevice=torch.device("cuda:0"iftorch.cuda.is_available()else"cpu")# modelmodel=SimpleMLP(num_classes=10)# CL Benchmark Creationperm_mnist=PermutedMNIST(n_experiences=3)train_stream=perm_mnist.train_streamtest_stream=perm_mnist.test_stream# Prepare for training & testingoptimizer=SGD(model.parameters(),lr=0.001,momentum=0.9)criterion=CrossEntropyLoss()# Continual learning strategycl_strategy=Naive(model,optimizer,criterion,train_mb_size=32,train_epochs=2,eval_mb_size=32,device=device)# train and test loop over the stream of experiencesresults= []fortrain_expintrain_stream:cl_strategy.train(train_exp)results.append(cl_strategy.eval(test_stream))

Current Release

Avalanche is a framework in constant development. Thanks to the support of theContinualAI community and its active members we are quickly extending its features and improve its usability based on the demands of our research community!

A the moment, Avalanche is inBeta. We supportseveralBenchmarks,Strategies andMetrics, that make it, we believe, the best tool out there for your continual learning research! 💪

You can install Avalanche by runningpip install avalanche-lib.
This will install the core Avalanche package. You can install Avalanche with extra packages to enable more functionalities.
Lookhere for a more complete guide on the different ways available to install Avalanche.

Getting Started

We know that learning a new tool may be tough at first. This is why we made Avalanche as easy as possible to learn with a set of resources that will help you along the way.For example, you may start with our 5-minutes guide that will let you acquire the basics about Avalanche and how you can use it in your research project:

We have also prepared for you a large set of examples & snippets you can plug-in directly into your code and play with:

Having completed these two sections, you will already feel with superpowers ⚡, this is why we have also created an in-depth tutorial that will cover all the aspects of Avalanche indetail and make you a true Continual Learner! 👩‍🎓

Cite Avalanche

If you use Avalanche in your research project, please remember to cite our JMLR-MLOSS paperhttps://jmlr.org/papers/v24/23-0130.html. This will help us make Avalanche better known in the machine learning community, ultimately making a better tool for everyone:

@article{JMLR:v24:23-0130,  author  = {Antonio Carta and Lorenzo Pellegrini and Andrea Cossu and Hamed Hemati and Vincenzo Lomonaco},  title   = {Avalanche: A PyTorch Library for Deep Continual Learning},  journal = {Journal of Machine Learning Research},  year    = {2023},  volume  = {24},  number  = {363},  pages   = {1--6},  url     = {http://jmlr.org/papers/v24/23-0130.html}}

you can also cite the previousCLVision @ CVPR2021 workshop paper:"Avalanche: an End-to-End Library for Continual Learning".

@InProceedings{lomonaco2021avalanche,    title={Avalanche: an End-to-End Library for Continual Learning},    author={Vincenzo Lomonaco and Lorenzo Pellegrini and Andrea Cossu and Antonio Carta and Gabriele Graffieti and Tyler L. Hayes and Matthias De Lange and Marc Masana and Jary Pomponi and Gido van de Ven and Martin Mundt and Qi She and Keiland Cooper and Jeremy Forest and Eden Belouadah and Simone Calderara and German I. Parisi and Fabio Cuzzolin and Andreas Tolias and Simone Scardapane and Luca Antiga and Subutai Amhad and Adrian Popescu and Christopher Kanan and Joost van de Weijer and Tinne Tuytelaars and Davide Bacciu and Davide Maltoni},    booktitle={Proceedings of IEEE Conference on Computer Vision and Pattern Recognition},    series={2nd Continual Learning in Computer Vision Workshop},    year={2021}}

Maintained by ContinualAI Lab

Avalanche is the flagship open-source collaborative project ofContinualAI: a non-profit research organization and the largest open community on Continual Learning for AI.

Do you have a question, do you want to report an issue or simply ask for a new feature? Check out theQuestions & Issues center. Do you want to improve Avalanche yourself? Follow these simple rules onHow to Contribute.

The Avalanche project is maintained by the collaborative research teamContinualAI Lab and used extensively by the Units of theContinualAI Research (CLAIR) consortium, a research network of the major continual learning stakeholders around the world.

We are always looking for new awesome members willing to join the ContinualAI Lab, so check out ourofficial website if you want to learn more about us and our activities, orcontact us.

Learn more about theAvalanche team and all the people who made it great!


About

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python81.0%
  • Jupyter Notebook18.9%
  • Other0.1%

[8]ページ先頭

©2009-2025 Movatter.jp