search

threestudio-project / threestudio

A unified framework for 3D content generation.
Apache License 2.0
6.32k stars 480 forks source link

【tinycudann error】tinycudann_bindings/_70_C.cpython-38-x86_64-linux-gnu.so: undefined symbol: cuMemAddressFree #277

Closed Bitterdhg closed 1 year ago

Bitterdhg commented 1 year ago

problem

1. Environment

2. How I installed tinycudann

2.1

git clone --recursive https://github.com/nvlabs/tiny-cuda-nn
cd bindings/torch
python setup.py install

2.2 log

setup.py:5: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html
  from pkg_resources import parse_version
Building PyTorch extension for tiny-cuda-nn version 1.7
Obtained compute capability 70 from PyTorch
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Sep_21_10:33:58_PDT_2022
Cuda compilation tools, release 11.8, V11.8.89
Build cuda_11.8.r11.8/compiler.31833905_0
Detected CUDA version 11.8
Targeting C++ standard 17
running install
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/setuptools/_distutils/cmd.py:66: SetuptoolsDeprecationWarning: setup.py install is deprecated.
!!

        ********************************************************************************
        Please avoid running ``setup.py`` directly.
        Instead, use pypa/build, pypa/installer or other
        standards-based tools.

        See https://blog.ganssle.io/articles/2021/10/setup-py-deprecated.html for details.
        ********************************************************************************

!!
  self.initialize_options()
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/setuptools/_distutils/cmd.py:66: EasyInstallDeprecationWarning: easy_install command is deprecated.
!!

        ********************************************************************************
        Please avoid running ``setup.py`` and ``easy_install``.
        Instead, use pypa/build, pypa/installer or other
        standards-based tools.

        See https://github.com/pypa/setuptools/issues/917 for details.
        ********************************************************************************

!!
  self.initialize_options()
running bdist_egg
running egg_info
writing tinycudann.egg-info/PKG-INFO
writing dependency_links to tinycudann.egg-info/dependency_links.txt
writing top-level names to tinycudann.egg-info/top_level.txt
reading manifest file 'tinycudann.egg-info/SOURCES.txt'
writing manifest file 'tinycudann.egg-info/SOURCES.txt'
installing library code to build/bdist.linux-x86_64/egg
running install_lib
running build_py
running build_ext
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/utils/cpp_extension.py:398: UserWarning: There are no g++ version bounds defined for CUDA version 11.8
  warnings.warn(f'There are no {compiler_name} version bounds defined for CUDA version {cuda_str_version}')
building 'tinycudann_bindings._70_C' extension
Emitting ninja build file /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/9] c++ -MMD -MF /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/dependencies/fmt/src/os.o.d -pthread -B /home/bitterdhg/anaconda3/envs/threestudio_py38/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/tools/util/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/TH -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/include/python3.8 -c -c /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/src/os.cc -o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/dependencies/fmt/src/os.o -std=c++17 -DTCNN_PARAMS_UNALIGNED -DTCNN_MIN_GPU_ARCH=70 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_70_C -D_GLIBCXX_USE_CXX11_ABI=0
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
[2/9] c++ -MMD -MF /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/dependencies/fmt/src/format.o.d -pthread -B /home/bitterdhg/anaconda3/envs/threestudio_py38/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/tools/util/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/TH -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/include/python3.8 -c -c /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/src/format.cc -o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/dependencies/fmt/src/format.o -std=c++17 -DTCNN_PARAMS_UNALIGNED -DTCNN_MIN_GPU_ARCH=70 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_70_C -D_GLIBCXX_USE_CXX11_ABI=0
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
[3/9] /usr/local/cuda/bin/nvcc  -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/tools/util/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/TH -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/include/python3.8 -c -c /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/src/object.cu -o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/src/object.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -std=c++17 --extended-lambda --expt-relaxed-constexpr -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -Xcompiler=-Wno-float-conversion -Xcompiler=-fno-strict-aliasing -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70 -DTCNN_PARAMS_UNALIGNED -DTCNN_MIN_GPU_ARCH=70 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_70_C -D_GLIBCXX_USE_CXX11_ABI=0
/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

[4/9] /usr/local/cuda/bin/nvcc  -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/tools/util/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/TH -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/include/python3.8 -c -c /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/src/common_host.cu -o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/src/common_host.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -std=c++17 --extended-lambda --expt-relaxed-constexpr -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -Xcompiler=-Wno-float-conversion -Xcompiler=-fno-strict-aliasing -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70 -DTCNN_PARAMS_UNALIGNED -DTCNN_MIN_GPU_ARCH=70 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_70_C -D_GLIBCXX_USE_CXX11_ABI=0
/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

[5/9] /usr/local/cuda/bin/nvcc  -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/tools/util/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/TH -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/include/python3.8 -c -c /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/src/network.cu -o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/src/network.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -std=c++17 --extended-lambda --expt-relaxed-constexpr -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -Xcompiler=-Wno-float-conversion -Xcompiler=-fno-strict-aliasing -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70 -DTCNN_PARAMS_UNALIGNED -DTCNN_MIN_GPU_ARCH=70 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_70_C -D_GLIBCXX_USE_CXX11_ABI=0
/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

[6/9] /usr/local/cuda/bin/nvcc  -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/tools/util/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/TH -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/include/python3.8 -c -c /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/src/cpp_api.cu -o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/src/cpp_api.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -std=c++17 --extended-lambda --expt-relaxed-constexpr -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -Xcompiler=-Wno-float-conversion -Xcompiler=-fno-strict-aliasing -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70 -DTCNN_PARAMS_UNALIGNED -DTCNN_MIN_GPU_ARCH=70 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_70_C -D_GLIBCXX_USE_CXX11_ABI=0
/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

[7/9] c++ -MMD -MF /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/tinycudann/bindings.o.d -pthread -B /home/bitterdhg/anaconda3/envs/threestudio_py38/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/tools/util/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/TH -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/include/python3.8 -c -c /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/tinycudann/bindings.cpp -o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/tinycudann/bindings.o -std=c++17 -DTCNN_PARAMS_UNALIGNED -DTCNN_MIN_GPU_ARCH=70 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_70_C -D_GLIBCXX_USE_CXX11_ABI=0
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/csrc/Exceptions.h:14,
                 from /home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/python.h:11,
                 from /home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/extension.h:6,
                 from /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/tinycudann/bindings.cpp:34:
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/pybind11/pybind11.h: In instantiation of ‘class pybind11::class_<tcnn::cpp::LogSeverity>’:
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/pybind11/pybind11.h:2134:7:   required from ‘class pybind11::enum_<tcnn::cpp::LogSeverity>’
/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/tinycudann/bindings.cpp:283:52:   required from here
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/pybind11/pybind11.h:1479:7: warning: ‘pybind11::class_<tcnn::cpp::LogSeverity>’ declared with greater visibility than its base ‘pybind11::detail::generic_type’ [-Wattributes]
 1479 | class class_ : public detail::generic_type {
      |       ^~~~~~
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/pybind11/pybind11.h: In instantiation of ‘class pybind11::class_<tcnn::cpp::Precision>’:
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/pybind11/pybind11.h:2134:7:   required from ‘class pybind11::enum_<tcnn::cpp::Precision>’
/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/tinycudann/bindings.cpp:292:48:   required from here
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/pybind11/pybind11.h:1479:7: warning: ‘pybind11::class_<tcnn::cpp::Precision>’ declared with greater visibility than its base ‘pybind11::detail::generic_type’ [-Wattributes]
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/pybind11/pybind11.h: In instantiation of ‘class pybind11::class_<tcnn::cpp::Context>’:
/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/tinycudann/bindings.cpp:309:45:   required from here
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/pybind11/pybind11.h:1479:7: warning: ‘pybind11::class_<tcnn::cpp::Context>’ declared with greater visibility than its base ‘pybind11::detail::generic_type’ [-Wattributes]
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/pybind11/pybind11.h: In instantiation of ‘class pybind11::class_<Module>’:
/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/tinycudann/bindings.cpp:316:32:   required from here
/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/pybind11/pybind11.h:1479:7: warning: ‘pybind11::class_<Module>’ declared with greater visibility than its base ‘pybind11::detail::generic_type’ [-Wattributes]
[8/9] /usr/local/cuda/bin/nvcc  -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/tools/util/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/TH -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/include/python3.8 -c -c /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/src/encoding.cu -o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/src/encoding.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -std=c++17 --extended-lambda --expt-relaxed-constexpr -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -Xcompiler=-Wno-float-conversion -Xcompiler=-fno-strict-aliasing -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70 -DTCNN_PARAMS_UNALIGNED -DTCNN_MIN_GPU_ARCH=70 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_70_C -D_GLIBCXX_USE_CXX11_ABI=0
/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

[9/9] /usr/local/cuda/bin/nvcc  -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/cutlass/tools/util/include -I/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/TH -I/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/bitterdhg/anaconda3/envs/threestudio_py38/include/python3.8 -c -c /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/src/cutlass_mlp.cu -o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/src/cutlass_mlp.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -std=c++17 --extended-lambda --expt-relaxed-constexpr -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -Xcompiler=-Wno-float-conversion -Xcompiler=-fno-strict-aliasing -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70 -DTCNN_PARAMS_UNALIGNED -DTCNN_MIN_GPU_ARCH=70 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_70_C -D_GLIBCXX_USE_CXX11_ABI=0
/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

/home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/dependencies/fmt/include/fmt/core.h(288): warning #1675-D: unrecognized GCC pragma

g++ -pthread -B /home/bitterdhg/anaconda3/envs/threestudio_py38/compiler_compat -Wl,--sysroot=/ -pthread -shared -B /home/bitterdhg/anaconda3/envs/threestudio_py38/compiler_compat -L/home/bitterdhg/anaconda3/envs/threestudio_py38/lib -Wl,-rpath=/home/bitterdhg/anaconda3/envs/threestudio_py38/lib -Wl,--no-as-needed -Wl,--sysroot=/ /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/../../dependencies/fmt/src/format.o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/../../dependencies/fmt/src/os.o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/../../src/common_host.o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/../../src/cpp_api.o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/../../src/cutlass_mlp.o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/../../src/encoding.o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/../../src/network.o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/../../src/object.o /home/bitterdhg/Code/nerf/Learn/tiny-cuda-nn/bindings/torch/build/temp.linux-x86_64-cpython-38/tinycudann/bindings.o -L/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/torch/lib -L/usr/local/cuda/lib64 -lcuda -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-cpython-38/tinycudann_bindings/_70_C.cpython-38-x86_64-linux-gnu.so
creating build/bdist.linux-x86_64/egg
creating build/bdist.linux-x86_64/egg/tinycudann_bindings
copying build/lib.linux-x86_64-cpython-38/tinycudann_bindings/_70_C.cpython-38-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg/tinycudann_bindings
creating build/bdist.linux-x86_64/egg/tinycudann
copying build/lib.linux-x86_64-cpython-38/tinycudann/bindings.cpp -> build/bdist.linux-x86_64/egg/tinycudann
copying build/lib.linux-x86_64-cpython-38/tinycudann/modules.py -> build/bdist.linux-x86_64/egg/tinycudann
copying build/lib.linux-x86_64-cpython-38/tinycudann/__init__.py -> build/bdist.linux-x86_64/egg/tinycudann
byte-compiling build/bdist.linux-x86_64/egg/tinycudann/modules.py to modules.cpython-38.pyc
byte-compiling build/bdist.linux-x86_64/egg/tinycudann/__init__.py to __init__.cpython-38.pyc
creating stub loader for tinycudann_bindings/_70_C.cpython-38-x86_64-linux-gnu.so
byte-compiling build/bdist.linux-x86_64/egg/tinycudann_bindings/_70_C.py to _70_C.cpython-38.pyc
creating build/bdist.linux-x86_64/egg/EGG-INFO
copying tinycudann.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO
copying tinycudann.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying tinycudann.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying tinycudann.egg-info/not-zip-safe -> build/bdist.linux-x86_64/egg/EGG-INFO
copying tinycudann.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
writing build/bdist.linux-x86_64/egg/EGG-INFO/native_libs.txt
creating 'dist/tinycudann-1.7-py3.8-linux-x86_64.egg' and adding 'build/bdist.linux-x86_64/egg' to it
removing 'build/bdist.linux-x86_64/egg' (and everything under it)
Processing tinycudann-1.7-py3.8-linux-x86_64.egg
removing '/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/tinycudann-1.7-py3.8-linux-x86_64.egg' (and everything under it)
creating /home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/tinycudann-1.7-py3.8-linux-x86_64.egg
Extracting tinycudann-1.7-py3.8-linux-x86_64.egg to /home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages
Adding tinycudann 1.7 to easy-install.pth file

Installed /home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/tinycudann-1.7-py3.8-linux-x86_64.egg
Processing dependencies for tinycudann==1.7
Finished processing dependencies for tinycudann==1.7

3. run

3.1 bash

python launch.py \
--config configs/dreamfusion-if.yaml \
--train \
--gpu 0 \
system.prompt_processor.prompt="a zoomed out DSLR photo of a baby bunny sitting on top of a stack of pancakes"

3.2 error

Traceback (most recent call last):
  File "launch.py", line 237, in <module>
    main(args, extras)
  File "launch.py", line 73, in main
    import threestudio
  File "/home/bitterdhg/Code/nerf/Learn/threestudio-main/threestudio/__init__.py", line 36, in <module>
    from . import data, models, systems
  File "/home/bitterdhg/Code/nerf/Learn/threestudio-main/threestudio/data/__init__.py", line 1, in <module>
    from . import co3d, image, multiview, uncond
  File "/home/bitterdhg/Code/nerf/Learn/threestudio-main/threestudio/data/co3d.py", line 17, in <module>
    from threestudio.data.uncond import (
  File "/home/bitterdhg/Code/nerf/Learn/threestudio-main/threestudio/data/uncond.py", line 13, in <module>
    from threestudio.utils.base import Updateable
  File "/home/bitterdhg/Code/nerf/Learn/threestudio-main/threestudio/utils/__init__.py", line 1, in <module>
    from . import base
  File "/home/bitterdhg/Code/nerf/Learn/threestudio-main/threestudio/utils/base.py", line 7, in <module>
    from threestudio.utils.misc import get_device, load_module_weights
  File "/home/bitterdhg/Code/nerf/Learn/threestudio-main/threestudio/utils/misc.py", line 5, in <module>
    import tinycudann as tcnn
  File "/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/tinycudann-1.7-py3.8-linux-x86_64.egg/tinycudann/__init__.py", line 9, in <module>
    from tinycudann.modules import free_temporary_memory, NetworkWithInputEncoding, Network, Encoding
  File "/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/tinycudann-1.7-py3.8-linux-x86_64.egg/tinycudann/modules.py", line 51, in <module>
    _C = importlib.import_module(f"tinycudann_bindings._{cc}_C")
  File "/home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
ImportError: /home/bitterdhg/anaconda3/envs/threestudio_py38/lib/python3.8/site-packages/tinycudann-1.7-py3.8-linux-x86_64.egg/tinycudann_bindings/_70_C.cpython-38-x86_64-linux-gnu.so: undefined symbol: cuMemAddressFree
v4r4rth commented 11 months ago

Can you please share the solution? I am running into the same error..