Deepstream libnvds_infercustomparser_tao.so

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Jetson Nx Orin
**• DeepStream 6.3 **
• JetPack Version vidia-jetpack-dev (= 5.1.3-b29)
**• TensorRT Version: libnvinfer-bin 8.5.2-1+cuda11.4 **

• Issue: I had a libnvds_infercustomparser_tao.so file for my app in Jetson Orin Nano. Now I have switched to Jetson Orin

How can I rebuild the right libnvds_infercustomparser_tao.so file again? i cannot find where to compile it. It was in one of the Tao examples I guess. how can I rebuild it for my hardware??

**• How to reproduce the issue ? **
Just switching from Jetson Orin to Jetson Nx caused it but probably the Tensorrt version or other libraries were also a new version. I need to compile .so files according the libraries in my new setup.#

• Deepstream 6.3 I need the custom ser for my custom trained yolo tiny v4 model

Thanks

3

Do you mean this shared library ? This is not part of deepstream sdk, just part of deepstream_tao_app

git clone https://github.com/NVIDIA-AI-IOT/deepstream_tao_apps.git

cd deepstream_tao_apps/post_processor

make CUDA_VER=11.4 install
4

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

5

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.