RF-DETR Small (ONNX) — pet detection for Gallery
ONNX export of RF-DETR Small by Roboflow, used by Gallery for pet detection.
Unmodified COCO-pretrained weights. No fine-tuning.
Files
| Path | Description |
|---|---|
detection/model.onnx |
RF-DETR Small, opset 17, batch 1 |
Inference contract
Getting any of this wrong degrades output silently rather than erroring.
Input — input, shape [1, 3, 512, 512], float32:
- Decode to RGB (not BGR)
- Resize to 512×512 — plain square resize, not letterboxed
- Scale to
[0, 1] - Normalise with ImageNet statistics: mean
[0.485, 0.456, 0.406], std[0.229, 0.224, 0.225] - Transpose HWC → CHW, add batch dimension
Output — two tensors:
| Name | Shape | Meaning |
|---|---|---|
dets |
[1, 300, 4] |
Boxes as cx, cy, w, h — normalised to [0, 1] |
labels |
[1, 300, 91] |
Class logits, pre-sigmoid |
Apply sigmoid to labels, then threshold. Classes use the 91-class COCO id space
(90 categories plus background), not the contiguous 80-class space YOLO uses — so
bird=16, cat=17, dog=18, horse=19, sheep=20, cow=21.
The 300 queries are already deduplicated. No NMS step is required.
License
Apache-2.0, inherited from RF-DETR. See the upstream repository for full terms.