Open ApdowJN opened 3 weeks ago
I have also encountered this situation, which seems to be the tetra nerf for triangulation not being successfully installed. I try reinstalling it, but in the # tetra nerf for triangulation step, after I run cmake . it reported an error as below, and I would greatly appreciate it if someone could provide a solution to help.
full text reads as follows:
CMake Error at /home/ywan/miniconda3/envs/gof113/share/cmake-3.26/Modules/CMakeDetermineCompilerId.cmake:751 (message): Compiling the CUDA compiler identification source file "CMakeCUDACompilerId.cu" failed.
Compiler: /usr/bin/nvcc
Build flags:
Id flags: --keep;--keep-dir;tmp -v
The output was:
255
PATH=/usr/lib/nvidia-cuda-toolkit/bin:/home/ywan/miniconda3/envs/gof113/bin:/home/ywan/miniconda3/bin:/home/ywan/miniconda3/condabin:/usr/local/cuda-11.7/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/usr/lib/wsl/lib:/mnt/c/Program Files/WindowsApps/CanonicalGroupLimited.Ubuntu20.04LTS_2004.6.16.0_x64__79rhkp1fndgsc:/mnt/c/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v11.8/bin:/mnt/c/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v11.8/libnvvp:/mnt/c/Windows/system32:/mnt/c/Windows:/mnt/c/Windows/System32/Wbem:/mnt/c/Windows/System32/WindowsPowerShell/v1.0:/mnt/c/Windows/System32/OpenSSH:/mnt/c/Program Files (x86)/NVIDIA Corporation/PhysX/Common:/mnt/c/Program Files/NVIDIA Corporation/NVIDIA NvDLISR:/mnt/c/WINDOWS/system32:/mnt/c/WINDOWS:/mnt/c/WINDOWS/System32/Wbem:/mnt/c/WINDOWS/System32/WindowsPowerShell/v1.0:/mnt/c/WINDOWS/System32/OpenSSH:/mnt/d/Program Files/MATLAB/R2022a/runtime/win64:/mnt/d/Program Files/MATLAB/R2022a/bin:/mnt/c/Program Files/Git/cmd:/mnt/c/Program Files/dotnet:/mnt/c/Program Files/NVIDIA Corporation/Nsight Compute 2022.3.0:/mnt/d/CMake/bin:/mnt/f/Anaconda:/mnt/f/Anaconda/Scripts:/mnt/f/Anaconda/Library/mingw-w64/bin:/mnt/f/Anaconda/Library/usr/bin:/mnt/f/Anaconda/Library/bin:/mnt/c/Program Files (x86)/Windows Kits/10/Windows Performance Toolkit:/mnt/c/Program Files/Microsoft Visual Studio/2022/Community/VC/Tools/MSVC/14.39.33519/bin/Hostx86/x86:/mnt/f:/mnt/f/Scripts:/mnt/c/Program Files/PowerShell/7:/mnt/c/Users/workstation/AppData/Local/Microsoft/WindowsApps:/mnt/d/App/PyCharm/installer/PyCharm Community Edition 2022.1/bin:/mnt/c/Users/workstation/.dotnet/tools:/mnt/d/Microsoft VS Code/bin:/snap/bin:/home/ywan/.pixi/bin
-DCUDACC -DNVCC -DCUDACC_VER_MAJOR=10 -DCUDACC_VER_MINOR=1 -DCUDACC_VER_BUILD=243 -include "cuda_runtime.h" -m64 "CMakeCUDACompilerId.cu" > "tmp/CMakeCUDACompilerId.cpp1.ii"
-ftz=0 -prec_div=1 -prec_sqrt=1 -fmad=1 --include_file_name "CMakeCUDACompilerId.fatbin.c" -tused -nvvmir-library "/usr/lib/nvidia-cuda-toolkit/libdevice/libdevice.10.bc" --gen_module_id_file --module_id_file_name "tmp/CMakeCUDACompilerId.module_id" --orig_src_file_name "CMakeCUDACompilerId.cu" --gen_c_file_name "tmp/CMakeCUDACompilerId.cudafe1.c" --stub_file_name "tmp/CMakeCUDACompilerId.cudafe1.stub.c" --gen_device_file_name "tmp/CMakeCUDACompilerId.cudafe1.gpu" "tmp/CMakeCUDACompilerId.cpp1.ii" -o "tmp/CMakeCUDACompilerId.ptx"
"tmp/CMakeCUDACompilerId.sm_30.cubin"
ptxas fatal : Value 'sm_30' is not defined for option 'gpu-name'
Call Stack (most recent call first): /home/ywan/miniconda3/envs/gof113/share/cmake-3.26/Modules/CMakeDetermineCompilerId.cmake:8 (CMAKE_DETERMINE_COMPILER_ID_BUILD) /home/ywan/miniconda3/envs/gof113/share/cmake-3.26/Modules/CMakeDetermineCompilerId.cmake:53 (__determine_compiler_id_test) /home/ywan/miniconda3/envs/gof113/share/cmake-3.26/Modules/CMakeDetermineCUDACompiler.cmake:307 (CMAKE_DETERMINE_COMPILER_ID) CMakeLists.txt:2 (project)
-- Configuring incomplete, errors occurred!
It seems that the 3090 does not support the old SM-30 architecture. I tried to adjust it in cmakelist.txt but so far it has not been successful yet
Hi, could you maybe check the solution here: https://github.com/autonomousvision/gaussian-opacity-fields/issues/52#issuecomment-2155320604
When I try python extract_mesh.py -m exp_playroom/release/ --iteration 30000, it shows issue below.
How to solve this problem? Has anyone meet this error?