## Model Information

### Source Model

- Input shape: 1024x1024
- Number of parameters: 2.65M
- Model size: 5.91M
- Output shape: 1x20x21504
- Source model repository: [YOLO26n-OBB](https://docs.ultralytics.com/tasks/obb/)

## Inference with AidLite SDK

```bash
sudo aid-pkg update
sudo aid-pkg install aidlite-sdk
sudo aid-pkg install aidlite-qnn248
```

```bash
cd run_yolo26n-obb
python3.10 code/python/run_test.py \
  --target_model ./models/QCS8550/FP16/yolo26n-obb_qcs8550_fp16.qnn248.ctx.bin \
  --imgs ./code/python/boats.jpg \
  --invoke_nums 10
```

The converted package exposes `output0: [1, 20, 21504]`, i.e. `xywh` (4) +
15 DOTAv1 class scores + angle (1) for 21504 anchors. Decoding uses the
Ultralytics OBB head layout and probabilistic-IoU NMS.

## Version

`2026.11.05.1`