ninja: build stopped: subcommand failed.

[MollyHoo]

RuntimeError: Error building extension 'standard_rasterize_cuda': [1/3] :/usr/local/cuda-11.2/bin/nvcc -DTORCH_EXTENSION_NAME=standard_rasterize_cuda -DTORCH_API_INCLUDE_EXTENSION_H -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/TH -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/THC -isystem :/usr/local/cuda-11.2/include -isystem /usr/include/python3.7m -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_61,code=sm_61 --compiler-options '-fPIC' -std=c++14 -ccbin=$(which gcc-7) -c /home/seemmo/DECA/decalib/utils/rasterizer/standard_rasterize_cuda_kernel.cu -o standard_rasterize_cuda_kernel.cuda.o
FAILED: standard_rasterize_cuda_kernel.cuda.o
:/usr/local/cuda-11.2/bin/nvcc -DTORCH_EXTENSION_NAME=standard_rasterize_cuda -DTORCH_API_INCLUDE_EXTENSION_H -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/TH -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/THC -isystem :/usr/local/cuda-11.2/include -isystem /usr/include/python3.7m -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_61,code=sm_61 --compiler-options '-fPIC' -std=c++14 -ccbin=$(which gcc-7) -c /home/seemmo/DECA/decalib/utils/rasterizer/standard_rasterize_cuda_kernel.cu -o standard_rasterize_cuda_kernel.cuda.o
/bin/sh: 1: :/usr/local/cuda-11.2/bin/nvcc: not found
[2/3] c++ -MMD -MF standard_rasterize_cuda.o.d -DTORCH_EXTENSION_NAME=standard_rasterize_cuda -DTORCH_API_INCLUDE_EXTENSION_H -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/TH -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/THC -isystem :/usr/local/cuda-11.2/include -isystem /usr/include/python3.7m -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -c /home/seemmo/DECA/decalib/utils/rasterizer/standard_rasterize_cuda.cpp -o standard_rasterize_cuda.o
FAILED: standard_rasterize_cuda.o
c++ -MMD -MF standard_rasterize_cuda.o.d -DTORCH_EXTENSION_NAME=standard_rasterize_cuda -DTORCH_API_INCLUDE_EXTENSION_H -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/TH -isystem /home/seemmo/.local/lib/python3.7/site-packages/torch/include/THC -isystem :/usr/local/cuda-11.2/include -isystem /usr/include/python3.7m -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -c /home/seemmo/DECA/decalib/utils/rasterizer/standard_rasterize_cuda.cpp -o standard_rasterize_cuda.o
In file included from /home/seemmo/.local/lib/python3.7/site-packages/torch/include/torch/csrc/Device.h:3:0,
from /home/seemmo/.local/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/python.h:8,
from /home/seemmo/.local/lib/python3.7/site-packages/torch/include/torch/extension.h:6,
from /home/seemmo/.local/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/torch.h:6,
from /home/seemmo/DECA/decalib/utils/rasterizer/standard_rasterize_cuda.cpp:1:
/home/seemmo/.local/lib/python3.7/site-packages/torch/include/torch/csrc/python_headers.h:10:20: fatal error: Python.h: No such file or directory
compilation terminated.
ninja: build stopped: subcommand failed.

could you help me. i have tried for cuda10.1+cudnn7.6.5+torch1.6.0+torchvision0.7.0+ubuntu16.04
always this error.

[biophase]

I'm also getting the same error on Ubuntu 20.04. Were you able to find any solutions?

[JonathanLehner]

did you find any?

[YunliYin]

Did you find any solutions to this error? I met the same error.

[chenerg]

Just use --rasterizer_type=pytorch3d to bypass the self-implemented rasterlization version.

[Fightzzw]

Solution1:

use --rasterizer_type=pytorch3d to bypass the self-implemented rasterlization version which will generate standard_rasterize_cuda.o at the beginning of the program.

Solution2:

change the gcc version to gcc-7, you can use following command:

sudo apt install gcc-7
sudo unlink /usr/bin/gcc 
sudo ln -s /usr/bin/x86_64-linux-gnu-gcc-7 /usr/bin/gcc

You also can look up this blog for the details: 【ubuntu】gcc/g++傻傻分不清？如何实现ubuntu多版本gcc/g++切换