awslabs/Renate
Library for automatic retraining and continual learning
Managing machine learning models that need to adapt to new information over time can be challenging and expensive. This tool helps machine learning engineers and data scientists automatically update their neural network models with new data, ensuring continuous high performance without starting from scratch. It takes in existing neural networks and new batches of data, then outputs an improved, updated model that retains past knowledge.
296 stars. No commits in the last 6 months.
Use this if your machine learning models need to be continuously updated with new data, but retraining from scratch is too costly or leads to performance issues like 'catastrophic forgetting'.
Not ideal if your models are static and do not require ongoing updates with new information, or if you prefer to manually manage all aspects of model retraining.
Stars
296
Forks
7
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 30, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/awslabs/Renate"
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.