VerwimpEli/CLAD

Implementation of CLAD: A Continual Learning benchmark for Autonomous Driving. A continual classification and detectin track. Provides pure PyTorch, Avalanche and Detectron2 implementations.

26
/ 100
Experimental

This project provides a standardized way to test and compare different machine learning models designed for autonomous driving. It takes in real-world driving footage and evaluates how well models can continuously learn to classify objects (like pedestrians or cars) and detect them over time, even as conditions change (e.g., day to night, city to highway). Autonomous vehicle engineers and researchers can use this to benchmark their continual learning algorithms.

No commits in the last 6 months.

Use this if you are developing or evaluating machine learning models for self-driving cars and need a realistic benchmark to test their ability to adapt to changing environments and data streams without forgetting previously learned information.

Not ideal if you are looking for a pre-trained model for immediate deployment in an autonomous driving system, or if your focus is on a different domain than object detection and classification in driving scenarios.

autonomous-driving machine-learning-benchmarking object-detection continual-learning computer-vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

33

Forks

4

Language

Python

License

Last pushed

Apr 24, 2024

Commits (30d)

0

Get this data via API

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

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