LAMDA-CL/PyCIL
PyCIL: A Python Toolbox for Class-Incremental Learning
This tool helps machine learning researchers build models that can continuously learn new categories of data without forgetting previously learned information. It takes in new datasets with unseen classes and produces a single, updated model that performs well across all categories, old and new. It's designed for researchers developing and evaluating class-incremental learning algorithms.
1,060 stars.
Use this if you are a machine learning researcher who needs to experiment with and compare various class-incremental learning methods to build models that adapt to new data over time.
Not ideal if you are looking for a plug-and-play solution for a business application and do not have machine learning research expertise.
Stars
1,060
Forks
157
Language
Python
License
—
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/PyCIL"
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...
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.
ContinualAI/avalanche
Avalanche: an End-to-End Library for Continual Learning based on PyTorch.