grasp-lyrl/modelzoo_continual
Model Zoos for Continual Learning (ICLR 22)
This project helps machine learning researchers and practitioners develop models that learn new tasks sequentially without forgetting previous knowledge. It takes a series of related tasks or datasets as input, processes them, and outputs an improved, more generalized model capable of performing well across all learned tasks. It's designed for those working with continual learning scenarios, where models need to adapt and grow over time.
No commits in the last 6 months.
Use this if you need to train AI models on a stream of incoming data or tasks, where each new task should ideally enhance past performance and not degrade it.
Not ideal if your learning problem involves discrete, unrelated tasks that don't benefit from shared knowledge or sequential processing.
Stars
45
Forks
9
Language
Python
License
MIT
Category
Last pushed
May 29, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/grasp-lyrl/modelzoo_continual"
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.