yolov5导出命令

python export.py --weights yolov5s.pt --img-size 640 --batch-size 1  --device cpu --include onnx  

关闭动态输入，cpu导出

检测onnx模型能否加载成功指令：

python detect.py --weights yolov5s.onnx --dnn   

终端调用detect.py检测图片命令：

python detect.py --weights yolov5s.onnx --img-size 640 --source .\data\images\bus.jpg  --device cpu
 

使用pt导出的yolov5s.onnx运行报错：

./main_cmake_exe
[ERROR:0@0.028] global onnx_importer.cpp:1061 handleNode DNN/ONNX: ERROR during processing node with 1 inputs and 1 outputs: [Floor]:(onnx_node!/model.11/Floor) from domain='ai.onnx'
terminate called after throwing an instance of 'cv::Exception'
  what():  OpenCV(4.8.0) /home/xwy/src/opencv-4.8.0/modules/dnn/src/onnx/onnx_importer.cpp:1083: error: (-2:Unspecified error) in function 'handleNode'
> Node [[e-mail]]:(onnx_node!/model.11/Floor) parse error: OpenCV(4.8.0) /home/xwy/src/opencv-4.8.0/modules/dnn/src/layers/elementwise_layers.cpp:260: error: (-215:Assertion failed) src.size == dst.size && src.type() == dst.type() && src.isContinuous() && dst.isContinuous() && src.type() == CV_32F in function 'forward'
>
已放弃 (核心已转储)

解决方法：导出onnx文件的时候把使用pytorch1.11或者更低版本