When converting the YOLOv8 ONNX model to the DeepStream engine, there is a loss of accuracy, especially for larger objects. However, when converting the model outside of DeepStream, from ONNX to Engine, accuracy is not affected. The same problem happens for yolov4 trained on tao Warning logs when a…

Thank you very much. I changed the parameter value of StateEstimator from 1 to 0 and now it is working correctly.

Loss of precision to onnx converter for engine by deepstream 6.3

yuweiw July 15, 2024, 2:56am 7

Could you please post the parameters you used in the above 2 scenarios?
You can also refer to our FAQ to tune some parameters.

Topic		Replies	Views
Issue with Bounding Boxes and Object Detection in DeepStream Using YOLOv8 Model DeepStream SDK yolo , deepstream	9	102	April 18, 2025
Yolov8seg giving divide by 0 errors if no detection in frame DeepStream SDK	11	796	November 7, 2023
App Run Fails With Errors DeepStream SDK jetson-inference , yolo , debugging-and-troubleshooting	28	1830	October 23, 2023
What kind of hardware rigs can support 100+ videos analytics using deepstream? DeepStream SDK hw	30	1838	October 12, 2021
Get wrong infer results while testing yolov4 on deepstream 5.0 DeepStream SDK	46	9420	October 12, 2021
ONNX as inference model (YoloV8) DeepStream SDK jetpack , onnx , deepstream	12	3545	July 10, 2023
Tutorial: How to run YOLOv7 on Deepstream DeepStream SDK demos-and-tutorials	19	6954	March 26, 2024
Engine file and calib.table not saved in DeepStream DeepStream SDK tensorrt	6	904	December 25, 2022
ONNX model with Jetson-Inference using GPU Jetson Xavier NX tensorrt , jetson-inference , onnx	38	5689	October 18, 2021
Getting an error while trying to use deepstream_launchpad.ipynb code DeepStream SDK deepstream	28	1372	January 10, 2024