search

graphdeco-inria / gaussian-splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/
Other
13.49k stars 1.72k forks source link

Problem installing #297

Open Schmidi321 opened 11 months ago

Schmidi321 commented 11 months ago

Microsoft Windows [Version 10.0.19045.3448] (c) Microsoft Corporation. Alle Rechte vorbehalten.

C:\Users\Michael>cd gaussian-splatting

C:\Users\Michael\gaussian-splatting>SET DISTUTILS_USE_SDK=1

C:\Users\Michael\gaussian-splatting>conda env create --file environment.yml Collecting package metadata (repodata.json): done Solving environment: done

==> WARNING: A newer version of conda exists. <== current version: 23.7.4 latest version: 23.9.0

Please update conda by running

$ conda update -n base -c defaults conda

Or to minimize the number of packages updated during conda update use

 conda install conda=23.9.0

Downloading and Extracting Packages

Preparing transaction: done Verifying transaction: done Executing transaction: \ "By downloading and using the CUDA Toolkit conda packages, you accept the terms and conditions of the CUDA End User License Agreement (EULA): https://docs.nvidia.com/cuda/eula/index.html"

done Installing pip dependencies: - Ran pip subprocess with arguments: ['C:\Users\Michael\anaconda3\envs\gaussian_splatting\python.exe', '-m', 'pip', 'install', '-U', '-r', 'C:\Users\Michael\gaussian-splatting\condaenv.szeyals7.requirements.txt', '--exists-action=b'] Pip subprocess output: Processing c:\users\michael\gaussian-splatting\submodules\diff-gaussian-rasterization Preparing metadata (setup.py): started Preparing metadata (setup.py): finished with status 'done' Processing c:\users\michael\gaussian-splatting\submodules\simple-knn Preparing metadata (setup.py): started Preparing metadata (setup.py): finished with status 'done' Building wheels for collected packages: diff-gaussian-rasterization, simple-knn Building wheel for diff-gaussian-rasterization (setup.py): started Building wheel for diff-gaussian-rasterization (setup.py): finished with status 'error' Running setup.py clean for diff-gaussian-rasterization Building wheel for simple-knn (setup.py): started Building wheel for simple-knn (setup.py): finished with status 'error' Running setup.py clean for simple-knn Failed to build diff-gaussian-rasterization simple-knn Installing collected packages: simple-knn, diff-gaussian-rasterization Running setup.py install for simple-knn: started Running setup.py install for simple-knn: finished with status 'error'

Pip subprocess error: error: subprocess-exited-with-error

× python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> [21 lines of output] running bdist_wheel C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:411: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils backend. warnings.warn(msg.format('we could not find ninja.')) running build running build_py creating build creating build\lib.win-amd64-cpython-37 creating build\lib.win-amd64-cpython-37\diff_gaussian_rasterization copying diff_gaussian_rasterization__init.py -> build\lib.win-amd64-cpython-37\diff_gaussian_rasterization running build_ext C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:346: UserWarning: Error checking compiler version for cl: [WinError 2] Das System kann die angegebene Datei nicht finden warnings.warn(f'Error checking compiler version for {compiler}: {error}') C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:813: UserWarning: The detected CUDA version (11.7) has a minor version mismatch with the version that was used to compile PyTorch (11.6). Most likely this shouldn't be a problem. warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda)) building 'diff_gaussian_rasterization._C' extension creating build\temp.win-amd64-cpython-37 creating build\temp.win-amd64-cpython-37\Release creating build\temp.win-amd64-cpython-37\Release\cuda_rasterizer "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin\nvcc" -c cuda_rasterizer/backward.cu -o build\temp.win-amd64-cpython-37\Release\cuda_rasterizer/backward.obj -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\TH -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\THC "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\include" -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\Include -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcompiler /EHsc -Xcompiler /wd4190 -Xcompiler /wd4018 -Xcompiler /wd4275 -Xcompiler /wd4267 -Xcompiler /wd4244 -Xcompiler /wd4251 -Xcompiler /wd4819 -Xcompiler /MD -D__CUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_BFLOAT16_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -IC:\Users\Michael\gaussian-splatting\submodules\diff-gaussian-rasterization\third_party/glm/ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 --use-local-env nvcc fatal : Cannot find compiler 'cl.exe' in PATH error: command 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin\nvcc.exe' failed with exit code 1 [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for diff-gaussian-rasterization error: subprocess-exited-with-error

× python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> [12 lines of output] running bdist_wheel C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:411: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils backend. warnings.warn(msg.format('we could not find ninja.')) running build running build_ext C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:346: UserWarning: Error checking compiler version for cl: [WinError 2] Das System kann die angegebene Datei nicht finden warnings.warn(f'Error checking compiler version for {compiler}: {error}') C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:813: UserWarning: The detected CUDA version (11.7) has a minor version mismatch with the version that was used to compile PyTorch (11.6). Most likely this shouldn't be a problem. warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda)) building 'simple_knn._C' extension cl.exe /c /nologo /O2 /W3 /GL /DNDEBUG /MD -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\TH -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\THC "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\include" -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\Include /EHsc /Tpext.cpp /Fobuild\temp.win-amd64-cpython-37\Release\ext.obj /MD /wd4819 /wd4251 /wd4244 /wd4267 /wd4275 /wd4018 /wd4190 /EHsc /wd4624 -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 error: command 'cl.exe' failed: None [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for simple-knn error: subprocess-exited-with-error

× Running setup.py install for simple-knn did not run successfully. │ exit code: 1 ╰─> [28 lines of output] running install C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\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()
  running build
  running build_ext
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:411: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils backend.
    warnings.warn(msg.format('we could not find ninja.'))
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:346: UserWarning: Error checking compiler version for cl: [WinError 2] Das System kann die angegebene Datei nicht finden
    warnings.warn(f'Error checking compiler version for {compiler}: {error}')
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:813: UserWarning: The detected CUDA version (11.7) has a minor version mismatch with the version that was used to compile PyTorch (11.6). Most likely this shouldn't be a problem.
    warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda))
  building 'simple_knn._C' extension
  creating build
  creating build\temp.win-amd64-cpython-37
  creating build\temp.win-amd64-cpython-37\Release
  cl.exe /c /nologo /O2 /W3 /GL /DNDEBUG /MD -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\TH -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\THC "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\include" -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\Include /EHsc /Tpext.cpp /Fobuild\temp.win-amd64-cpython-37\Release\ext.obj /MD /wd4819 /wd4251 /wd4244 /wd4267 /wd4275 /wd4018 /wd4190 /EHsc /wd4624 -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0
  error: command 'cl.exe' failed: None
  [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. error: legacy-install-failure

× Encountered error while trying to install package. ╰─> simple-knn

note: This is an issue with the package mentioned above, not pip. hint: See above for output from the failure.

failed

CondaEnvException: Pip failed

C:\Users\Michael\gaussian-splatting>

Schmidi321 commented 11 months ago

Microsoft Windows [Version 10.0.19045.3448] (c) Microsoft Corporation. Alle Rechte vorbehalten.

C:\Users\Michael>cd gaussian-splatting

C:\Users\Michael\gaussian-splatting>SET DISTUTILS_USE_SDK=1

C:\Users\Michael\gaussian-splatting>conda env create --file environment.yml Collecting package metadata (repodata.json): done Solving environment: done

==> WARNING: A newer version of conda exists. <== current version: 23.7.4 latest version: 23.9.0

Please update conda by running

$ conda update -n base -c defaults conda

Or to minimize the number of packages updated during conda update use

 conda install conda=23.9.0

Downloading and Extracting Packages

Preparing transaction: done Verifying transaction: done Executing transaction: \ "By downloading and using the CUDA Toolkit conda packages, you accept the terms and conditions of the CUDA End User License Agreement (EULA): https://docs.nvidia.com/cuda/eula/index.html"

done Installing pip dependencies: - Ran pip subprocess with arguments: ['C:\Users\Michael\anaconda3\envs\gaussian_splatting\python.exe', '-m', 'pip', 'install', '-U', '-r', 'C:\Users\Michael\gaussian-splatting\condaenv.h493l1rx.requirements.txt', '--exists-action=b'] Pip subprocess output: Processing c:\users\michael\gaussian-splatting\submodules\diff-gaussian-rasterization Preparing metadata (setup.py): started Preparing metadata (setup.py): finished with status 'done' Processing c:\users\michael\gaussian-splatting\submodules\simple-knn Preparing metadata (setup.py): started Preparing metadata (setup.py): finished with status 'done' Building wheels for collected packages: diff-gaussian-rasterization, simple-knn Building wheel for diff-gaussian-rasterization (setup.py): started Building wheel for diff-gaussian-rasterization (setup.py): finished with status 'error' Running setup.py clean for diff-gaussian-rasterization Building wheel for simple-knn (setup.py): started Building wheel for simple-knn (setup.py): finished with status 'error' Running setup.py clean for simple-knn Failed to build diff-gaussian-rasterization simple-knn Installing collected packages: simple-knn, diff-gaussian-rasterization Running setup.py install for simple-knn: started Running setup.py install for simple-knn: finished with status 'error'

Pip subprocess error: error: subprocess-exited-with-error

× python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> [18 lines of output] running bdist_wheel C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:411: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils backend. warnings.warn(msg.format('we could not find ninja.')) running build running build_py creating build creating build\lib.win-amd64-cpython-37 creating build\lib.win-amd64-cpython-37\diff_gaussian_rasterization copying diff_gaussian_rasterization__init.py -> build\lib.win-amd64-cpython-37\diff_gaussian_rasterization running build_ext building 'diff_gaussian_rasterization._C' extension creating build\temp.win-amd64-cpython-37 creating build\temp.win-amd64-cpython-37\Release creating build\temp.win-amd64-cpython-37\Release\cuda_rasterizer "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\bin\nvcc" -c cuda_rasterizer/backward.cu -o build\temp.win-amd64-cpython-37\Release\cuda_rasterizer/backward.obj -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\TH -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\THC "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\include" -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\Include -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcompiler /EHsc -Xcompiler /wd4190 -Xcompiler /wd4018 -Xcompiler /wd4275 -Xcompiler /wd4267 -Xcompiler /wd4244 -Xcompiler /wd4251 -Xcompiler /wd4819 -Xcompiler /MD -D__CUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_BFLOAT16_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -IC:\Users\Michael\gaussian-splatting\submodules\diff-gaussian-rasterization\third_party/glm/ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 --use-local-env C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\include\crt/host_config.h(238): fatal error C1083: Datei (Include) kann nicht ge\xf6ffnet werden: "crtdefs.h": No such file or directory backward.cu error: command 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\bin\nvcc.exe' failed with exit code 2 [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for diff-gaussian-rasterization error: subprocess-exited-with-error

× python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> [10 lines of output] running bdist_wheel C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:411: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils backend. warnings.warn(msg.format('we could not find ninja.')) running build running build_ext building 'simple_knn._C' extension "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Tools\MSVC\14.29.30133\bin\Hostx64\x64\cl.exe" /c /nologo /O2 /W3 /GL /DNDEBUG /MD -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\TH -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\THC "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\include" -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\Include /EHsc /Tpext.cpp /Fobuild\temp.win-amd64-cpython-37\Release\ext.obj /MD /wd4819 /wd4251 /wd4244 /wd4267 /wd4275 /wd4018 /wd4190 /EHsc /wd4624 -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 ext.cpp C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include\torch/cuda.h(5): fatal error C1083: Datei (Include) kann nicht geöffnet werden: "cstdint": No such file or directory error: command 'C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Tools\MSVC\14.29.30133\bin\Hostx64\x64\cl.exe' failed with exit code 2 [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for simple-knn error: subprocess-exited-with-error

× Running setup.py install for simple-knn did not run successfully. │ exit code: 1 ╰─> [26 lines of output] running install C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\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()
  running build
  running build_ext
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py:411: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils backend.
    warnings.warn(msg.format('we could not find ninja.'))
  building 'simple_knn._C' extension
  creating build
  creating build\temp.win-amd64-cpython-37
  creating build\temp.win-amd64-cpython-37\Release
  "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Tools\MSVC\14.29.30133\bin\Hostx64\x64\cl.exe" /c /nologo /O2 /W3 /GL /DNDEBUG /MD -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\TH -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\THC "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\include" -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\Include /EHsc /Tpext.cpp /Fobuild\temp.win-amd64-cpython-37\Release\ext.obj /MD /wd4819 /wd4251 /wd4244 /wd4267 /wd4275 /wd4018 /wd4190 /EHsc /wd4624 -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0
  ext.cpp
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include\torch/cuda.h(5): fatal error C1083: Datei (Include) kann nicht geöffnet werden: "cstdint": No such file or directory
  error: command 'C:\\Program Files (x86)\\Microsoft Visual Studio\\2019\\Enterprise\\VC\\Tools\\MSVC\\14.29.30133\\bin\\Hostx64\\x64\\cl.exe' failed with exit code 2
  [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. error: legacy-install-failure

× Encountered error while trying to install package. ╰─> simple-knn

note: This is an issue with the package mentioned above, not pip. hint: See above for output from the failure.

failed

CondaEnvException: Pip failed

Batchvorgang abbrechen (J/N)? ^C C:\Users\Michael\gaussian-splatting>

C:\Users\Michael\gaussian-splatting>

wgcban commented 11 months ago

@Schmidi321 @yzslab @jakubcerveny @emepetres @gdrett After trying a full day I was able to successfully install submodules. I followed the following steps.

  1. Created a Conda environment: conda create -n gaussian_splatting python=3.7
  2. activate the conda environment: conda activate gaussian_splatting
  3. install the torch with cuda version following this [issue] pip install torch==1.9.0+cu102 torchvision==0.10.0+cu102 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html
  4. install submodule/diff-gaussian-rasterization pkg: pip install submodules/diff-gaussian-rasterization
  5. install submodule/simple-knn pip install submodules/simple-knn
  6. Then install the rest of the packages

Hope this helps. thanks.

daxue2017 commented 11 months ago

i install pytorch by the anaconda, and also have this problem.

it have three requirement

  1. install ninja
  2. the visual studio maybe vs2019
  3. also install the cuda toolkit , because there is different between nvidai cuda toolkit and the ananconda cuda

your install way is not anaconda, so may the requirement is 1-2 requirements

Schmidi321 commented 11 months ago 
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=c10::impl::OperatorEntry::CppSignatureWithDebug
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=c10::impl::OperatorEntry::CppSignatureWithDebug
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<c10::impl::OperatorEntry::CppSignatureWithDebug>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\ATen/core/dispatch/OperatorEntry.h(234): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<c10::impl::OperatorEntry::CppSignatureWithDebug>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=c10::impl::OperatorEntry::CppSignatureWithDebug
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: "c10::constexpr_storage_t<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=c10::either<c10::OperatorName,c10::FunctionSchema>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=c10::either<c10::OperatorName,c10::FunctionSchema>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=c10::either<c10::OperatorName,c10::FunctionSchema>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<c10::either<c10::OperatorName,c10::FunctionSchema>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\ATen/core/op_registration/op_registration.h(434): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<c10::either<c10::OperatorName,c10::FunctionSchema>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=c10::either<c10::OperatorName,c10::FunctionSchema>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: "c10::constexpr_storage_t<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=at::ThreadLocalState
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=at::ThreadLocalState
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=at::ThreadLocalState
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<at::ThreadLocalState>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch/csrc/jit/runtime/interpreter.h(141): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<at::ThreadLocalState>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=at::ThreadLocalState
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: "c10::constexpr_storage_t<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::shared_ptr<torch::jit::Graph>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=std::shared_ptr<torch::jit::Graph>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=std::shared_ptr<torch::jit::Graph>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<std::shared_ptr<torch::jit::Graph>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch/csrc/jit/api/function_impl.h(124): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<std::shared_ptr<torch::jit::Graph>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::shared_ptr<torch::jit::Graph>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: "c10::constexpr_storage_t<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=torch::jit::Method
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=torch::jit::Method
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=torch::jit::Method
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<torch::jit::Method>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch/csrc/jit/api/object.h(41): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<torch::jit::Method>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=torch::jit::Method
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: "c10::constexpr_storage_t<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::vector<std::string,std::allocator<std::string>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=std::vector<std::string,std::allocator<std::string>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=std::vector<std::string,std::allocator<std::string>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<std::vector<std::string,std::allocator<std::string>>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch/csrc/jit/api/module.h(295): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<std::vector<std::string,std::allocator<std::string>>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::vector<std::string,std::allocator<std::string>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: "c10::constexpr_storage_t<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include\torch/nn/options/loss.h(404): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: "c10::constexpr_storage_t<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::vector<double,std::allocator<double>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=std::vector<double,std::allocator<double>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=std::vector<double,std::allocator<double>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<std::vector<double,std::allocator<double>>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include\torch/nn/options/upsampling.h(26): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<std::vector<double,std::allocator<double>>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::vector<double,std::allocator<double>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: "c10::constexpr_storage_t<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::tuple<at::Tensor,at::Tensor>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=std::tuple<at::Tensor,at::Tensor>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=std::tuple<at::Tensor,at::Tensor>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<std::tuple<at::Tensor,at::Tensor>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include\torch/nn/modules/rnn.h(157): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<std::tuple<at::Tensor,at::Tensor>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::tuple<at::Tensor,at::Tensor>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: "c10::constexpr_storage_t<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<std::function<void (const torch::autograd::profiler::thread_event_lists &)>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch/csrc/autograd/profiler_legacy.h(514): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<std::function<void (const torch::autograd::profiler::thread_event_lists &)>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: "c10::constexpr_storage_t<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::vector<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>,std::allocator<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=std::vector<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>,std::allocator<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=std::vector<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>,std::allocator<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<std::vector<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>,std::allocator<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>>>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch/csrc/autograd/profiler_legacy.h(588): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<std::vector<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>,std::allocator<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>>>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::vector<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>,std::allocator<std::vector<torch::autograd::profiler::LegacyEvent,std::allocator<torch::autograd::profiler::LegacyEvent>>>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(183): warning C4624: "c10::constexpr_storage_t<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::vector<at::Tensor,std::allocator<at::Tensor>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(367): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::constexpr_storage_t<T>".
          with
          [
              T=std::vector<at::Tensor,std::allocator<at::Tensor>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::trivially_copyable_optimization_optional_base<T>".
          with
          [
              T=std::vector<at::Tensor,std::allocator<at::Tensor>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(427): note: Siehe Verweis auf die gerade kompilierte Alias Vorlage-Instanziierung "c10::OptionalBase<std::vector<at::Tensor,std::allocator<at::Tensor>>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include\torch/optim/lbfgs.h(47): note: Siehe Verweis auf die gerade kompilierte Klasse Vorlage-Instanziierung "c10::optional<std::vector<at::Tensor,std::allocator<at::Tensor>>>".
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\c10/util/Optional.h(395): warning C4624: "c10::trivially_copyable_optimization_optional_base<T>": Der Destruktor wurde impliziert als gel”scht definiert.
          with
          [
              T=std::vector<at::Tensor,std::allocator<at::Tensor>>
          ]
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\pybind11\detail/common.h(108): warning C4005: "HAVE_SNPRINTF": Makro-Neudefinition
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\include\pyerrors.h(490): note: Siehe vorherige Definition von "HAVE_SNPRINTF"
  "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\bin\nvcc" -c rasterize_points.cu -o build\temp.win-amd64-cpython-37\Release\rasterize_points.obj -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\torch\csrc\api\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\TH -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\THC "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\include" -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\include -IC:\Users\Michael\anaconda3\envs\gaussian_splatting\Include "-IC:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Tools\MSVC\14.29.30133\include" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\shared" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\winrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\cppwinrt" -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcompiler /EHsc -Xcompiler /wd4190 -Xcompiler /wd4018 -Xcompiler /wd4275 -Xcompiler /wd4267 -Xcompiler /wd4244 -Xcompiler /wd4251 -Xcompiler /wd4819 -Xcompiler /MD -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -IC:\Users\Michael\gaussian-splatting\submodules\diff-gaussian-rasterization\third_party/glm/ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=compute_75 -gencode=arch=compute_75,code=sm_75 --use-local-env
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\pybind11\detail/common.h(108): warning C4005: "HAVE_SNPRINTF": Makro-Neudefinition
  C:\Users\Michael\anaconda3\envs\gaussian_splatting\include\pyerrors.h(490): note: Siehe vorherige Definition von "HAVE_SNPRINTF"
  C:/Users/Michael/anaconda3/envs/gaussian_splatting/lib/site-packages/torch/include\ATen/core/builtin_function.h(110): warning #20236-D: pragma "diag_suppress" is deprecated, use "nv_diag_suppress" instead

  C:/Users/Michael/anaconda3/envs/gaussian_splatting/lib/site-packages/torch/include\ATen/core/builtin_function.h(117): warning #20236-D: pragma "diag_default" is deprecated, use "nv_diag_default" instead

  C:/Users/Michael/anaconda3/envs/gaussian_splatting/lib/site-packages/torch/include\ATen/core/builtin_function.h(110): warning #20236-D: pragma "diag_suppress" is deprecated, use "nv_diag_suppress" instead

  C:/Users/Michael/anaconda3/envs/gaussian_splatting/lib/site-packages/torch/include\ATen/core/builtin_function.h(117): warning #20236-D: pragma "diag_default" is deprecated, use "nv_diag_default" instead

  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\pybind11\cast.h(1429): error: too few arguments for template template parameter "Tuple"
            detected during instantiation of class "pybind11::detail::tuple_caster<Tuple, Ts...> [with Tuple=std::pair, Ts=<T1, T2>]"
  (1507): here

  C:\Users\Michael\anaconda3\envs\gaussian_splatting\lib\site-packages\torch\include\pybind11\cast.h(1503): error: too few arguments for template template parameter "Tuple"
            detected during instantiation of class "pybind11::detail::tuple_caster<Tuple, Ts...> [with Tuple=std::pair, Ts=<T1, T2>]"
  (1507): here

  2 errors detected in the compilation of "rasterize_points.cu".
  rasterize_points.cu
  error: command 'C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.6\\bin\\nvcc.exe' failed with exit code 1
  [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. error: legacy-install-failure

× Encountered error while trying to install package. ╰─> diff-gaussian-rasterization

note: This is an issue with the package mentioned above, not pip. hint: See above for output from the failure.

(gaussian_splatting) C:\Users\Michael\gaussian-splatting>

axteroide commented 11 months ago

2 errors detected in the compilation of "rasterize_points.cu". rasterize_points.cu error: command 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\bin\nvcc.exe' failed with exit code 1 [end of output]



note: This error originates from a subprocess, and is likely not a problem with pip. error: legacy-install-failure

× Encountered error while trying to install package. ╰─> diff-gaussian-rasterization

note: This is an issue with the package mentioned above, not pip. hint: See above for output from the failure.

(gaussian_splatting) C:\Users\Michael\gaussian-splatting>

I'm getting the same error

m-gon-kim commented 11 months ago

@Schmidi321 @yzslab @jakubcerveny @emepetres @gdrett After trying a full day I was able to successfully install submodules. I followed the following steps.

  1. Created a Conda environment: conda create -n gaussian_splatting python=3.7
  2. activate the conda environment: conda activate gaussian_splatting
  3. install the torch with cuda version following this [issue] pip install torch==1.9.0+cu102 torchvision==0.10.0+cu102 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html
  4. install submodule/diff-gaussian-rasterization pkg: pip install submodules/diff-gaussian-rasterization
  5. install submodule/simple-knn pip install submodules/simple-knn
  6. Then install the rest of the packages

Hope this helps. thanks.

This solution helped me indeed. I appreciate it so much! 👍

ishipachev commented 11 months ago

I went through the same problems. If someone has it, check the possible solution here: https://github.com/graphdeco-inria/gaussian-splatting/issues/317

white6zz commented 10 months ago

2 errors detected in the compilation of "rasterize_points.cu". rasterize_points.cu error: command 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\bin\nvcc.exe' failed with exit code 1 [end of output]

I get similar error.I have installed cudatookit v11.6 using conda in virtual env.Then find that installing nvcc using conda solve this. conda install -c "nvidia/label/cuda-11.6.0" cuda-nvcc

AvierNZ commented 9 months ago

@Schmidi321 @yzslab @jakubcerveny @emepetres @gdrett After trying a full day I was able to successfully install submodules. I followed the following steps.

  1. Created a Conda environment: conda create -n gaussian_splatting python=3.7
  2. activate the conda environment: conda activate gaussian_splatting
  3. install the torch with cuda version following this [issue] pip install torch==1.9.0+cu102 torchvision==0.10.0+cu102 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html
  4. install submodule/diff-gaussian-rasterization pkg: pip install submodules/diff-gaussian-rasterization
  5. install submodule/simple-knn pip install submodules/simple-knn
  6. Then install the rest of the packages

Hope this helps. thanks.

This solution helped me indeed. I appreciate it so much! 👍

Thanks for this. If anyone is coming across the simple-knn errors and to clarify -first make sure you delete the current non working version onC:\Users\YOURNAME\.conda\envs\gaussian_splatting and also C:\Users\YOURNAME\gaussian-splatting. -Clone the repo again. -Then run @m-gon-kim instructions, ( cd gaussian-splatting to run the submodules commands ) -Finally you can SET DISTUTILS_USE_SDK=1 / conda env create --file environment.yml / conda activate gaussian_splatting

behnamasadi commented 8 months ago

I solved this problem by correcting setting the CUDA version (11.8), on Ubuntu :

export PATH="/usr/local/cuda-11.8/bin:$PATH"
export LD_LIBRARY_PATH="/usr/local/cuda-11.8/lib64:$LD_LIBRARY_PATH"

validate the correctness:

nvcc --version

Please pay attention to "/" and "\" in windows and Linux:

pip install submodules/simple-knn
pip install submodules/diff-gaussian-rasterization

to continue the installation:

conda env update --file environment.yml --name gaussian_splatting
luocha0107 commented 4 months ago

@Schmidi321 @yzslab @jakubcerveny @emepetres @gdrett After trying a full day I was able to successfully install submodules. I followed the following steps.

  1. Created a Conda environment: conda create -n gaussian_splatting python=3.7
  2. activate the conda environment: conda activate gaussian_splatting
  3. install the torch with cuda version following this [issue] pip install torch==1.9.0+cu102 torchvision==0.10.0+cu102 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html
  4. install submodule/diff-gaussian-rasterization pkg: pip install submodules/diff-gaussian-rasterization
  5. install submodule/simple-knn pip install submodules/simple-knn
  6. Then install the rest of the packages

Hope this helps. thanks.

@wgcban Hello, I still failed to install using your method and the cuda version I am using is also 10.2. Did you not encounter any diff-gaussian-rasterization or simple-knn errors during the installation of cuda version 10.2?

felixgeen commented 2 months ago

I've tried so many different things to compile this. I am on a 4090 on windows 11. I have VS2019 and VS2022 installed now with Cuda 11.8 and im now getting this error:

(gaussian_splatting) C:\Users\7950x\gaussian-splatting>conda env update --file environment.yml --name gaussian_splatting

Channels:
 - pytorch
 - conda-forge
 - defaults
Platform: win-64
Collecting package metadata (repodata.json): done
Solving environment: done

Downloading and Extracting Packages:

Preparing transaction: done
Verifying transaction: done
Executing transaction: | "By downloading and using the CUDA Toolkit conda packages, you accept the terms and conditions

done
Installing pip dependencies: / Ran pip subprocess with arguments:
['C:\\Users\\7950x\\miniconda3\\envs\\gaussian_splatting\\python.exe', '-m', 'pip', 'install', '-U', '-r', 'C:\\Users\\]
Pip subprocess output:
Processing c:\users\7950x\gaussian-splatting\submodules\diff-gaussian-rasterization
  Preparing metadata (setup.py): started
  Preparing metadata (setup.py): finished with status 'error'

Pip subprocess error:
  error: subprocess-exited-with-error

  × python setup.py egg_info did not run successfully.
  │ exit code: 1
  ╰─> [12 lines of output]
      Traceback (most recent call last):
        File "<string>", line 2, in <module>
        File "<pip-setuptools-caller>", line 34, in <module>
        File "C:\Users\7950x\gaussian-splatting\submodules\diff-gaussian-rasterization\setup.py", line 21, in <module>
          CUDAExtension(
        File "C:\Users\7950x\miniconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py", line 1n
          library_dirs += library_paths(cuda=True)
        File "C:\Users\7950x\miniconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py", line 1s
          paths.append(_join_cuda_home(lib_dir))
        File "C:\Users\7950x\miniconda3\envs\gaussian_splatting\lib\site-packages\torch\utils\cpp_extension.py", line 2e
          raise OSError('CUDA_HOME environment variable is not set. '
      OSError: CUDA_HOME environment variable is not set. Please set it to your CUDA install root.
      [end of output]

  note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed

× Encountered error while generating package metadata.
╰─> See above for output.

note: This is an issue with the package mentioned above, not pip.
hint: See above for details.

failed

CondaEnvException: Pip failed

(gaussian_splatting) C:\Users\7950x\gaussian-splatting>nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Sep_21_10:41:10_Pacific_Daylight_Time_2022
Cuda compilation tools, release 11.8, V11.8.89
Build cuda_11.8.r11.8/compiler.31833905_0

(gaussian_splatting) C:\Users\7950x\gaussian-splatting>

I have CUDA_HOME, CUDA_PATH and CUDA_PATH_V11_8 in my Path already pointing to "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8"

Any clues why I get this error now?