OpenVINO部署Yolov5

0.开发环境

硬件平台： 8  11th Gen Intel(R) Core(TM) i5-1145G7E @ 2.60GHz

操作系统：Ubuntu 20.04 (LTS)

OpenVINO: 2021.04（LTS）

Python: 3.8.5 (conda 虚拟环境)

Pytorch: 1.9.0+cpu

onnx: 1.9.0

onnx-simplifier: 0.3.6

onnxruntime: 1.8.1

onnxoptimizer: 0.2.6

1. yolov5转onnx

1）github 下载yolov5 v3.1版本

git clone https://github.com/ultralytics/yolov5.git

2) 下载yolov5s v3.1 版本模型文件

cd yolov5
mkdir weights
cd weights
wget https://github-releases.githubusercontent.com/264818686/997a2180-dd58-11ea-913b-55fd4470d8be?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAIWNJYAX4CSVEH53A%2F20210721%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20210721T100023Z&X-Amz-Expires=300&X-Amz-Signature=5c555f53117829f9a8b0251dab8540a70a9557dc51cad429a0165476aab7b2c0&X-Amz-SignedHeaders=host&actor_id=21002818