Hardware Platform：jetson orin nano 4G DeepStream Version ：6.2 I use DeepStream YOLO to quantify the YOLOv5S INT8 model, and the theoretical fps can reach 120. When I run the YOLOv5 object detection model with 4 RTSP streams in DeepStream, the running delay increases and the image becomes distorted…

Whenever I had the distortion issue, using rtspt:// (TCP) instead of rtsp:// in the URI fixed the issue.

@Fiona.Chen Right, min=1, opt=4, max=8

Why did you set the nvinfer batch size as 1?

@Fiona.Chen I realized this morning that I had originally intended to set the batch size of nvinfer to num_rtp. I conducted another experiment this morning and changed the batch size of nvinfer to num_rtp. However, I found that the inference time was still too long. I will share the report with you…

The postprocessing seems CPU version, have you tested the performance of the postprocessing? The GitHub - marcoslucianops/DeepStream-Yolo: NVIDIA DeepStream SDK 7.1 / 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models is not provided by Nvidia, we does not guaran…

What is the original FPS of your RTSP sources? Are they all TCP protocol? Have you set enough latency with rtspsrc?

@Fiona.Chen My RTSP stream has a maximum FPS of 25 and uses nvurisrcbin for decoding. The specific parameters are as follows： g_object_set(G_OBJECT(uri_decode_bin), "uri", uri, NULL); g_object_set(G_OBJECT(uri_decode_bin), "rtsp-reconnect-interval", 60, NULL); g_object_set(G_OBJECT(uri_decode_bin)…

@Fiona.Chen In Nsight log: batch size =1 queueInput max Duration=16.180ms batch size =2 queueInput max Duration=324.4ms batch size =4 queueInput max Duration=622.355ms I found that most of the time is spent on a certain node in TensorRT, as shown in the following figure [image] But these la…

@Fiona.Chen The purpose of my inspection is that my deepstream application has latency and distortion, and GST_DEBUG=3 keeps displaying <nvv4l2decoder0>Decoder is producing too many buffers. I used the above model to theoretically infer more than 100 frames per second, but in my application, I con…

[image] LFYTMLY: I used the above model to theoretically infer more than 100 frames per second, but in my application, As I have explained above, the inferencing performance is decided by the “preprocess+inference+postprocess” speed. Seems the “preprocess+inference+postprocess” speed can’t r…

Analyzing latency using Nsight systems in deepstream

Accelerated Computing Intelligent Video Analytics DeepStream SDK

Fiona.Chen April 10, 2025, 6:47am 28

It is inside gst-nvinfer. The gst-nvinfer plugin is open source. The source code is in /opt/nvidia/deepstream/deepstream/sources/libs/nvdsinfer and /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvinfer. There is also source code diagram for your reference. DeepStream SDK FAQ - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums

Topic		Replies	Views
How to improve the performance of pipelines in deepstream DeepStream SDK deepstream	25	789	October 21, 2025
Inference with deepstream yolov5s-3.0 on 2 camera long delay (20-25s) DeepStream SDK	17	2713	March 17, 2021
DeepStream deepstream with rtsp stream, 3s latency DeepStream SDK	8	2678	August 3, 2021
How to test the pipeline latency of deepstream test3? DeepStream SDK deepstream	10	279	May 23, 2025
Deepstream multiple rtsp output latency DeepStream SDK	1	770	November 10, 2022
Model ran much slower in deepstream pipeline DeepStream SDK	1	851	October 15, 2020
Deepstream-app latency increasing DeepStream SDK	11	2900	June 18, 2020
High latency in Deepstream pipeline DeepStream SDK nvbugs , deepstream	7	411	March 30, 2026
Some question about Deep stream 5 DeepStream SDK	41	2761	November 7, 2020
Facing Glitches RTSP using my deepstream app DeepStream SDK rtsp , jetson-inference , gstreamer , jetson , deepstream	16	679	January 14, 2025

Analyzing latency using Nsight systems in deepstream

Related topics