Please provide complete information as applicable to your setup. • Hardware Platform (Jetson / GPU) jetson • DeepStream Version 6.3 • JetPack Version (valid for Jetson only) 5.1.3 • TensorRT Version 8.4 Question 1: I used the uploaded export_yolov8.py to convert the PT model to onnx, resulting …

[image] ncepuwuhan: Network type parameters equal to 0, 1, and 2 do not necessarily correspond exactly to the model type. "network-type‘ only impact which postprocessing will be trigerred to handle the model’s outputs. [image] ncepuwuhan: In fact, the detection model can also be set to n…

[image] Fiona.Chen: The postprocessing algorithms of classifier and detector are different. Please check with your postprocessing implementation. I promise it’s a detection model,but use the latest deepstream-yolo convert file(export_yolov8.py), the onnx model only have one output header,shou…

[image] ncepuwuhan: I promise it’s a detection model,but use the latest deepstream-yolo convert file(export_yolov8.py), the onnx model only have one output header,should I use the convert file that not the latest version? The postprocessing I mentioned in this topic is the postprocessing whic…

hi, What is your final target? export an yolov8 onnx and run with yolo_deepstream ? thanks

Okay, I understand what you mean. How should I configure the config_infer_primary_yoloV8.txt file for post-processing if the output header of the model is one?

i use the deepstream-yolo proj to generate onnx,and use the deepstream-app -c config_primary_yolov8.txt tool to generate the engine format that can run detection analysis on jetson device.i use the above upload file to generate onnx and engine but when I run it’s acount a segmentation error.

you must generate a correct onnx model here is how I export the onnx with python: from ultralytics import YOLO model = YOLO("yolov8s.yaml") path = model.export(format="onnx", imgsz=(640, 640)) # return path to exported model yolov8’s output format is different with yolov7, so you must rewrite …

[image] ncepuwuhan: Okay, I understand what you mean. How should I configure the config_infer_primary_yoloV8.txt file for post-processing if the output header of the model is one? You’ve already configured your postprocessing function “NvDsInferParseYolo” with “network-type=0” in the configur…

ok, thank you so…much for your reply ! I don’t know if I can understand it this way. Network type parameters equal to 0, 1, and 2 do not necessarily correspond exactly to the model type. Previously, I saw that network type=0 corresponds to detection, and equal to 2 represents classification. In fact…

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Consultation on YOLOV8 model conversion related issues and config.inpfer_primary_YOLOV8.txt parameters

Accelerated Computing Intelligent Video Analytics DeepStream SDK

Fiona.Chen December 20, 2024, 1:06am 3

The postprocessing algorithms of classifier and detector are different. Please check with your postprocessing implementation.

Please refer to Gst-nvinfer — DeepStream documentation and DeepStream SDK FAQ - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums

Topic		Replies	Views
Consultation on YOLOV8 model conversion related issues and config.inpfer_primary_YOLOV8.txt parameters DeepStream SDK deepstream	1	78	December 19, 2024
Jetson Orin Nano 8GB, The transformed model has an inference result of [], How to investigate and solve DeepStream SDK jetson , deepstream	2	101	February 27, 2025
Using custom model in deepstream DeepStream SDK jetson-inference , python , deepstream	39	866	September 10, 2024
Generate engine using onnx2trt, The engine was used to call deepstream, but an error was reported DeepStream SDK onnx	4	336	June 11, 2024
Yolov8 and Yolov11 are giving wrong infer results on deepstream 8.0 on Ubuntu24 DeepStream SDK deepstream	3	120	February 13, 2026
ONNX as inference model (YoloV8) DeepStream SDK jetpack , onnx , deepstream	11	4096	June 26, 2023
Deepstream-YOLO-seg custom yolov8 onnx model not working as expected DeepStream SDK onnx , segmentation	21	2634	November 10, 2023
Error during run inference with custom yolov5 model in deepstream DeepStream SDK deepstream	7	282	September 17, 2024
Yolo V8 run on deepstream 7 with python binding DeepStream SDK	5	1123	July 22, 2024
No Detections with YOLOv8 Model DeepStream SDK jetson , deepstream	6	198	November 12, 2025

Consultation on YOLOV8 model conversion related issues and config.inpfer_primary_YOLOV8.txt parameters

Related topics