Why did we open-source our inference engine? Read the post

IDEA-Research/grounding-dino-tiny

The Grounding DINO model was proposed in Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection by Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang.

Architecture
Swin
Parameters
172M
Tasks
Extract
Outputs
Bounding Boxes
License
apache-2.0

Benchmarks

COCO

general detection en

Object detection on COCO natural images

Corpus: 5,000 Queries: 5,000
default_limit-1000
Performance A10G b1 c4
Performance L4-SPOT b1 c4
Performance L4 b1 c4
default_limit-100
Quality
ap 0.4860
ap50 0.6553
ap75 0.5001
ar 100 0.5593
Performance RTX-4090 b1 c16
Reference →

Self-hosted inference for search & document processing

Cut API costs by 50x, boost quality with 85+ SOTA models, and keep your data in your own cloud.