Minhchuyentoancbn/Continual-Learning

All in One - Continual Learning

20
/ 100
Experimental

This is a collection of implementations for various continual learning algorithms using PyTorch. It helps machine learning engineers and researchers explore and apply different strategies to train models on new data without forgetting previously learned information. You provide existing PyTorch models and datasets, and it outputs models capable of incremental learning across tasks.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher experimenting with models that need to learn continuously from new data streams without suffering from 'catastrophic forgetting'.

Not ideal if you need a high-level, production-ready framework for immediate deployment or are not comfortable working directly with PyTorch code and research-oriented implementations.

continual-learning deep-learning-research model-training catastrophic-forgetting pytorch-implementations
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Jupyter Notebook

License

Last pushed

May 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Minhchuyentoancbn/Continual-Learning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.