Please provide complete information as applicable to your setup. • Hardware Platform (Jetson / GPU) GPU • DeepStream Version Docker 6.3 • JetPack Version (valid for Jetson only) • TensorRT Version • NVIDIA GPU Driver Version (valid for GPU only) • Issue Type( questions, new requirements, bugs) • 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) • Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description) When I am using deepstream-app or deepstream-parallel-infer-app, I want to get the elapsed time of each model, such as video decoding elapsed time, detection model elapsed time, classification model elapsed time, what should I do to get it? Meanwhile, for single-source multi-model (detection model + classification model), how do the detection model and classification model schedule the GPU resources? (50% occupied by detection models and 50% by classification models？)

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks [image] Pedestrian_Z: What should I do to get the latency of each plugin? There is a print of each component on the image you posted earlier. Like Comp name = .... We has no limitations about the resource. It limited by the hardware and some processing of the plugins.

You can refer to the FAQ:https://forums.developer.nvidia.com/t/deepstream-sdk-faq/80236/12.

Thanks for your reply, I get the latency time successfully, I want to konw what are the units of component latency (ms or s)? When I add [source 0] num-sources 1–> 16, batch-num = fram-num → batch-num ≠ fram-num. What is the relationship between batch-num and frame-num? [image] And for pgie and secondary-gie or different secondary-gie, how do they allocate GPU resources?

[image] Pedestrian_Z: I want to konw what are the units of component latency (ms or s)? ms. [image] Pedestrian_Z: And for pgie and secondary-gie or different secondary-gie, how do they allocate GPU resources? About this question, you can refer to our source code directly. source code: sources\gst-plugins\gst-nvinfer diagram： https://forums.developer.nvidia.com/t/deepstream-sdk-faq/80236

Thanks, I will try it later. The BATCH-NUM shown in the terminal, can I understand it as a batch coming out of gst-nvstreammux？And when decoding sources at the same time, different sources have different frames, is because of Gst-Nvstreammux? [image] And when I run the follow command: export NVDS_ENABLE_COMPONENT_LATENCY_MEASUREMENT=1 export NVDS_ENABLE_LATENCY_MEASUREMENT=1 the FPS is display on the terminal, how could I do to display it, by the way, the follow command is openning [application] enable-perf-measurement=1 perf-measurement-interval-sec=1

When Frame_num =1441, Frame_latency = 531ms, the displayed omponent latency’s add up to equal 138ms, I want to know what is the remaining elapsed time used for? Looking forward to your reply, thanks.

Which config file did you run? How did you calculate the total latency? Could you attach the config file and the log file?

cd /opt/nvidia/deepstream/deepstream-6.3/samples/configs/deepstream-app export NVDS_ENABLE_COMPONENT_LATENCY_MEASUREMENT=1 export NVDS_ENABLE_LATENCY_MEASUREMENT=1 deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt num-sources = 1: The config file is the original config file, I didn’t make any changes to it. num-sources = 16: nothing to do except change all batch-size = 1 → 16 I’m loading the video stream as a local file, is that why?

I know, I’ve exported the pipeline and I can see that there are many more plugins in there, also, I’ve found many more in… /deepstream/lib/gst-plugins as well. [图片] Could I understand that when sources go into the whole piepeline, the all green elements in the pipeline below are re-run at every frame, like GstTees, GstQueue, Gstnvvideoconvert? [图片] Meanwhile, when I run deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt, I’ve seen classifiers take only about 0.01ms of elapsed time, I thinks it is very amazing!

Yes. This graph shows the flowchart of each buffer. The performace of hardware acceleration processing is indeed fast.

Could I get the time spent by each module in the deepstream-app or deepstream-parallel-inference-app runtime?

Accelerated Computing Intelligent Video Analytics DeepStream SDK

yuweiw November 10, 2023, 7:12am 10

No. You can refer to the link Generate GStreamer Pipeline Graph to get the graph of the pipeline. You can find that in addition to a few plugins that printed, there are also many other plugins in the whole pipeline.

Topic		Replies	Views
The most efficient method to evaluate time each plugin (in DeepStream)cost? DeepStream SDK	7	1488	August 10, 2021
Latency measure for every frame DeepStream SDK	13	1377	January 17, 2024
Measuring DeepStream pipeline latency DeepStream SDK	6	2954	April 26, 2020
Fame latencty DeepStream SDK	6	1022	March 30, 2023
How to test the pipeline latency of deepstream test3? DeepStream SDK deepstream	10	322	May 23, 2025
The time it takes for the model to process each frame of the image DeepStream SDK deepstream	5	254	September 18, 2024
How to improve the performance of pipelines in deepstream DeepStream SDK deepstream	25	885	October 21, 2025
Latency measurement issue DeepStream SDK	3	1382	May 13, 2020
Measuring Frame and Element wise latency DeepStream SDK	11	728	June 13, 2023
Analyzing latency using Nsight systems in deepstream DeepStream SDK jetson , deepstream	29	793	April 14, 2025

Could I get the time spent by each module in the deepstream-app or deepstream-parallel-inference-app runtime?

Related topics