Error when trying to parse Triton output tensor on multistream input

[casetiadharma]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.2
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.5.2.2
• NVIDIA GPU Driver Version (valid for GPU only) 525.85.12
• 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)

When I am trying to parse my triton custom ensemble model following the deepstream-ssd-parser example , I can do it just fine with one video stream.

However, when i am trying to do the same with multiple stream, I am getting this error.

Please advise on how to parse output tensor from custom ensemble model on multistream input.

[fanzh]

could you share the media pipeline? could you share the configuration file? and you might check the nvinferserver code because it is opensource from DS6.2.

[casetiadharma]

infer_config.txt (1.7 KB)
deepstream_pipeline.py (8.7 KB)

@fanzh Here is my pipeline and infer config file.

Previously when it was only a single stream, I managed to parse my triton ensemble output using the output tensor metadata, so I am looking for a similar way to do it with multistream. Thanks in advance

[fanzh]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

there are a lot of custom code in deepstream_pipeline.py, can you simplify it? and please refer to deepstream_test_3.py, which can accept multiple inputs, you only need to port this code multiple sources