My project is based on Deepstream-test2 modifications Pipeline flow: appsrc ! h264parse ! nvv4l2decoder ! nvstreammux ! nvinfer ! nvtracker ! nvvidconv ! nvdsosd ! nvvideoconvert ! video/x-raw(memory:NVMM),format=I420 ! nvv4l2h264enc ! video/x-h264,stream-format=byte-stream ! h264parse ! flvmu…

If you run the yolo model, please refer to the yolo_deepstream . You need to implement your own post-processing function like: nvdsinfer_custom_impl_Yolo .

The relevant configuration has been introduced in the configuration file : parse-bbox-func-name: NvDsInferParseYolo custom-lib-path: ../libnvdsinfer_custom_impl_Yolo.so engine-create-func-name: NvDsInferYoloCudaEngineGet

好的，等测完后我尝试一下

Hello, I have no abnormalities during the operation, but the device is powered off root@nvidia-desktop:~/DeepStream-Yolo-master# deepstream-app -c deepstream_app_config.txt Opening in BLOCKING MODE DEBUG: [TRT]: Registered plugin creator - ::BatchedNMSDynamic_TRT version 1 DEBUG: [TRT]: Register…

Could you refer to the link below and get the changes of memory when it’s running? https://forums.developer.nvidia.com/t/deepstream-sdk-faq/80236/14

Can you also collect log from “tail -f /var/log/syslog”? In the meanwhile please open another console to collect the output of “sudo tegerastats” to check the power consumption of the Orin module. AGX Orin module doesn’t have 16G version, are you using Orin NX? And what’s your Jetpack version?

terminal-log.txt (42.8 KB) Here is my memory usage

syslog.log (6.2 KB) Distribution： ubuntu 20.04 focal Python ： 3.8.10 CUDA：11.4.315 cuDNN ：8.6.0.166 TensorRT ：8.5.2.2 VPI：2.2.7 OpenCV：4.5.4 Model：NVIDIA Orin NX Developer Kit Module：NVIDIA Jetson Oriin NX(16GB ram) Jetpack：5.1.1 DeepStream: 6.2

Is this the log before shutdown happened? Please also check the output of “sudo tegrastats” to check the power consumption.

Hello, I use YoloV8 on my Orin 16G device The converted model automatically shuts down after running for a while

Accelerated Computing Intelligent Video Analytics DeepStream SDK

yuweiw July 20, 2023, 5:27am 5

OK. Could you help to debug where it got stuck? You can open some nvinfer log by referring https://forums.developer.nvidia.com/t/deepstream-sdk-faq/80236/33.

Topic		Replies	Views
Yolov7 model run stuck on deepstream by 640*640 inputs of Orin NX DeepStream SDK jetson , deepstream	5	210	December 24, 2024
Yolov8 on Orin NX with Jetpack 5.1.2 DeepStream SDK tensorrt , yolo , deepstream	2	308	December 5, 2024
Application Migration from Jetson Orin NX(16G) to Jetson Orin NX Super(16G) Jetson Orin NX cuda , deepstream , jetson-orin	45	1208	June 30, 2025
How to resolve 'System Throttled Due to Overcurrent' Issue and Increase Concurrent Streams on Custom YOLOv8 Model on Jetson AGX Orin? DeepStream SDK tensorrt , jetson-inference	7	361	September 3, 2024
Using custom model in deepstream DeepStream SDK jetson-inference , python , deepstream	39	985	September 10, 2024
Deepstream with triton is stuck and not outputting anything DeepStream SDK inference-server-triton , inception	4	1177	September 19, 2022
AI NVR configuration issues with DeepStream 7.1 and YOLOv8 on Jetson Orin NX Metropolis Microservices for Jetson jetson , deepstream , jetson-platform-services	7	536	January 13, 2025
Yolov7 Deepstream application won't start DeepStream SDK	13	1062	December 20, 2022
Tactic Device request: 250MB Available: 6MB. Device memory is insufficient to use tactic DeepStream SDK deepstream	4	116	April 8, 2026
Deepstream-App not working on Jetson Orin Nanod DeepStream SDK tensorrt , gstreamer , jetson , deepstream	2	153	May 13, 2025

Hello, I use YoloV8 on my Orin 16G device The converted model automatically shuts down after running for a while

Related topics