Can not get the output of frame_usr_meta_list in python but I can get it from C++

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson
• DeepStream Version 5.0
• JetPack Version (valid for Jetson only) 4.4
• TensorRT Version 7.0
• 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)
I am using deepstream pgie to perform text recongnition, but when I tried to use “l_user = frame_meta.frame_user_meta_list” to get the output tensor of engine in python, it turned out that the l_user is None. But surprisingly I can get it from C code with same config file!! How did that happen? Can someone help me?
Here are the python code, c code and config file.
config.txt (551 Bytes)
textRecongnition.c (18.5 KB) (13.7 KB)

Can you add some log to ensure the meta is added?

Thanks for your response, but I am a little confused about what meta you refered to and how can I add log. Looking forward to your response, thanks!

Why you need access the meta? Which module add the meta?

Because I want to build a text recongnition pipeline and I need to get the raw tensor from framemeta to do post process. The only nvinfer plugin pgie add the meta.

Please upgrade to DS6.0. nvinfer is open source plugin. Can you add log to ensure the meta data is added?

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