LAMDA-CL/LAMDA-PILOT
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
This toolbox helps researchers and machine learning practitioners evaluate and compare various continual learning algorithms built on pre-trained models. It takes existing pre-trained models and new datasets, then applies different methods to adapt the model to new information without forgetting old knowledge. The output is a performance evaluation of these strategies, valuable for those developing or integrating machine learning systems that need to learn continuously over time.
568 stars.
Use this if you are a researcher or ML engineer working with pre-trained models and need to rigorously test how well they can learn new tasks incrementally while retaining previous knowledge.
Not ideal if you are looking for a plug-and-play solution for a specific application without needing to compare different continual learning algorithms.
Stars
568
Forks
67
Language
Python
License
MIT
Category
Last pushed
Jan 29, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LAMDA-CL/LAMDA-PILOT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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,...
mmasana/FACIL
Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.
ContinualAI/avalanche
Avalanche: an End-to-End Library for Continual Learning based on PyTorch.