How to generate box location base on the frame weight/height in the postprocess api?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) gpu
• DeepStream Version 5.0.0
• JetPack Version (valid for Jetson only)
• TensorRT Version 7.0.0
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs) questions
• 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)
hi,
I have a detector model that i want to use in deepstream. I checked the postprocess api like:

image
image957×853 42.7 KB

and
image
image700×248 11.7 KB

i found that in those api I can not get neither width/height of input frame nor the sacle factor, all the demo just get the location box based on the model input width/height, since I hand a sencondary model to do classifer , so How can I get the box location based on the frame weight/height ?

3

I also checked the code of deepstream-test2 which has sgie but without custom postprocess func. I guess deepstream will do the transform after calling the custom postprocess. Its’ right?

4

any useful info or hint for me ？

5

Sorry for the delay, you can refer gstnvinfer_meta_utils.cpp → attach_metadata_detector for how nvinfer pluin handle the frame info.

1 Like
6

ok, let me check, anyway thx!