AXERA-TECH/E_bike-axera

Axera-emd

This version of Axera-emd has been converted to run on the Axera NPU using w8a16 quantization. It is primarily used for detecting bicycles, e-bikes, or motorcycles in elevator control applications.

Supported Classes

This model is trained to detect the following 2 classes:

1. bicycle
2. e-bike

Compatible with Pulsar2 version: 5.0.

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
• AX620E
  • 爱芯派2
  • Module-LLM

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 ax_emd_infer.py --model ./AX650/ax_ax650_emd_algo_V1.0.0.axmodel --img test.jpg

root@ax650:/pcd# python3 ax_emd_infer.py --model ./AX650/ax_ax650_emd_algo_V1.0.0.axmodel --img test.jpg
[INFO] Available providers:  ['AxEngineExecutionProvider']
[INFO] Using provider: AxEngineExecutionProvider
[INFO] Chip type: ChipType.MC50
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Engine version: 2.10.1s
[INFO] Model type: 2 (triple core)
[INFO] Compiler version: 6.0 79a1e641
Input_name: images, Output_name: ['output0', 'output1']
Preprocess time: 7.52 ms
Inference time: 18.09 ms
Total detect 1 objects
0: e-bike        0.785 [657.0, 321.0, 877.0, 635.0]

Output image: