mmasana/FACIL

Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.

49
/ 100
Emerging

This framework helps machine learning researchers and practitioners analyze different strategies for Class-Incremental Learning (CIL). It takes in existing CIL approaches and datasets, allowing you to train models on a sequence of new classes over time without forgetting old ones. The output is a performance evaluation of various incremental learning methods.

563 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer developing and evaluating new class-incremental learning algorithms or comparing existing ones.

Not ideal if you are looking for a pre-trained model for immediate use in an application or a simple, non-incremental supervised learning solution.

Machine Learning Research Continual Learning Deep Learning Evaluation Model Training Image Classification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

563

Forks

103

Language

Python

License

MIT

Last pushed

May 26, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mmasana/FACIL"

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