How to avoid start-up delay in deepstream-app with YOLOv4


I have an application in which I run deepstream-app with YOLOv4 as the object detector on several small video files (around 0.5 s/ 30fps). I have noticed that each time there is around 3 s start-up delay associated with deepstream. I was wondering if there is any way I can circumvent this problem?


Hi, This looks like a deepstream issue. We recommend you to raise it to the respective forum.


I added DeepStream SDK to the categories. Thanks for your advice!

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• 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)

Sure, here are the relevant details:
Hardware Platform (Jetson / GPU) GPU T4
• DeepStream Version Deepstream sdk 5.0
• NVIDIA GPU Driver Version (valid for GPU only) 11.3
I am trying to do this for deepstream-app with YOLOv4 object detector.

Does it rebuild the TensorRT engine every bootup?
Did you set “model-engine-file=” in the DS config file?

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.