Avalanche
GitHubAPI DocCL-BaselinesAvalanche-RLOnline CL Repo
Avalanche - latest
Avalanche - latest
  • Avalanche: an End-to-End Library for Continual Learning
  • 📌Getting Started
    • Introduction
    • Current Release
    • How to Install
    • Learn Avalanche in 5 Minutes
  • 📙From Zero to Hero Tutorial
    • Introduction
    • Models
    • Benchmarks
    • Training
    • Evaluation
    • Loggers
    • Putting All Together
    • Extending Avalanche
    • Contribute to Avalanche
  • How-Tos
    • AvalancheDataset
      • avalanche-datasets
      • avalanche-transformations
    • Dataloaders, Buffers, and Replay
    • Save and load checkpoints
  • 📝Examples
    • Models
    • Benchmarks
    • Training
    • Evaluation
    • Loggers
  • 💻Code Documentation
    • Avalanche API
  • How to Contribute
    • Guidelines
  • ❓Questions and Issues
    • Ask Your Question
    • Add Your Issue
    • Request a Feature
    • Give Feedback
    • FAQ
  • 👪About Us
    • The People
    • Join Us!
    • Slack
    • Email
    • Twitter
Powered by GitBook
On this page
  • Benchmarks and Datasets
  • 🖼️ Datasets
  • 📚 Benchmarks
  • 📈 Continual Learning Strategies
  • Models
  • 📊 Metrics and Evaluation

Was this helpful?

Edit on GitHub
Export as PDF
  1. Getting Started

Current Release

Avalnche Features: Benchmarks, Strategies & Metrics

PreviousIntroductionNextHow to Install

Last updated 2 years ago

Was this helpful?

Avalanche is a framework in constant development. Thanks to the support of the 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 Beta (v0.3.1). We support a large number of Benchmarks, Strategies and Metrics, that makes it, we believe, the best tool out there for your continual learning research! 💪

You can find the full list of available features on the .

Do you think we are missing some important features? Please ! We deeply value !

Benchmarks and Datasets

You find a complete list of the features on the .

🖼️ Datasets

Avalanche supports all the most popular computer vision datasets used in Continual Learning. Some of them are available in , while other have been integrated by us. Most datasets can be automatically downloaded by Avalanche.

  • Toy datasets: MNIST, Fashion MNIST, KMNIST, EMNIST, QMNIST.

  • CIFAR: CIFAR10, CIFAR100.

  • ImageNet: TinyImagenet, MiniImagenet, Imagenet.

  • Others: EndlessCLDataset, CUB200, OpenLORIS, Stream-51, INATURALIST2018, Omniglot, CLEARImage, ...

📚 Benchmarks

All the major continual learning benchmarks are available and ready to use. Benchmarks split the datasets and create the train and test streams:

  • MNIST: SplitMNIST, RotatedMNIST, PermutedMNIST, SplitFashionMNIST.

  • CIFAR10: SplitCIFAR10, SplitCIFAR100, SplitCIFAR110.

  • CORe50: all the CORe50 scenarios are supported.

  • Others: SplitCUB200, CLStream51, CLEAR.

📈 Continual Learning Strategies

  • Baselines: Naive, JointTraining, Cumulative.

  • Rehearsal: Replay with reservoir sampling and balanced buffers, GSS greedy, CoPE, Generative Replay.

  • Regularization: EWC, LwF, GEM, AGEM, CWR*, Synaptic Intelligence, MAS.

  • Architectural: Progressive Neural Networks, multi-head, incremental classifier.

  • Others: GDumb, iCaRL, AR1, Streaming LDA, LFL.

Models

Avalanche uses and extends pytorch nn.Module to define continual learning models:

  • support for nn.Modules and torchvision models.

  • Dynamic output heads for class-incremental scenarios and multi heads for task-incremental scenarios.

  • support for architectural strategies and dynamically expanding models such as progressive neural networks.

📊 Metrics and Evaluation

Avalanche provides continuous evaluation of CL strategies with a large set of Metrics. They are collected and logged automatically by the strategy during the training and evaluation loops.

  • Standard Performance Metrics: accuracy, loss, confusion (averaged over streams or experiences).

  • CL-Metrics: backward/forward transfer, forgetting.

  • Computational Resources: CPU and RAM usage, MAC, execution times.

Avalanche provides Continual Learning algorithms (strategies). We are continuously expanding the library with new algorithms and making sure they can reproduce seminal papers results in the sibling project .

and .

📌
ContinualAI
API documentation
let us know
your feedback
benchmarks API documentation
Torchvision
CL-Baselines
many more