roboflow/roboflow-100-benchmark

Code for replicating Roboflow 100 benchmark results and programmatically downloading benchmark datasets

41
/ 100
Emerging

This project provides a standardized set of 100 diverse image datasets to help computer vision engineers and researchers evaluate how well different object detection models perform across various real-world scenarios. It allows you to download these datasets, structured in common formats like COCO or YOLO, and then run your object detection models to see how accurately they identify objects. The primary users are practitioners who build and test AI models for visual tasks.

288 stars. No commits in the last 6 months.

Use this if you need a comprehensive, multi-domain collection of image data to benchmark the performance of your object detection models.

Not ideal if you are looking for a pre-trained, ready-to-use object detection model or a tool for annotating your own custom datasets.

computer-vision object-detection model-benchmarking image-analysis machine-learning-evaluation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

288

Forks

29

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/roboflow/roboflow-100-benchmark"

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