Drone-axera

This version of Drone-axera has been converted to run on the Axera NPU using w8a16 quantization. It is trained with yolo11s/yolo26s to detect drones.

Supported Classes

This model is trained to detect drones in our life with one label:

1. Drone

Compatible with Pulsar2 version: 5.2.

Convert tools links:

For those who are interested in model conversion, you can try to export axmodel through:

• The repo of AXera Platform, where you can get the detailed guide.
• Pulsar2 Link, How to Convert ONNX to axmodel

Support Platform

https://docs.m5stack.com/zh_CN/ai_hardware/AI_Pyramid-Pro

• AX650N/AX8850
  • M4N-Dock(爱芯派Pro)
  • AI Pyramid
  • M.2 Accelerator card

How to use

Download all files from this repository to the device.

python env requirement

pyaxengine

https://github.com/AXERA-TECH/pyaxengine

wget https://github.com/AXERA-TECH/pyaxengine/releases/download/0.1.3.rc2/axengine-0.1.3-py3-none-any.whl
pip install axengine-0.1.3-py3-none-any.whl

Inference with AX650 Host, such as M4N-Dock(爱芯派Pro)

Input image:

run

python3 axmodel_infer_yolo26.py
or
python3 axmodel_infer_yolo11.py

root@ax650:~/Drone# python3 axmodel_infer_yolo11.py
[INFO] Available providers:  ['AxEngineExecutionProvider', 'AXCLRTExecutionProvider']
[INFO] Using provider: AxEngineExecutionProvider
[INFO] Chip type: ChipType.MC50
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Engine version: 2.12.0s
[INFO] Model type: 0 (single core)
[INFO] Compiler version: 5.2 df2fe798
0/1: ./test/23.jpg
class: Drone:0.97, bbox: [294, 226, 335, 270], score: 0.97
结果已保存到 ./drone_yolo11_res

Output image: