Hello,
I am currently using TensorRT version 8.6.1 and TAO version 5.5.0. I would like to know if I can install the TAO Converter to convert my FPNet model. In the NVIDIA documentation, there is only mention of TensorRT version 8.4.
Thank you!
You can download from https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/resources/tao-converter/files.
wget --content-disposition 'https://api.ngc.nvidia.com/v2/resources/org/nvidia/team/tao/tao-converter/v5.1.0_8.6.3.1_x86/files?redirect=true&path=tao-converter' -O tao-converter
Thank you. I have downloaded this version, but I’m encountering an issue with tao-converter. When I try to run it, I get the following error:
./tao-converter: /lib/x86_64-linux-gnu/libc.so.6: version GLIBC_2.34 not found (required by ./tao-converter)
My current glibc version is 2.31, and upgrading it could cause issues with other applications on my system. Is there an alternative way to solve this problem?
From TAO5.0, you can get onnx file after exporting. If you are using .etlt from ngc, you can change it to onnx file. Refer to tao_toolkit_recipes/tao_forum_faq/FAQ.md at main · NVIDIA-AI-IOT/tao_toolkit_recipes · GitHub.
Then, use trtexec to generate tensorrt engine. Refer to TRTEXEC with Facial Landmarks Estimation - NVIDIA Docs.
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
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.