Jinwoo Kim

Thank you for responding to my question. I found the image from issue #14, and this paper. (Gopinathan, M., Truong, G., & Abu-Khalaf, J. (2021). Indoor Semantic Scene Understanding using...

This worked for me in melodic (from [link](https://answers.ros.org/question/344951/could-not-find-the-following-boost-libraries-boost_python3/)). If it already exists, then remove it with sudo rm -rf and try again. ``` cd /usr/lib/x86_64-linux-gnu sudo ln -s libboost_python3.a libboost_python37.a...

> > This worked for me in melodic (from [link](https://answers.ros.org/question/344951/could-not-find-the-following-boost-libraries-boost_python3/)). If it already exists, then remove it with sudo rm -rf and try again. > > ``` > > cd...

There's an error in the last commit. I used the previous commit and it worked well. Try the commit 30dac933e540c3c08052dc62c51f55e803df8dac. ``` git checkout 30dac933e540c3c08052dc62c51f55e803df8dac ```

I'm using CUDA12.2 and CUDA12.6, used `export SPCONV_CUDA_VERSION=12.8` option and it worked. I guess it works for all CUDA12 versions. Try with `export SPCONV_CUDA_VERSION=12.8` in tool/environment.sh

There's a document related to converting the model to onnx from the pth file here. https://github.com/NVIDIA/DL4AGX/tree/master/AV-Solutions/vad-trt