I have just downloaded deepstream 6 and I am having some performance issues running the YOLO example I have been trying to run the YOLO example app in deepstream 6 and the video performance is extremely slow. When I run the example on my Xavier NX with deepstream 5.0 it runs around 56fps The same file running on same NX with deepstream 6.0 runs around 6 fps Here is a video to explain: [Deepstream 6 Yolo performance issues]

I can reproduce this issue. We are checking it, will get back to you ASAP. Thanks!

I know you guys are busy But Any updates?

Hi @adventuredaisy , We are checking this with priority. So far, we have found the inference time of some layers are much longer on DS6.0GA than DS5.1, we are working for the fix.

Thanks for the update I know you guys will win the day!

How’s the fix coming? Is there a timetable for when It will be rolled out.?

Hey guys I know you are working on the issue. But I am dead in the water with DS6 when it comes to updating my YOLO projects from DS5.1 to Deepstream 6. Just wondering when a fix would be coming out. Thanks Joe Valdivia

Noted! Sorry! Still wroking on it… will get back to you ASAP

Hi @adventuredaisy , This issue is still under debugging, it may be related to the nvdsinfer_custom_impl_Yolo/trt_utils.cpp which build the TensorRT model from the cfg file. If this is urgent for you, is it possible for you to try TAO Yolov3 network - GitHub - NVIDIA-AI-IOT/deepstream_tao_apps: Sample apps to demonstrate how to deploy models trained with TAO on DeepStream ?

Thanks for the update. I’m not in any bind at the moment. I thought I would explore Omniverse Issac sim in the meantime. Kind of excited about the Synthetic data generator that’s coming out.

Deepstream 6 YOLO performance issue

Accelerated Computing Intelligent Video Analytics DeepStream SDK

mchi December 1, 2021, 4:39am 22

Hi All,
Sorry for long delay!

Attached the fix for this perf regression issue. Verified on my side.

$ cd /opt/nvidia/deepstream/deepstream-6.0/sources/objectDetector_Yolo/
$ patch -p1 < DS6.0GA_objectDetector_Yolo_perf_regression.patch
$ export CUDA_VER= // specify the CUDA version, e.g. export CUDA_VER=11.4
$ make -C nvdsinfer_custom_impl_Yolo

DS6.0GA_objectDetector_Yolo_perf_regression.patch (2.5 KB)

Thanks!

Deepstream 6.0 Python Yolo bad performance

DeepStream 5 vs 6 inference time and calculate fps in the pipeline on Jetson Nano

Yolo V3 slow

The FPS of USB camera based tracking app is a lot slower than the MP4 format

Deepstream 6 on Xavier NX detection performance issues

DeepStream 5 vs 6 inference time and calculate fps in the pipeline on Jetson Nano

Topic		Replies	Views
Deepstream 6.0 Python Yolo bad performance DeepStream SDK	7	1858	December 8, 2021
Significant slowdown after DeepStream v6.2 DeepStream SDK	10	435	July 23, 2024
Deepstream 6 on Xavier NX detection performance issues DeepStream SDK	8	1129	April 21, 2022
App Run Fails With Errors DeepStream SDK jetson-inference , yolo , debugging-and-troubleshooting	27	2672	October 9, 2023
Yolov4 perf deepstream 6.0 DeepStream SDK	8	1403	February 22, 2022
PERF issues with DeepStream6.2 + YOLOv8 in Jetson Xavier DeepStream SDK jetson-inference , performance , yolo , fps , deepstream	7	1340	September 26, 2023
DeepStream 5 vs 6 inference time and calculate fps in the pipeline on Jetson Nano DeepStream SDK	8	3190	December 31, 2021
Yolo V3 slow DeepStream SDK yolo	22	3340	December 27, 2021
Jetson xavier nx deepstream Yolov5 DeepStream SDK camera , cuda , gstreamer	7	1488	March 10, 2023
Detections change in Deepstream 6.2 DeepStream SDK tensorrt , camera , cuda , kernel , gstreamer , yolo , python , deepstream , deepstream61	21	2278	July 31, 2023

Deepstream 6 YOLO performance issue

Related topics