bes-dev/pytorch_clip_bbox

Pytorch based library to rank predicted bounding boxes using text/image user's prompts.

33
/ 100
Emerging

This library helps refine object detection results to find very specific items. You provide an image with detected objects and a text description (like "red cup" instead of just "cup") or an example image. It then helps you pinpoint the exact object you're looking for, making your detection more precise. This is for machine learning engineers and computer vision scientists who build and deploy object detection systems.

No commits in the last 6 months.

Use this if you need to find highly specific objects within an image using natural language descriptions or example images, going beyond the general categories your object detector was originally trained on.

Not ideal if your existing object detection model already provides sufficient specificity for your needs without further refinement.

Object Detection Computer Vision Image Analysis Machine Learning Engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

52

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Dec 25, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/bes-dev/pytorch_clip_bbox"

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