Access Embedl RF-DETR Base
To access this model, please review and accept the terms below. Your contact information is collected solely to manage access and, with your explicit consent, to notify you about updated or new optimized models from Embedl.
By requesting access you agree to the Embedl Models Community Licence and the upstream RF-DETR License
Log in or Sign Up to review the conditions and access this model content.
Embedl RF-DETR Base (Quantized for TensorRT)
Deployable INT8-quantized version of Roboflow/rf-detr-base,
optimized with embedl-deploy
for low-latency NVIDIA TensorRT inference on edge GPUs.
Upstream Model
Highlights
- Mixed-precision INT8/FP16 quantization with hardware-aware optimizations from embedl-deploy.
- Drop-in replacement for
Roboflow/rf-detr-basein TensorRT pipelines: same image input (560×560), same output semantics. - Validated accuracy within 1.19 pp of the FP32 baseline on COCO (see Accuracy table below).
- Faster than
trtexec --beston supported NVIDIA hardware (see Performance table below). - Includes both ONNX (for TensorRT) and PT2
(
torch.export-loadable) artifacts plus runnable inference scripts.
Quick Start
pip install huggingface_hub onnxruntime-gpu pillow numpy
python -c "from huggingface_hub import snapshot_download; snapshot_download('embedl/rf-detr-base-quantized-tensorrt', local_dir='.')"
python infer_trt.py --image path/to/image.jpg # TensorRT
# or
python infer_pt2.py --image path/to/image.jpg # pure PyTorch via torch.export
Files
| File | Purpose |
|---|---|
embedl_rf-detr-base_int8.onnx |
INT8-quantized ONNX with Q/DQ nodes, ready for TensorRT. |
embedl_rf-detr-base_int8.pt2 |
INT8-quantized torch.export ExportedProgram. |
infer_trt.py |
Build a TRT engine from the ONNX and run sample inference. |
infer_pt2.py |
Load the .pt2 with torch.export.load and run sample inference. |
Performance
Latency measured with TensorRT + trtexec, GPU compute time only
(--noDataTransfers), CUDA Graph + Spin Wait enabled, clocks locked
(max-performance nvpmodel mode + jetson_clocks on Jetson).
NVIDIA Jetson Orin Nano Super
| Configuration | Mean Latency | Speedup vs FP16 |
|---|---|---|
| TensorRT FP16 | 14.83 ms | 1.00x |
| TensorRT --best (unconstrained) | 14.87 ms | 1.00x |
| Embedl Deploy INT8 | 11.77 ms | 1.26x |
Example Detections
Both panels in every figure below are decoded from the actual
TensorRT engines running on the Jetson Orin Nano Super: inputs fed
with trtexec --loadInputs, raw dets/labels outputs exported and
drawn offline. Small per-detection score differences between the two
precisions are expected for a two-stage DETR (proposal selection
reorders under precision changes); the detection sets match.
Confidence-threshold sweep from 0.80 down to 0.30, both engines in sync; detections appear at nearly identical thresholds:
Accuracy
Evaluated on the COCO validation split. The quantized model retains nearly all of the FP32 accuracy with a small tolerance.
| Model | mAP@50-95 | mAP@50 |
|---|---|---|
Roboflow/rf-detr-base FP32 (ours) |
53.32% | 72.16% |
| Embedl RF-DETR Base INT8 | 52.14% | 71.26% |
Creating Your Own Optimized Models
This artifact was produced with embedl-deploy, Embedl's open-source PyTorch-to-TensorRT deployment library. You can apply the same workflow to your own models - see the documentation for installation and usage.
License
| Component | License |
|---|---|
| Optimized model artifacts (this repo) | Embedl Models Community Licence v1.0 (no redistribution as a hosted service) |
| Upstream architecture and weights | RF-DETR License |
Contact
We offer engineering support for on-prem/edge deployments and partner co-marketing opportunities. Reach out at contact@embedl.com, or open an issue on GitHub.
- Downloads last month
- -
Model tree for embedl/rf-detr-base-quantized-tensorrt
Base model
Roboflow/rf-detr-base