Wiki
GitHubContinualAI
  • Welcome to ContinualAI Wiki
  • Wiki contents
    • Introduction to Continual Learning
    • Research
    • Industry
    • Software and Benchmarks
    • Tutorials and Courses
    • Media Articles
  • Continual Learning papers
    • GitHub List + Bibtex
  • ABOUT US
    • The People
    • Join us!
    • Slack
    • Email
Powered by GitBook
On this page
  • Software
  • Datasets and Benchmarks

Was this helpful?

  1. Wiki contents

Software and Benchmarks

PreviousIndustryNextTutorials and Courses

Last updated 3 years ago

Was this helpful?

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

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

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

  • : 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…).

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

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

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

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

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

Datasets and Benchmarks

  • : Continual Learning benchmark for object recognition and robotics.

  • : A Dataset and Benchmark towards Lifelong Object Recognition

  • : Streaming Classification and Novelty Detection from Videos

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

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

  • : a Dataset for Continual Learning and Robotics.

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

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

Avalanche
ContinualAI
Sequoia Library
Continuum
NORB sequencer
GEM implementation
OpenAI Gym
DeepMind Lab
DEN
CORe50 benchmark
OpenLORIS-Object
Stream-51
CRIB
Visual Domain Decathlon
iCubWord Transformation
Omniglot
NICO