README.md

metadata

license: agpl-3.0
language:
  - en
pipeline_tag: object-detection
tags:
  - Axera
  - YOLOv5
  - NPU
  - Ultralytics
  - Cow Detection
  - Object Detection

Cow-axera

This version of Cow-axera has been converted to run on the Axera NPU using w8a16 quantization. It is trained to detect cows in the wild.

Supported Classes

This model is trained to detect cows with one class:

1. Cow

Compatible with Pulsar2 version: 6.0.

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

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 sample:

run

python3 axmodel_infer_yolov5.py

root@ax650:~/cow-axera# python3 axmodel_infer_cow_yolov5.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: 2 (triple core)
[INFO] Compiler version: 6.0 6965315a
class: cow left:356 top:79 right:464 bottom:119 conf: 76%
class: cow left:57 top:109 right:322 bottom:284 conf: 94%
class: cow left:251 top:104 right:550 bottom:355 conf: 95%
Saved res to ./axmodel_res.jpg

Output image sample: