Pgie creation with nvinferserver doesn't work

[mikelmujika11]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) NVIDIA GeForce RTX 3090
• DeepStream Version 6.3
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.6.1.6
• NVIDIA GPU Driver Version (valid for GPU only) 535.113.01
• 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) I am interested on using the NVIDIA® Triton Inference Server along with DeepStream. I have tried running the python sample deepstream-rtsp-in-rtsp-out but when selecting the nvinferserver option the pgie can’t be created:

I haven’t made any changes in the code and I have followed the instructions that the README tells:

Do I have to do something else?

Thank you,

Mikel

[fanzh]

please install the libs according to the readme. what is the start command-line? seems creating nvinfer/nvinferserver plugin failed, could you share the result of “ldd /opt/nvidia/deepstream/deepstream/lib/gst-plugins/libnvdsgst_inferserver.so” and “ldd /opt/nvidia/deepstream/deepstream/lib/libnvds_infer_server.so” ?

[mikelmujika11]

The “ldd /opt/nvidia/deepstream/deepstream/lib/gst-plugins/libnvdsgst_inferserver.so” result:

And the result of “ldd /opt/nvidia/deepstream/deepstream/lib/libnvds_infer_server.so”:

Seams like the tritonserver lib is not installed. How should I install it?

[fanzh]

please refer to /opt/nvidia/deepstream/deepstream/samples/configs/deepstream-app-triton/README. you can use DeepStream triton docker.

[mikelmujika11]

So I should run, deepstream-app -c inside the triton docker?

[fanzh]

yes, in DeeStream triton docker, all triton libs are already installed.