ariG23498/gemma3-object-detection

Fine tune Gemma 3 on an object detection task

39
/ 100
Emerging

This project helps computer vision engineers and researchers adapt Gemma 3, a large vision-language model, for specific object detection tasks. You input images along with corresponding bounding box labels, and the output is a fine-tuned model capable of identifying and locating objects within new images. It’s for those who need a powerful, adaptable model for image analysis.

100 stars. No commits in the last 6 months.

Use this if you need to train a Gemma 3 model to accurately detect specific objects in images, moving beyond its general capabilities.

Not ideal if you need a pre-trained, ready-to-use object detection model without any custom training or model adaptation.

computer-vision image-analysis object-recognition model-fine-tuning vision-language-models
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 7 / 25
Community 21 / 25

How are scores calculated?

Stars

100

Forks

40

Language

Python

License

Last pushed

Jul 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ariG23498/gemma3-object-detection"

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