please refer to this topic and my last comment. you need to copy https://github.com/marcoslucianops/DeepStream-Yolo/blob/master/config_infer_primary_yoloV8.txt and nvdsinfer_custom_impl_Yolo to Python deepstream_test1.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How to Increase FPS on Jetson Xavier NX for Real-Time AI & Video Processing? | 6 | 187 | October 9, 2025 | |
| Nvidia Jetson NX extremely slow even with TensorRT inference for yolov3 | 21 | 2847 | October 18, 2021 | |
| Our yolov5s TensorRT 8 version can work well on Nano but cannot work well on NX | 3 | 709 | December 9, 2021 | |
| Issues with deepstream object detection model and inference on Jetson NX Xavier | 10 | 713 | April 28, 2023 | |
| PERF issues with DeepStream6.2 + YOLOv8 in Jetson Xavier | 8 | 1139 | September 26, 2023 | |
| Crash bug of running the deepstream and performance optimization issues on jetson xavier NX | 4 | 738 | November 23, 2023 | |
| Predictions on Jetson Xavier NX wrong while working on NVIDIA T1000 laptop gpu | 6 | 698 | January 30, 2023 | |
| Deepstream - Jetson Xavier NX - Mode int8 | 10 | 1056 | October 12, 2021 | |
| Jetson Xavier NX yolov4 benchmark | 4 | 1571 | October 18, 2021 | |
| Nvidia Jetson NX extremely slow even with TensorRT inference for yolov3 | 3 | 1279 | August 23, 2021 |