Passing user defined values to Custom Parse function

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) RTX 2060
• DeepStream Version 5.0
• JetPack Version (valid for Jetson only)
• TensorRT Version 7.1
• NVIDIA GPU Driver Version (valid for GPU only) 10.2
• Issue Type( questions, new requirements, bugs) Requirements
• 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 want to pass a value to Custom Object Detection function which I have implemented in library and configured in deepstream using parse-bbox-func-name and custom-lib-path.
I want to include some values dynamically here.
I am using the deepstream-test3 for reference.
How can I achieve that from deepstream_app.c

what type info you need to include, is the info from your customized post process parser?

Yes, some post processing values.

I am running multiple models on multiple input streams and I want to choose which values to choose dynamically here, so looking for a way to pass information from the main file to the custom library.

I think you can refer deepstream-infer-tensor-meta-test

I have written a custom parser function. This Parser function has to configure some parameters based on input stream,
The only input data I get here is through the function

extern “C” bool NvDsInferParseCustom(
std::vector const &outputLayersInfo,
NvDsInferNetworkInfo const &networkInfo,
NvDsInferParseDetectionParams const &detectionParams,
std::vector &objectList)

which gets called if I mention this in infer config file.
Suppose I want to send an unique id here at runtime how can I achieve that?

Currently I think you need to achieve that following deepstream-infer-tensor-meta-test.
Because you cannot pass the params like id you mentioned via current post parser function

hi, If I use non classification and non detection, then I set “network type = 100”. Is my definition of parsing function still like this

extern “C” bool NvDsInferParseCustom(
std::vector const &
outputLayersInfo , NvDsInferNetworkInfo const &networkInfo,
NvDsInferParseDetectionParams const &detectionParams,
std::vector &objectList)

Hi yueshangchang,

Please help to open a new topic for your issue. Thanks