ContinualAI/avalanche
Avalanche: an End-to-End Library for Continual Learning based on PyTorch.
Provides modular components for benchmarking (PermutedMNIST, standard CL datasets), implementing strategies (Naive, replay-based, and state-of-the-art algorithms), and evaluating continual learning systems through unified metrics and TensorBoard integration. Built on PyTorch with a unified streaming API for task sequences, enabling researchers to prototype algorithms while standardizing evaluation across continual learning research.
2,036 stars. No commits in the last 6 months.
Stars
2,036
Forks
316
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ContinualAI/avalanche"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aimagelab/mammoth
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of...
LAMDA-CL/PyCIL
PyCIL: A Python Toolbox for Class-Incremental Learning
GMvandeVen/continual-learning
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR,...
LAMDA-CL/LAMDA-PILOT
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
mmasana/FACIL
Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.