Description Hi, I’m currently running inference with deepstream yolov5s-3.0 on 2 camera IP on a jetson nano 4GB and its runs with a long delay. Here you can see the log [Screenshot from 2021-03-12 14-04-03] I saw that the jetson nano can handle multiple IP camera with full FPS. I have 20 seconds…

Could you refer to GitHub - NVIDIA-AI-IOT/deepstream_tao_apps: Sample apps to demonstrate how to deploy models trained with TAO on DeepStream to measure the trtexec perf of yolov5 on NANO?

Here is the result : Warmup completed 1 queries over 200 ms [03/15/2021-09:43:56] [I] Timing trace has 10 queries over 0.873358 s [03/15/2021-09:43:56] [I] Trace averages of 10 runs: [03/15/2021-09:43:56] [I] Average on 10 runs - GPU latency: 85.5117 ms - Host latency: 85.9994 ms (end to end 87.…

this should be the perf of batch-size=1, so, the inference time is ~ 86ms / frame with batch-size=1. you could try below command to batch-size=2, I guess the inference time / batch will be double since yolov5 with batch-size=1 should already fully use NANO GPU. $ ./trtexec --loadEngine=/opt/nvid…

here the result with batch of 2 [03/15/2021-11:12:58] [I] Average on 10 runs - GPU latency: 0.000634766 ms - Host latency: 0.951318 ms (end to end 0.961865 ms, enqueue 0.138208 ms) [03/15/2021-11:12:58] [I] Average on 10 runs - GPU latency: 0.00065918 ms - Host latency: 0.997388 ms (end to end 1.3…

the latency of batch-size=2 is much less than that of batch-size=1, looks there is problem with batch-size=2. Where and how did you observe 15 or 20 second latency?

When I run the detection on the cameras, there is a delay of 20s between the reality and the display window. With 1 or 2 cameras it is the same In the console it shows 6 FPS for each camera but in the display window it is showing with more than 30s delay

6FPS makes sense. As per previous test, bs=1, infer time = 86ms, then bs=2, infer time = ~ 2 x 86 = 176ms, so fps = 1000 / 176 = 5.7 fps

Is the performance normal ? I saw that with some model you can have full fps: [DeepStream on Jetson Nano] And why there is a delay between the display window and the reality ?

[image] constantin.fite: Is the performance normal ? I saw that with some model you can have full fps: This seriously depends on the model you use. Different model requires different compute caability. The video you shared is based on some more lightweight video. why there is a delay betwee…

you can try set batched-push-timeout in group [streammux] from 40000 to 20000 or lower , and run again

Inference with deepstream yolov5s-3.0 on 2 camera long delay (20-25s)

Accelerated Computing Intelligent Video Analytics DeepStream SDK

mchi March 17, 2021, 3:05pm 21

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

HI @constantin.fite ,
Could you refer to DeepStream SDK FAQ - #12 by bcao to capture the DS component and pipeline latency log?

Topic		Replies	Views
Inference with deepstream yolov5s-3.0 on 2 camera long delay (20-25s) TensorRT jetson-inference	3	721	March 12, 2021
DeepStream 5 vs 6 inference time and calculate fps in the pipeline on Jetson Nano DeepStream SDK	8	3146	December 31, 2021
There is a delay between the RTSP video stream output by Deepstream and the source RTSP video stream DeepStream SDK	9	1617	March 10, 2021
Analyzing latency using Nsight systems in deepstream DeepStream SDK jetson , deepstream	29	699	April 14, 2025
DeepStream Jetson nano Yolo v3 tiny DeepStream SDK	2	995	November 7, 2019
Deepstream fps DeepStream SDK cudnn , jetson , deepstream , jetson-nano , jetson-orin	4	277	July 1, 2025
How to improve the performance of pipelines in deepstream DeepStream SDK deepstream	25	775	October 21, 2025
Deepstream-app latency increasing DeepStream SDK	11	2892	June 18, 2020
Delay due to nvinfer DeepStream SDK deepstream	11	286	February 25, 2025
Delay gathered over time DeepStream SDK	14	1246	June 19, 2023

Inference with deepstream yolov5s-3.0 on 2 camera long delay (20-25s)

Related topics