How to set tlt-model-key on cpp deepstream-app sourcecode instead of config file

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hello everyone.
I am looking for a feature I thought I was going to find right away, but haven’t been able to find.
How do I set the tlt-model-key on a deepstream-app based application’s source code instead of setting it from config file or config_infer file?

I tryed to add it on deepstream_app_config_parser.c

config->primary_gie_config.tlt_model_key = "<My Secret Key>";

but it says that deepstream_app_config_parser.c:463:34: error: 'struct NvDsGieConfig' has no member named 'tlt_model_key'.

I could not find any documentation on NvDsGieConfig struct

Thank you!

3

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)

4

Hello @bcao, thank you for your answer
here is the info. Sorry for not posting it before.

• Hardware Platform (Jetson / GPU)
nvidia GPU
• DeepStream Version
5.1
• JetPack Version (valid for Jetson only)
• TensorRT Version
7.2.2
• NVIDIA GPU Driver Version (valid for GPU only)
460.39
• Issue Type( questions, new requirements, bugs)
question
• 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)

5

Thanks, I guess you cannot change the key from app level, the config “CONFIG_GROUP_INFER_TLT_MODEL_KEY” in gstnvinfer_property_parser.h is used in gstnvinfer. If you really don’t want it in config file, I think you can change the gstnvinfer source code.