FocsleFo’c’sle
BR

RT-DETR-Edge

22%
by Baidu Research

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
arXiv
OverviewBenchmarks6Sim ResultsDeploy7FilesDiscussion23

Deploy RT-DETR-Edge

Pick a chip family. We hand you the artifacts (HEF, TRT engine, Core ML, ONNX) plus a one-click endpoint deploy. For private endpoints, on-prem deploy, or air-gapped distribution, see Enterprise.

NNVIDIA Jetson Orin Nano
# Build a TensorRT engine
$ focsle pull baidu-research/rt-detr-edge --target jetson-orin-nano
$ focsle build trt --plan rt-detr-edge.plan \
    --precision fp16 \
    --workspace 4G

# Run with TensorRT
import focsle.runtime as fr
m = fr.load("rt-detr-edge.plan", target="trt")
out = m.run(frame)

One-click endpoint

Spins up a managed endpoint in the closest region. Pro and above.

Or deploy yourself