训练时报错

Question

训练时报错

sunmingyang666 opened this issue a year ago · 9 comments

(Radnerf) D:\RAD-NeRF>python main.py data/obama/ --workspace trial_obama/ -O --iters 200000
Traceback (most recent call last):
File "D:\RAD-NeRF\raymarching\raymarching.py", line 10, in
import _raymarching_face as _backend
ModuleNotFoundError: No module named '_raymarching_face'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py", line 1808, in _run_ninja_build
subprocess.run(
File "D:\LeStoreDownload\anaconda\envs\Radnerf\lib\subprocess.py", line 528, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "D:\RAD-NeRF\main.py", line 131, in
from nerf.network import NeRFNetwork
File "D:\RAD-NeRF\nerf\network.py", line 7, in
from .renderer import NeRFRenderer
File "D:\RAD-NeRF\nerf\renderer.py", line 10, in
import raymarching
File "D:\RAD-NeRF\raymarching_init_.py", line 1, in
from .raymarching import *
File "D:\RAD-NeRF\raymarching\raymarching.py", line 12, in
from .backend import backend
File "D:\RAD-NeRF\raymarching\backend.py", line 31, in
backend = load(name='raymarching_face',
File "D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py", line 1202, in load
return jit_compile(
File "D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py", line 1425, in jit_compile
write_ninja_file_and_build_library(
File "D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py", line 1537, in write_ninja_file_and_build_library
run_ninja_build(
File "D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py", line 1824, in run_ninja_build
raise RuntimeError(message) from e
RuntimeError: Error building extension 'raymarching_face': [1/2] C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\bin\nvcc --generate-dependencies-with-compile --dependency-output raymarching.cuda.o.d -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 -DTORCH_EXTENSION_NAME=raymarching_face -DTORCH_API_INCLUDE_EXTENSION_H -ID:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\include -ID:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\include\torch\csrc\api\include -ID:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\include\TH -ID:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\include\THC "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\include" -ID:\LeStoreDownload\anaconda\envs\Radnerf\Include -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_BFLOAT16_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS --expt-relaxed-constexpr -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 -O3 -std=c++14 -U__CUDA_NO_HALF_OPERATORS -U__CUDA_NO_HALF_CONVERSIONS_ -U__CUDA_NO_HALF2_OPERATORS__ -c D:\RAD-NeRF\raymarching\src\raymarching.cu -o raymarching.cuda.o
FAILED: raymarching.cuda.o
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\bin\nvcc --generate-dependencies-with-compile --dependency-output raymarching.cuda.o.d -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 -DTORCH_EXTENSION_NAME=raymarching_face -DTORCH_API_INCLUDE_EXTENSION_H -ID:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\include -ID:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\include\torch\csrc\api\include -ID:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\include\TH -ID:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\include\THC "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\include" -ID:\LeStoreDownload\anaconda\envs\Radnerf\Include -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS_ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 -O3 -std=c++14 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_HALF2_OPERATORS__ -c D:\RAD-NeRF\raymarching\src\raymarching.cu -o raymarching.cuda.o
cl: 命令行 warning D9025 :正在重写“/D__CUDA_NO_HALF_OPERATORS__”(用“/U__CUDA_NO_HALF_OPERATORS__”)
cl: 命令行 warning D9025 :正在重写“/D__CUDA_NO_HALF_CONVERSIONS__”(用“/U__CUDA_NO_HALF_CONVERSIONS__”)
cl: 命令行 warning D9025 :正在重写“/D__CUDA_NO_HALF2_OPERATORS__”(用“/U__CUDA_NO_HALF2_OPERATORS__”)
raymarching.cu
D:/LeStoreDownload/anaconda/envs/Radnerf/lib/site-packages/torch/include\c10/macros/Macros.h(143): warning C4067: 预处理器指令后有意外标记 - 应输入换行符
cl: 命令行 warning D9025 :正在重写“/D__CUDA_NO_HALF_OPERATORS__”(用“/U__CUDA_NO_HALF_OPERATORS__”)
cl: 命令行 warning D9025 :正在重写“/D__CUDA_NO_HALF_CONVERSIONS__”(用“/U__CUDA_NO_HALF_CONVERSIONS__”)
cl: 命令行 warning D9025 :正在重写“/D__CUDA_NO_HALF2_OPERATORS__”(用“/U__CUDA_NO_HALF2_OPERATORS__”)
raymarching.cu
D:/LeStoreDownload/anaconda/envs/Radnerf/lib/site-packages/torch/include\c10/macros/Macros.h(143): warning C4067: 预处理器指令后有意外标记 - 应输入换行符
D:/LeStoreDownload/anaconda/envs/Radnerf/lib/site-packages/torch/include\c10/core/SymInt.h(84): warning #68-D: integer conversion resulted in a change of sign

D:\LeStoreDownload\anaconda\envs\Radnerf\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

D:\LeStoreDownload\anaconda\envs\Radnerf\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

D:\RAD-NeRF\raymarching\src\raymarching.cu(181): warning #177-D: variable "rdx" was declared but never referenced
detected during instantiation of "void kernel_sph_from_ray(const scalar_t *, const scalar_t *, float, uint32_t, scalar_t *) [with scalar_t=double]"
(205): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(181): warning #177-D: variable "rdy" was declared but never referenced
detected during instantiation of "void kernel_sph_from_ray(const scalar_t *, const scalar_t *, float, uint32_t, scalar_t *) [with scalar_t=double]"
(205): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(181): warning #177-D: variable "rdz" was declared but never referenced
detected during instantiation of "void kernel_sph_from_ray(const scalar_t *, const scalar_t *, float, uint32_t, scalar_t *) [with scalar_t=double]"
(205): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(181): warning #177-D: variable "rdx" was declared but never referenced
detected during instantiation of "void kernel_sph_from_ray(const scalar_t *, const scalar_t *, float, uint32_t, scalar_t *) [with scalar_t=float]"
(205): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(181): warning #177-D: variable "rdy" was declared but never referenced
detected during instantiation of "void kernel_sph_from_ray(const scalar_t *, const scalar_t *, float, uint32_t, scalar_t *) [with scalar_t=float]"
(205): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(181): warning #177-D: variable "rdz" was declared but never referenced
detected during instantiation of "void kernel_sph_from_ray(const scalar_t *, const scalar_t *, float, uint32_t, scalar_t *) [with scalar_t=float]"
(205): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(181): warning #177-D: variable "rdx" was declared but never referenced
detected during instantiation of "void kernel_sph_from_ray(const scalar_t *, const scalar_t *, float, uint32_t, scalar_t *) [with scalar_t=c10::Half]"
(205): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(181): warning #177-D: variable "rdy" was declared but never referenced
detected during instantiation of "void kernel_sph_from_ray(const scalar_t *, const scalar_t *, float, uint32_t, scalar_t *) [with scalar_t=c10::Half]"
(205): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(181): warning #177-D: variable "rdz" was declared but never referenced
detected during instantiation of "void kernel_sph_from_ray(const scalar_t *, const scalar_t *, float, uint32_t, scalar_t *) [with scalar_t=c10::Half]"
(205): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(553): warning #177-D: variable "index" was declared but never referenced
detected during instantiation of "void kernel_march_rays_train_backward(const scalar_t *, const scalar_t *, const int *, const scalar_t *, uint32_t, uint32_t, scalar_t *, scalar_t *) [with scalar_t=double]"
(589): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(553): warning #177-D: variable "index" was declared but never referenced
detected during instantiation of "void kernel_march_rays_train_backward(const scalar_t *, const scalar_t *, const int *, const scalar_t *, uint32_t, uint32_t, scalar_t *, scalar_t *) [with scalar_t=float]"
(589): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(553): warning #177-D: variable "index" was declared but never referenced
detected during instantiation of "void kernel_march_rays_train_backward(const scalar_t *, const scalar_t *, const int *, const scalar_t *, uint32_t, uint32_t, scalar_t *, scalar_t *) [with scalar_t=c10::Half]"
(589): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(864): warning #177-D: variable "near" was declared but never referenced
detected during instantiation of "void kernel_march_rays(uint32_t, uint32_t, const int *, const scalar_t *, const scalar_t *, const scalar_t *, float, float, uint32_t, uint32_t, uint32_t, const uint8_t *, const scalar_t *, const scalar_t *, scalar_t *, scalar_t *, scalar_t *, const scalar_t *) [with scalar_t=double]"
(935): here

D:\RAD-NeRF\raymarching\src\raymarching.cu(864): warning #177-D: variable "near" was declared but never referenced
detected during instantiation of "void kernel_march_rays(uint32_t, uint32_t, const int *, const scalar_t *, const scalar_t *, const scalar_t *, float, float, uint32_t, uint32_t, uint32_t, const uint8_t *, const scalar_t *, const scalar_t *, scalar_t *, scalar_t *, scalar_t *, const scalar_t *) [with scalar_t=float]"
(935): here

2 errors detected in the compilation of "D:/RAD-NeRF/raymarching/src/raymarching.cu".
raymarching.cu
ninja: build stopped: subcommand failed.

Answer 1 · 2023-05-07T14:00:39.000Z

try bash ./RAD-NeRF/scripts/install_ext.sh

Answer 2 · 2023-05-07T14:34:07.000Z

try bash ./RAD-NeRF/scripts/install_ext.sh
ERROR: Invalid requirement: './freqencoder'
ERROR: Invalid requirement: './shencoder'
ERROR: Invalid requirement: './gridencoder'
ERROR: Invalid requirement: './raymarching'
so I have to restart?

Answer 3 · 2023-05-07T17:00:53.000Z

getting a working notebook together today will update here. I would start from the beginning again though.

Answer 4 · 2023-05-12T11:33:45.000Z

getting a working notebook together today will update here. I would start from the beginning again though.

`(Radnerf) D:\github\RAD-NeRF>bash scripts/install_ext.sh
Processing d:\github\rad-nerf\freqencoder
Preparing metadata (setup.py) ... done
Building wheels for collected packages: freqencoder
Building wheel for freqencoder (setup.py) ... error
error: subprocess-exited-with-error

× python setup.py bdist_wheel did not run successfully.
│ exit code: 1
╰─> [13 lines of output]
running bdist_wheel
running build
running build_ext
D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py:813: UserWarning: The detected CUDA version (11.6) has a minor version mismatch with the version that was used to compile PyTorch (11.3). Most likely this shouldn't be a problem.
warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda))
building '_freqencoder' extension
Emitting ninja build file D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
1.11.1.git.kitware.jobserver-1
"C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe" /nologo /INCREMENTAL:NO /LTCG /DLL /MANIFEST:EMBED,ID=2 /MANIFESTUAC:NO /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\lib "/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\lib/x64" /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\libs /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\PCbuild\amd64 "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\ATLMFC\lib\x64" "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\lib\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\lib\um\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\ucrt\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\um\x64" c10.lib torch.lib torch_cpu.lib torch_python.lib cudart.lib c10_cuda.lib torch_cuda_cu.lib torch_cuda_cpp.lib /EXPORT:PyInit__freqencoder D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\freqencoder\src\bindings.obj D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\freqencoder\src\freqencoder.obj /OUT:build\lib.win-amd64-cpython-39_freqencoder.cp39-win_amd64.pyd /IMPLIB:D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\freqencoder\src_freqencoder.cp39-win_amd64.lib
LINK : fatal error LNK1181: 无法打开输入文件“D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\freqencoder\src\bindings.obj”
error: command 'C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe' failed with exit code 1181
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for freqencoder
Running setup.py clean for freqencoder
Failed to build freqencoder
Installing collected packages: freqencoder
Running setup.py install for freqencoder ... error
error: subprocess-exited-with-error

× Running setup.py install for freqencoder did not run successfully.
│ exit code: 1
╰─> [34 lines of output]
running install
D:\LeStoreDownload\anaconda\envs\Radnerf\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, pypa/build 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
  D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py:813: UserWarning: The detected CUDA version (11.6) has a minor version mismatch with the version that was used to compile PyTorch (11.3). Most likely this shouldn't be a problem.
    warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda))
  building '_freqencoder' extension
  creating D:\github\RAD-NeRF\freqencoder\build
  creating D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39
  creating D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release
  creating D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github
  creating D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF
  creating D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\freqencoder
  creating D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\freqencoder\src
  Emitting ninja build file D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\build.ninja...
  Compiling objects...
  Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
  1.11.1.git.kitware.jobserver-1
  creating D:\github\RAD-NeRF\freqencoder\build\lib.win-amd64-cpython-39
  "C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe" /nologo /INCREMENTAL:NO /LTCG /DLL /MANIFEST:EMBED,ID=2 /MANIFESTUAC:NO /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\lib "/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\lib/x64" /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\libs /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\PCbuild\amd64 "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\ATLMFC\lib\x64" "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\lib\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\lib\um\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\ucrt\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\um\x64" c10.lib torch.lib torch_cpu.lib torch_python.lib cudart.lib c10_cuda.lib torch_cuda_cu.lib torch_cuda_cpp.lib /EXPORT:PyInit__freqencoder D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\freqencoder\src\bindings.obj D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\freqencoder\src\freqencoder.obj /OUT:build\lib.win-amd64-cpython-39\_freqencoder.cp39-win_amd64.pyd /IMPLIB:D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\freqencoder\src\_freqencoder.cp39-win_amd64.lib
  LINK : fatal error LNK1181: 无法打开输入文件“D:\github\RAD-NeRF\freqencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\freqencoder\src\bindings.obj”
  error: command 'C:\\Program Files (x86)\\Microsoft Visual Studio\\2019\\Community\\VC\\Tools\\MSVC\\14.29.30133\\bin\\HostX86\\x64\\link.exe' failed with exit code 1181
  [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.
╰─> freqencoder

note: This is an issue with the package mentioned above, not pip.
hint: See above for output from the failure.
Processing d:\github\rad-nerf\shencoder
Preparing metadata (setup.py) ... done
Building wheels for collected packages: shencoder
Building wheel for shencoder (setup.py) ... error
error: subprocess-exited-with-error

× python setup.py bdist_wheel did not run successfully.
│ exit code: 1
╰─> [13 lines of output]
running bdist_wheel
running build
running build_ext
D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py:813: UserWarning: The detected CUDA version (11.6) has a minor version mismatch with the version that was used to compile PyTorch (11.3). Most likely this shouldn't be a problem.
warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda))
building '_shencoder' extension
Emitting ninja build file D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
1.11.1.git.kitware.jobserver-1
"C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe" /nologo /INCREMENTAL:NO /LTCG /DLL /MANIFEST:EMBED,ID=2 /MANIFESTUAC:NO /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\lib "/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\lib/x64" /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\libs /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\PCbuild\amd64 "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\ATLMFC\lib\x64" "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\lib\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\lib\um\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\ucrt\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\um\x64" c10.lib torch.lib torch_cpu.lib torch_python.lib cudart.lib c10_cuda.lib torch_cuda_cu.lib torch_cuda_cpp.lib /EXPORT:PyInit__shencoder D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\shencoder\src\bindings.obj D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\shencoder\src\shencoder.obj /OUT:build\lib.win-amd64-cpython-39_shencoder.cp39-win_amd64.pyd /IMPLIB:D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\shencoder\src_shencoder.cp39-win_amd64.lib
LINK : fatal error LNK1181: 无法打开输入文件“D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\shencoder\src\bindings.obj”
error: command 'C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe' failed with exit code 1181
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for shencoder
Running setup.py clean for shencoder
Failed to build shencoder
Installing collected packages: shencoder
Running setup.py install for shencoder ... error
error: subprocess-exited-with-error

× Running setup.py install for shencoder did not run successfully.
│ exit code: 1
╰─> [34 lines of output]
running install
D:\LeStoreDownload\anaconda\envs\Radnerf\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, pypa/build 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
  D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py:813: UserWarning: The detected CUDA version (11.6) has a minor version mismatch with the version that was used to compile PyTorch (11.3). Most likely this shouldn't be a problem.
    warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda))
  building '_shencoder' extension
  creating D:\github\RAD-NeRF\shencoder\build
  creating D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39
  creating D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release
  creating D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github
  creating D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF
  creating D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\shencoder
  creating D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\shencoder\src
  Emitting ninja build file D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\build.ninja...
  Compiling objects...
  Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
  1.11.1.git.kitware.jobserver-1
  creating D:\github\RAD-NeRF\shencoder\build\lib.win-amd64-cpython-39
  "C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe" /nologo /INCREMENTAL:NO /LTCG /DLL /MANIFEST:EMBED,ID=2 /MANIFESTUAC:NO /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\lib "/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\lib/x64" /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\libs /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\PCbuild\amd64 "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\ATLMFC\lib\x64" "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\lib\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\lib\um\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\ucrt\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\um\x64" c10.lib torch.lib torch_cpu.lib torch_python.lib cudart.lib c10_cuda.lib torch_cuda_cu.lib torch_cuda_cpp.lib /EXPORT:PyInit__shencoder D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\shencoder\src\bindings.obj D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\shencoder\src\shencoder.obj /OUT:build\lib.win-amd64-cpython-39\_shencoder.cp39-win_amd64.pyd /IMPLIB:D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\shencoder\src\_shencoder.cp39-win_amd64.lib
  LINK : fatal error LNK1181: 无法打开输入文件“D:\github\RAD-NeRF\shencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\shencoder\src\bindings.obj”
  error: command 'C:\\Program Files (x86)\\Microsoft Visual Studio\\2019\\Community\\VC\\Tools\\MSVC\\14.29.30133\\bin\\HostX86\\x64\\link.exe' failed with exit code 1181
  [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.
╰─> shencoder

note: This is an issue with the package mentioned above, not pip.
hint: See above for output from the failure.
Processing d:\github\rad-nerf\gridencoder
Preparing metadata (setup.py) ... done
Building wheels for collected packages: gridencoder
Building wheel for gridencoder (setup.py) ... error
error: subprocess-exited-with-error

× python setup.py bdist_wheel did not run successfully.
│ exit code: 1
╰─> [13 lines of output]
running bdist_wheel
running build
running build_ext
D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py:813: UserWarning: The detected CUDA version (11.6) has a minor version mismatch with the version that was used to compile PyTorch (11.3). Most likely this shouldn't be a problem.
warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda))
building '_gridencoder' extension
Emitting ninja build file D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
1.11.1.git.kitware.jobserver-1
"C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe" /nologo /INCREMENTAL:NO /LTCG /DLL /MANIFEST:EMBED,ID=2 /MANIFESTUAC:NO /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\lib "/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\lib/x64" /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\libs /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\PCbuild\amd64 "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\ATLMFC\lib\x64" "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\lib\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\lib\um\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\ucrt\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\um\x64" c10.lib torch.lib torch_cpu.lib torch_python.lib cudart.lib c10_cuda.lib torch_cuda_cu.lib torch_cuda_cpp.lib /EXPORT:PyInit__gridencoder D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\gridencoder\src\bindings.obj D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\gridencoder\src\gridencoder.obj /OUT:build\lib.win-amd64-cpython-39_gridencoder.cp39-win_amd64.pyd /IMPLIB:D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\gridencoder\src_gridencoder.cp39-win_amd64.lib
LINK : fatal error LNK1181: 无法打开输入文件“D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\gridencoder\src\bindings.obj”
error: command 'C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe' failed with exit code 1181
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for gridencoder
Running setup.py clean for gridencoder
Failed to build gridencoder
Installing collected packages: gridencoder
Running setup.py install for gridencoder ... error
error: subprocess-exited-with-error

× Running setup.py install for gridencoder did not run successfully.
│ exit code: 1
╰─> [34 lines of output]
running install
D:\LeStoreDownload\anaconda\envs\Radnerf\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, pypa/build 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
  D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py:813: UserWarning: The detected CUDA version (11.6) has a minor version mismatch with the version that was used to compile PyTorch (11.3). Most likely this shouldn't be a problem.
    warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda))
  building '_gridencoder' extension
  creating D:\github\RAD-NeRF\gridencoder\build
  creating D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39
  creating D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release
  creating D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github
  creating D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF
  creating D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\gridencoder
  creating D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\gridencoder\src
  Emitting ninja build file D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\build.ninja...
  Compiling objects...
  Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
  1.11.1.git.kitware.jobserver-1
  creating D:\github\RAD-NeRF\gridencoder\build\lib.win-amd64-cpython-39
  "C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe" /nologo /INCREMENTAL:NO /LTCG /DLL /MANIFEST:EMBED,ID=2 /MANIFESTUAC:NO /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\lib "/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\lib/x64" /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\libs /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\PCbuild\amd64 "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\ATLMFC\lib\x64" "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\lib\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\lib\um\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\ucrt\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\um\x64" c10.lib torch.lib torch_cpu.lib torch_python.lib cudart.lib c10_cuda.lib torch_cuda_cu.lib torch_cuda_cpp.lib /EXPORT:PyInit__gridencoder D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\gridencoder\src\bindings.obj D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\gridencoder\src\gridencoder.obj /OUT:build\lib.win-amd64-cpython-39\_gridencoder.cp39-win_amd64.pyd /IMPLIB:D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\gridencoder\src\_gridencoder.cp39-win_amd64.lib
  LINK : fatal error LNK1181: 无法打开输入文件“D:\github\RAD-NeRF\gridencoder\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\gridencoder\src\bindings.obj”
  error: command 'C:\\Program Files (x86)\\Microsoft Visual Studio\\2019\\Community\\VC\\Tools\\MSVC\\14.29.30133\\bin\\HostX86\\x64\\link.exe' failed with exit code 1181
  [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.
╰─> gridencoder

note: This is an issue with the package mentioned above, not pip.
hint: See above for output from the failure.
Processing d:\github\rad-nerf\raymarching
Preparing metadata (setup.py) ... done
Building wheels for collected packages: raymarching-face
Building wheel for raymarching-face (setup.py) ... error
error: subprocess-exited-with-error

× python setup.py bdist_wheel did not run successfully.
│ exit code: 1
╰─> [13 lines of output]
running bdist_wheel
running build
running build_ext
D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py:813: UserWarning: The detected CUDA version (11.6) has a minor version mismatch with the version that was used to compile PyTorch (11.3). Most likely this shouldn't be a problem.
warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda))
building '_raymarching_face' extension
Emitting ninja build file D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
1.11.1.git.kitware.jobserver-1
"C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe" /nologo /INCREMENTAL:NO /LTCG /DLL /MANIFEST:EMBED,ID=2 /MANIFESTUAC:NO /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\lib "/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\lib/x64" /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\libs /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\PCbuild\amd64 "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\ATLMFC\lib\x64" "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\lib\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\lib\um\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\ucrt\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\um\x64" c10.lib torch.lib torch_cpu.lib torch_python.lib cudart.lib c10_cuda.lib torch_cuda_cu.lib torch_cuda_cpp.lib /EXPORT:PyInit__raymarching_face D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\raymarching\src\bindings.obj D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\raymarching\src\raymarching.obj /OUT:build\lib.win-amd64-cpython-39_raymarching_face.cp39-win_amd64.pyd /IMPLIB:D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\raymarching\src_raymarching_face.cp39-win_amd64.lib
LINK : fatal error LNK1181: 无法打开输入文件“D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\raymarching\src\bindings.obj”
error: command 'C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe' failed with exit code 1181
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for raymarching-face
Running setup.py clean for raymarching-face
Failed to build raymarching-face
Installing collected packages: raymarching-face
Running setup.py install for raymarching-face ... error
error: subprocess-exited-with-error

× Running setup.py install for raymarching-face did not run successfully.
│ exit code: 1
╰─> [34 lines of output]
running install
D:\LeStoreDownload\anaconda\envs\Radnerf\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, pypa/build 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
  D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\utils\cpp_extension.py:813: UserWarning: The detected CUDA version (11.6) has a minor version mismatch with the version that was used to compile PyTorch (11.3). Most likely this shouldn't be a problem.
    warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda))
  building '_raymarching_face' extension
  creating D:\github\RAD-NeRF\raymarching\build
  creating D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39
  creating D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release
  creating D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github
  creating D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF
  creating D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\raymarching
  creating D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\raymarching\src
  Emitting ninja build file D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\build.ninja...
  Compiling objects...
  Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
  1.11.1.git.kitware.jobserver-1
  creating D:\github\RAD-NeRF\raymarching\build\lib.win-amd64-cpython-39
  "C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\HostX86\x64\link.exe" /nologo /INCREMENTAL:NO /LTCG /DLL /MANIFEST:EMBED,ID=2 /MANIFESTUAC:NO /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\lib\site-packages\torch\lib "/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6\lib/x64" /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\libs /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf /LIBPATH:D:\LeStoreDownload\anaconda\envs\Radnerf\PCbuild\amd64 "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\ATLMFC\lib\x64" "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\lib\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\lib\um\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\ucrt\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\lib\10.0.19041.0\um\x64" c10.lib torch.lib torch_cpu.lib torch_python.lib cudart.lib c10_cuda.lib torch_cuda_cu.lib torch_cuda_cpp.lib /EXPORT:PyInit__raymarching_face D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\raymarching\src\bindings.obj D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\raymarching\src\raymarching.obj /OUT:build\lib.win-amd64-cpython-39\_raymarching_face.cp39-win_amd64.pyd /IMPLIB:D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\raymarching\src\_raymarching_face.cp39-win_amd64.lib
  LINK : fatal error LNK1181: 无法打开输入文件“D:\github\RAD-NeRF\raymarching\build\temp.win-amd64-cpython-39\Release\github\RAD-NeRF\raymarching\src\bindings.obj”
  error: command 'C:\\Program Files (x86)\\Microsoft Visual Studio\\2019\\Community\\VC\\Tools\\MSVC\\14.29.30133\\bin\\HostX86\\x64\\link.exe' failed with exit code 1181
  [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.
╰─> raymarching-face

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

what should I do now

Answer 5 · 2023-05-12T22:35:55.000Z

everything works perfectly for me in this environment, it should work fine after.

Answer 6 · 2023-06-15T07:42:09.000Z

I met the same problem. It seems cause by ninja do not work correctly but I dont know how to solve it. Do you have any ideas?

Answer 7 · 2023-07-01T15:53:44.000Z

After upgrading from cuda 11.6 to 11.8 and deleting 11.6 env path in windows 10 and uninstalling torch torchvision and torchaudio and reinistalling current cuda 11.8 stable torch 2.0 install it didn't have this error. I also had to use powershell instead on cmd to start training on windows.

Answer 8 · 2023-11-01T17:25:06.000Z

从 cuda 11.6 升级到 11.8 并删除 Windows 10 中的 11.6 env 路径并卸载 torch torchvision 和 torchaudio 并重新安装当前的 cuda 11.8 stable torch 2.0 安装后，没有出现此错误。我还必须在 cmd 上使用 powershell 来开始在 Windows 上进行训

Hello, I referred to your colab deployment plan, but I found that I still cannot solve this problem. The error is that freqencoder, shencoder, etc. cannot be built. The problem seems to be install_ext.sh. How to solve it?

Answer 9 · 2024-01-08T03:16:22.000Z

@davidspicy @Sticcolet @Tuziking @gloomiebloomie @sunmingyang666
i want to train model about 256x256 resolution, how can i do this, thanks in advance