1 下载yolov10模型

wget https://github.com/THU-MIG/yolov10/releases/download/v1.1/yolov10s.pt

2 搭建ixrt的conda 环境

conda create --name py310 python=3.10
conda env list
conda activate py310

pip3 install ixrt-0.9.1+corex.4.1.2-cp310-cp310-linux_x86_64.whl

pip3 install torch-2.1.1+corex.4.1.2-cp310-cp310-linux_x86_64.whl

pip3 install torchvision-0.16.0+corex.4.1.2-cp310-cp310-linux_x86_64.whl

3 编辑测试py文件

from ultralytics import YOLO

# Load the model
model = YOLO('yolov10s.pt')

# Export the model to ONNX format
model.export(format='onnx')

4 执行py文件，生成yolov10s.onnx文件

python3 testyolov10.py

5 使用ixrtexec命令快速测试

ixrtexec --onnx yolov10s.onnx