overeasy-sh/overeasy

Orchestrate zero-shot computer vision models

36
/ 100
Emerging

This project helps operations engineers or safety managers quickly set up custom computer vision systems to automatically identify objects, classify images, or detect bounding boxes in visual data. You provide images and define what you're looking for (e.g., 'person's head', 'hard hat'), and it outputs identified objects and their classifications without needing large amounts of labeled training data. This is ideal for those who need to automate visual inspection tasks.

390 stars. No commits in the last 6 months.

Use this if you need to build custom image analysis workflows quickly, like detecting if construction workers are wearing hard hats, without the hassle of collecting and annotating thousands of images.

Not ideal if you need to train highly specialized models from scratch with very specific, unique datasets, or if you prefer a system that requires extensive dataset annotation for optimal performance.

safety-monitoring visual-inspection operations-management image-analysis quality-control
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

390

Forks

15

Language

HTML

License

MIT

Last pushed

Aug 20, 2024

Commits (30d)

0

Get this data via API

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

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