Jetson Orin Nano 8GB, The transformed model has an inference result of [], How to investigate and solve

device: Jetson Orin Nano 8GB,
model:Object detection model developed by Ultralytics,yolov8s.pt
Conversion process:pt————> onnx————> engine
Conversion Script:
python3 export-det.py --weights deepstream/yolov8s_bak.pt --iou-thres 0.65 --conf-thres 0.25 --topk 100 --opset 11 --sim --input-shape 1 3 544 960 --device cuda:0

/usr/src/tensorrt/bin/trtexec --onnx=deepstream/yolov8s_bak.onnx --saveEngine=deepstream/yolov8s_bak.engine --buildOnly --minShapes=images:1x3x544x960 --optShapes=images:1x3x544x960 --maxShapes=images:1x3x544x960

Please refer to this sample for yolov8 model. it provides model, configuration file, pipeline, and post-processing code.

The model export code is not provided by DeepStream. For more questions, please consult the Ultralytics

Seem like you exported with NMS, in which case you would need to modify the post-processing to not use NMS and use correct parsing.