Secondary inference using IInferCustomProcessor: How to access to ObjectMeta?

[ta.sugiyama]

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU) : dGPU
**• DeepStream Version : 6.0.1
**• JetPack Version (valid for Jetson only) : None
**• TensorRT Version : 8.0.1
**• NVIDIA GPU Driver Version (valid for GPU only) : 495.29.05
**• 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) : None
**• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description) : None

---

I want to implement secondary-inference and metadata-attaching using IInferCustomProcessor(nvinferserver),
but I can not access to ObjectMeta in inferenceDone().

I checked nvdsinferserver_custom_process.cpp but couldn’t figure out how.

I found OPTION_NVDS_OBJ_META_LIST in the header but
inOptions->hasValue(OPTION_NVDS_OBJ_META_LIST) returns false in my experiment.

[ta.sugiyama]

It seems that inOptions->getValueArray(OPTION_NVDS_FRAME_META_LIST, frameMetaList) returns ObjectMeta* instead of FrameMeta* in the case of secondary inference.

I can access to ObjectMeta and my problem is solved for now.

But this behavior is of an unexpected kind.
It would be nice if the behavior were documented or corrected.

[kayccc]

Glad to know issue fixed, will forward the comments to internal to improve it. Thanks