I have a scale problem on deepstream sgie:

if i use 608 608 on pgie and sgie, deepstream works well, but 1536 1536 on pgie and sgie, deepstream will be hung after 20-30 minutes, said scale problems on sgie!
pls give an advice to get it work normally,

thank you very much!

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)

my platform is jetson nx and deepstream5.1.

thank you

What does this mean? What have you set as “608” or “1536”?

it is for custom yolo model, trained by 608X608, or 1536X1536, or 412X412, like that.


It may be caused by SGIE. When the model dimension is 1536x1536 and the PGIE detects objects whose size is less than 256x256, the HW scaler can not scaling the object to the model size for the HW limitation(Jetson HW can only scale 1/16 to 16 ratio). Please avoid such configuration.

ok get it.
thank you very much!

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