ghty11468
ghty11468
> 请关注： https://github.com/marcoslucianops/DeepStream-Yolo/blob/master/docs/YOLOv5.md > > 引擎输出错误，因此您使用了错误的 ONNX 模型。 My onnx file was generated using the Ultratics/Yolov5 project, but is it not allowed?
> 您是否使用带有检测的 RTSP 输出？ Thank you for your answer. My problem has been solved
> It's better to use database/kafka, in my opinion, to save the results and use another code to control de GPIO. But you can put the GPIO code in the...
> Before the NMS? If so, why? It's not the front of NMS, it's the back of NMS. After the NMS is executed, the detection results are available. I use...
> You can set it in the `pad_buffer_probe` function in any `deepstream_python_apps` after the `frame_meta` or `obj_meta` cast depending on what you want to do. What the author means is...
> Please use the branch of the to convert the model (even using older versions).`master``ultralytics/yolov5` Is it necessary to use the model obtained from the old version of the YOLOv5...
> Please use the branch of the to convert the model (even using older versions).`master``ultralytics/yolov5` I am also reporting errors like this. How can I solve it?
This problem has been solved. The method is to reduce the version of onnx
> 尝试使用以下命令导出的 ONNX 模型： > > ``` > python3 export_yoloV5.py -w yolov5s.pt -s 320 --opset 11 > ``` I have already tried. The same error will still occur
> Sorry I saw the log now, probably you don't need the ; The log is saying that the exported ONNX model is with dynamic range. You should not get...