Software and Benchmarks

One of the most important objectives of the Continual AI project is to provide easy access to Continual Learning both in terms of didactic materials and open software/datasets for business/research. In this page we will try to collect every open-source project related to Continual Learning.

Software

  • Avalanche: an End-to-End Library for Continual Learning, developed and maintained by ContinualAI.

  • Sequoia Library: A Playground for research at the intersection of Continual, Reinforcement, and Self-Supervised Learning.

  • Continuum: Continuum is a Python library (written with PyTorch) for loading of datasets in Continual Learning. It supports many datasets and most CL scenarios (NC, NI, NIC…).

  • NORB sequencer: Java application (with GUI) to make small videos out of the NORB dataset.

  • GEM implementation: Implementation of the CL strategy “Gradient Episodic Memory”.

  • OpenAI Gym: Open source interface that provides a ready-to-use suite of reinforcement learning tasks for evaluating performance of your algorithm.

  • DeepMind Lab: 3D learning environment that provides a suite of challenging 3D navigation and puzzle-solving tasks for learning agents.

  • DEN: TensorFlow implementation of the CL strategy “Dynamically Expandable Networks”.

Datasets and Benchmarks

  • CORe50 benchmark: Continual Learning benchmark for object recognition and robotics.

  • OpenLORIS-Object: A Dataset and Benchmark towards Lifelong Object Recognition

  • Stream-51: Streaming Classification and Novelty Detection from Videos

  • CRIB: Synthetic, incremental object learning environment that can produce data that models visual imagery produced by object exploration in early infancy

  • Visual Domain Decathlon: Ten image classification problems representative of very different visual domains.

  • iCubWord Transformation: a Dataset for Continual Learning and Robotics.

  • Omniglot: A dataset for few shot, meta-learning and continual learning.

  • NICO: Towards Non-i.i.d. Image Classification.