ZhangGongjie/SAM-DETR

[CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation

46
/ 100
Emerging

This project helps computer vision researchers and practitioners efficiently train object detection models. It takes in annotated image datasets (like COCO) and produces a highly accurate object detection model that identifies multiple objects within an image. Anyone working on computer vision tasks requiring fast and precise object detection, such as in autonomous vehicles, surveillance, or content analysis, would find this beneficial.

302 stars. No commits in the last 6 months.

Use this if you need to train a state-of-the-art object detection model faster and more efficiently than traditional DETR-based methods, without sacrificing accuracy.

Not ideal if you are looking for a pre-trained model for immediate inference without needing to customize or train your own object detector.

object-detection computer-vision image-analysis machine-learning-training AI-model-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

302

Forks

46

Language

Python

License

MIT

Last pushed

Aug 24, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ZhangGongjie/SAM-DETR"

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