---
library_name: onnx
tags:
  - dfine
  - object-detection
  - coco
  - computer-vision
  - apache-2.0
  - onnx
  - inference4j
license: apache-2.0
pipeline_tag: object-detection
---

# D-FINE Small (COCO) — ONNX

ONNX export of [ustc-community/dfine-small-coco](https://huggingface.co/ustc-community/dfine-small-coco), the small variant of D-FINE (Redefine Bounding Box Regression for DETR-based Object Detection) trained on COCO (80 classes). Licensed under Apache-2.0, providing a commercially permissive, non-copyleft alternative to AGPL-licensed YOLOv8 and YOLO26 models.

Mirrored for use with [inference4j](https://github.com/inference4j/inference4j), an inference-only AI library for Java.

## Original Source

- **Repository:** [USTC / onnx-community (D-FINE)](https://huggingface.co/ustc-community/dfine-small-coco)
- **License:** apache-2.0

## Usage with inference4j

```java
try (DFine model = DFine.fromPretrained("inference4j/dfine-small-coco")) {
    List<Detection> detections = model.detect(Path.of("street.jpg"));
    detections.forEach(d -> System.out.printf("%s (%.0f%%) at [%.0f, %.0f, %.0f, %.0f]%n",
        d.label(), d.confidence() * 100,
        d.box().x1(), d.box().y1(), d.box().x2(), d.box().y2()));
}
```

## Model Details

| Property | Value |
|----------|-------|
| Architecture | D-FINE Small (transformer object detector) |
| Task | Object detection (COCO 80 classes) |
| License note | Apache-2.0 (permissive non-AGPL alternative to YOLOv8/YOLO26) |
| Input | `pixel_values`: `[batch, 3, 640, 640]` — RGB, normalized 0-1 (bilinear resize, no letterbox) |
| Output | `logits`: `[batch, 300, 80]` (raw logits, apply sigmoid) and `pred_boxes`: `[batch, 300, 4]` (normalized [cx, cy, w, h]) |
| Post-processing | Convert [cx, cy, w, h] to [x1, y1, x2, y2] scaled to image dimensions; filter by score threshold (> 0.5). No NMS required. |
| Original framework | PyTorch (USTC D-FINE) |

## License

This model is licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). Original model by [USTC / Peng et al.](https://github.com/Peterande/D-FINE), hosted by [ustc-community](https://huggingface.co/ustc-community/dfine-small-coco) and converted by [onnx-community](https://huggingface.co/onnx-community/dfine_s_coco-ONNX).