BRby Baidu Research
RT-DETR-Edge
22%Real-time DETR optimized for transformer-friendly NPUs. Wins on transformer-class silicon, struggles on legacy NPUs.
Object detectionApache-2.0INT8FP16transformercocodetection
92K downloads 5.4K deploymentsUpdated Apr 2, 2028
Headline:18.6ms · NVIDIA Jetson Orin Nano · FP16
Files
Weights, configs, and per-vendor compiled exports. Files marked LFS are stored on the Fo’c’sle CDN and served regional.
| Name | Size | Updated | |
|---|---|---|---|
| README.md | 8.4 KB | 2028-04-02 | |
| config.json | 2.1 KB | 2028-04-02 | |
| tokenizer.json | 1.8 MB | 2028-04-02 | |
| model.safetensorsLFS | 25.7 MB | 2028-04-02 | |
| rt-detr-edge.onnxLFS | 22.9 MB | 2028-04-02 | |
| rt-detr-edge_int8.tfliteLFS | 22 MB | 2028-04-02 | |
| rt-detr-edge.jetson-orin-nano.planLFS | 35 MB | 2028-04-02 | |
| rt-detr-edge.jetson-agx-orin.planLFS | 35 MB | 2028-04-02 | |
| rt-detr-edge.jetson-thor.planLFS | 35 MB | 2028-04-02 | |
| rt-detr-edge.mlmodelcLFS | 24 MB | 2028-04-02 | |
| examples/ | — | 2028-04-02 | |
| benchmarks/ | — | 2028-04-02 | |
| LICENSE | 11.4 KB | 2028-04-02 |