• Hardware Platform (Jetson / GPU): dPU A40. • DeepStream Version: 6.4-triton-multiarch. • TensorRT Version: 8.6.2.3. • NVIDIA GPU Driver Version (valid for GPU only): 525.147.05. • Issue Type( questions, new requirements, bugs): questions. • How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing) I am using DeepStream with Python, specifically the repository GitHub - marcoslucianops/DeepStream-Yolo: NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models to convert a YOLOv8x.pt model to ONNX for use in a single-class person detection pgie model. I’ve noticed significant differences in the results when comparing the model’s performance using Ultralytics for inference versus using DeepStream. In Ultralytics, I set the iou to 0.7 and the threshold to 0.5, and similarly in DeepStream, I set the nms-iou-threshold to 0.7 and the pre-cluster-threshold to 0.5. Am I configuring something incorrectly? Can you identify why there might be such a significant discrepancy in the results between the two methods? Below are the results of using ultralytics for inference: [204] And here is the result from deepstream: [Screenshot 2024-02-06 at 21.45.53] Here is the ultralytics code I am using for inference, config pgie deepstream, model pt and model onnx: yolov8 - Google Drive

Could you attach the original image to us? And how to run that with Ultralytics?

I uploaded everything to this link: yolov8 - Google Drive. 204_origin is the original image, 204_ultralytics is the inference image using ultralytics, 204_deepstream is the result I get when using deepstream and built_in_infer.py is the script for inference using ultralytics. Please help me, thank you very much.

@taolanhat were you able to find a solution for the issue? I’m having an identical issue using the following nvinfer config.

Found the following git issue from DeepStream-Yolo repository owner. Apparently, TensorRT drops the accuracies when converting model, particularly, during layer optimizations. The issue is still open and I couldn’t find any resolution in the shape of a fix, alternative or workaround.

Discrepancies in Object Detection Results between Ultralytics and DeepStream at Yolov8

Accelerated Computing Intelligent Video Analytics DeepStream SDK

yuweiw February 23, 2024, 5:32am 7

DId you implement the NvDsInferParseYolo yourself? We have summarized some experience in accuracy. Could you refer to the Debug Tips for DeepStream Accuracy Issue and check if that helps?

Topic		Replies	Views
Yolov8 and Yolov11 are giving wrong infer results on deepstream 8.0 on Ubuntu24 DeepStream SDK deepstream	3	217	February 13, 2026
Performance Gap between Deepstream YOLO and pytorch YOLO DeepStream SDK	3	1118	January 2, 2024
Performance Drop After Converting YOLO ReLU6 Model from ONNX to DeepStream: Causes and Solutions DeepStream SDK deepstream	7	460	February 24, 2025
Frustrating Problem with Custom Yolov8 on Deepstream DeepStream SDK camera , cuda , usb , python	5	1416	November 19, 2023
Accuracy issues in object detection models using Jetson AGX Orin DeepStream SDK yolo , deepstream , inception	8	1091	December 8, 2023
No detection for trained Yolo model on Deepstream 7.0.0 DeepStream SDK deepstream	3	220	August 12, 2025
Deepstream trained yolo3-tiny accuracy DeepStream SDK	4	848	June 2, 2020
Tensorrt YOLOv8 with deepstream python DeepStream SDK	10	2132	March 13, 2024
Yolov3 deepstream vs pytorch pipeline differences DeepStream SDK	4	627	August 1, 2022
Different result with custom tiny_yolo model in DeepStream vs cv2.dnn module DeepStream SDK	8	1293	November 22, 2019

Discrepancies in Object Detection Results between Ultralytics and DeepStream at Yolov8

Related topics