Current Release

Avalanche is a framework in constant development. 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 Beta (v0.2.0). 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 API documentation.

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 are automatically downloaded by Avalanche.

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

• CIFAR: CIFAR10, CIFAR100.

• ImageNet: TinyImagenet, MiniImagenet, Imagenet.

• Others

📚 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.

📈 Continual Learning Strategies

Avalanche provides Continual Learning algorithms (strategies). We are continuously expanding the library with new algorithms.

• Baselines: Naive, JointTraining, Cumulative.

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

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

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.

• accuracy, loss, confusion (averaged over streams or experiences).

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

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

and .