Linux 中使用gcc, g++, nvcc 编译 PyTorch 扩展时，#include “torch/extension.h“ No such path or file.

原创 已于 2024-03-26 16:01:18 修改 · 765 阅读 · 0 ·
CC 4.0 BY-SA版权
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
文章标签：

#linux #pytorch #运维

于 2024-03-20 16:31:08 首次发布
文章指导用户在.bashrc文件中配置环境变量，以确保正确包含Torch库（如torch/extension.h,torch/all.h,Python.h）的头文件路径，以便在Anaconda环境中顺利使用Torch库。
部署运行你感兴趣的模型镜像

在 ~/.bashrc 中添加以下内容：

# torch/extension.h 父文件夹
export CPATH=/home/xxx/Anaconda/envs/torch/lib/python3.xx/site-packages/torch/include:$CPATH
# torch/all.h 父文件夹
export CPATH=/home/xxx/Anaconda/envs/torch/lib/python3.xx/site-packages/torch/include/torch/csrc/api/include:$CPATH
# Python.h 父文件夹
export CPATH=/home/xxx/Anaconda/envs/torch/include/python3.xx:$CPATH

您可能感兴趣的与本文相关的镜像

Python3.8

Python3.8

Conda
Python

Python 是一种高级、解释型、通用的编程语言，以其简洁易读的语法而闻名，适用于广泛的应用，包括Web开发、数据分析、人工智能和自动化脚本

bakaloop
关注
CPP, CUDA 扩展 PyTorch
qq_46013251的博客
10-03 1054
使用 C++, CUDA 扩展 PyTorch准备工作用 C++ 扩展 PyTorch用 CUDA 扩展 PyTorch参考 准备工作 请先确定一下 PyTorch 版本： >>> torch.__version__ ‘1.9.1’ >>> torch.version.cuda ‘11.1’ >>> torch.backends.cudnn.version() 8005 实验环境： 用 C++ 扩展 PyTorch 官网上案例使用的算子大多和 py
解决fatal error: torch/extension.h: No such file or directory
热门推荐
yuanlulu的博客
12-31 1万+
错误描述 在安装https://github.com/SeanNaren/warp-ctc/tree/pytorch_bindings的时候遇到编译错误： src/binding.cpp:6:10: fatal error: torch/extension.h: No such file or directory #include <torch/extension.h> 看样子是缺...
src/binding.cpp:6:29: fatal error: torch/extension.h: 没有那个文件或目录
bc521bc的博客
03-20 4144
error: command ‘gcc’ failed with exit status 1 warp-ctc 请确保你是在进行 warp-ctc 下的 python setup.py install 出现的报错！ 解决方案： 终端输入命令后 git checkout ac045b6072b9bc3454fb9f9f17674f0d59373789 之后再运行命令： python setup...
ctc loss解决问题：src/binding.cpp:6:29: fatal error: torch/extension.h: No such file or directory
Willen_的博客
03-28 1734
ctc loss解决问题：src/binding.cpp:6:29: fatal error: torch/extension.h: No such file or directory 借鉴： https://blog.csdn.net/gubenpeiyuan/article/details/85390830 https://blog.csdn.net/yuanlulu/article/d...
ctc loss解决问题：src/binding.cpp:6:29: fatal error: torch/extension.h: No such file or directory 墙内没有
固本培元的专栏
12-30 7240
  编译安装pytorch的 ctc loss 使用仓库： https://github.com/SeanNaren/warp-ctc   会遇到问题：墙内没有解决方案： src/binding.cpp:6:29: fatal error: torch/extension.h: No such file or directory compilation terminated.   解...
(point) jin@jin-Legion-Y9000P-IRX8:~/PointPillars-main$ python setup.py build_ext --inplace running build_ext /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/utils/cpp_extension.py:369: 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 'pointpillars.ops.voxel_op' extension creating build/temp.linux-x86_64-3.7 creating build/temp.linux-x86_64-3.7/pointpillars creating build/temp.linux-x86_64-3.7/pointpillars/ops creating build/temp.linux-x86_64-3.7/pointpillars/ops/voxelization gcc -pthread -B /home/jin/anaconda3/envs/point/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/TH -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/jin/anaconda3/envs/point/include/python3.7m -c pointpillars/ops/voxelization/voxelization.cpp -o build/temp.linux-x86_64-3.7/pointpillars/ops/voxelization/voxelization.o -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -DTORCH_EXTENSION_NAME=voxel_op -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14 cc1plus: warning: command-line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Parallel.h:140, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:13, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/extension.h:4, from pointpillars/ops/voxelization/voxelization.cpp:1: /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/ParallelOpenMP.h:83: warning: ignoring ‘#pragma omp parallel’ [-Wunknown-pragmas] 83 | #pragma omp parallel for if ((end - begin) >= grain_size) | gcc -pthread -B /home/jin/anaconda3/envs/point/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/TH -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/jin/anaconda3/envs/point/include/python3.7m -c pointpillars/ops/voxelization/voxelization_cpu.cpp -o build/temp.linux-x86_64-3.7/pointpillars/ops/voxelization/voxelization_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -DTORCH_EXTENSION_NAME=voxel_op -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14 cc1plus: warning: command-line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Parallel.h:140, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:13, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/extension.h:4, from pointpillars/ops/voxelization/voxelization_cpu.cpp:2: /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/ParallelOpenMP.h:83: warning: ignoring ‘#pragma omp parallel’ [-Wunknown-pragmas] 83 | #pragma omp parallel for if ((end - begin) >= grain_size) | /usr/local/cuda/bin/nvcc -DWITH_CUDA -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/TH -I/home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/jin/anaconda3/envs/point/include/python3.7m -c pointpillars/ops/voxelization/voxelization_cuda.cu -o build/temp.linux-x86_64-3.7/pointpillars/ops/voxelization/voxelization_cuda.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -DTORCH_EXTENSION_NAME=voxel_op -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 -std=c++14 In file included from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/detail/config/config.h:37, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/detail/config.h:22, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/complex.h:24, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/util/complex.h:9, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/core/ScalarType.h:4, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/core/Scalar.h:10, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:8, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Context.h:4, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9, from pointpillars/ops/voxelization/voxelization_cuda.cu:1: /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/detail/config/cpp_dialect.h:78:6: error: #error Thrust requires at least C++17. Define CCCL_IGNORE_DEPRECATED_CPP_DIALECT to suppress this message. 78 | # error Thrust requires at least C++17. Define CCCL_IGNORE_DEPRECATED_CPP_DIALECT to suppress this message. | ^~~~~ In file included from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cuda/std/detail/libcxx/include/__config:24, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cuda/std/detail/__config:43, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cuda/std/version:14, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cuda/version:14, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/version.h:41, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/detail/config/namespace.h:30, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/detail/config/config.h:43, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/detail/config.h:22, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/complex.h:24, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/util/complex.h:9, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/core/ScalarType.h:4, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/core/Scalar.h:10, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:8, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Context.h:4, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9, from pointpillars/ops/voxelization/voxelization_cuda.cu:1: /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cuda/std/__internal/cpp_dialect.h:40:6: error: #error libcu++ requires at least C++ 17. Define CCCL_IGNORE_DEPRECATED_CPP_DIALECT to suppress this message. 40 | # error libcu++ requires at least C++ 17. Define CCCL_IGNORE_DEPRECATED_CPP_DIALECT to suppress this message. | ^~~~~ In file included from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cub/util_arch.cuh:46, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cub/config.cuh:46, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cub/util_debug.cuh:39, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/system/cuda/config.h:49, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/system/cuda/detail/execution_policy.h:40, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/iterator/detail/device_system_tag.h:31, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/iterator/iterator_traits.h:42, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/type_traits/is_trivially_relocatable.h:37, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/complex.h:35, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/util/complex.h:9, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/core/ScalarType.h:4, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/core/Scalar.h:10, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:8, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Context.h:4, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9, from pointpillars/ops/voxelization/voxelization_cuda.cu:1: /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cub/util_cpp_dialect.cuh:88:8: error: #error CUB requires at least C++17. Define CCCL_IGNORE_DEPRECATED_CPP_DIALECT to suppress this message. 88 | # error CUB requires at least C++17. Define CCCL_IGNORE_DEPRECATED_CPP_DIALECT to suppress this message. | ^~~~~ error: command '/usr/local/cuda/bin/nvcc' failed with exit status 1 如何解决
11-24
我们遇到了在编译pytorch3d时，由于CUB等库需要C++17而当前编译器使用C++14导致的错误。根据引用[1][2][3][4]的提示，我们需要修改编译配置以支持C++17。以下是解决步骤： ### 解决方法 #### 1. 修改`setup.py`文件...
No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda' running build_ext /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/utils/cpp_extension.py:369: 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 'pointpillars.ops.voxel_op' extension creating build creating build/temp.linux-x86_64-3.8 creating build/temp.linux-x86_64-3.8/pointpillars creating build/temp.linux-x86_64-3.8/pointpillars/ops creating build/temp.linux-x86_64-3.8/pointpillars/ops/voxelization gcc -pthread -B /home/jin/anaconda3/envs/point1/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include -I/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/TH -I/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/jin/anaconda3/envs/point1/include/python3.8 -c pointpillars/ops/voxelization/voxelization.cpp -o build/temp.linux-x86_64-3.8/pointpillars/ops/voxelization/voxelization.o -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -DTORCH_EXTENSION_NAME=voxel_op -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14 cc1plus: warning: command-line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/ATen/Parallel.h:140, from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3, from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5, from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3, from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:13, from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/extension.h:4, from pointpillars/ops/voxelization/voxelization.cpp:1: /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/ATen/ParallelOpenMP.h:83: warning: ignoring ‘#pragma omp parallel’ [-Wunknown-pragmas] 83 | #pragma omp parallel for if ((end - begin) >= grain_size) | gcc -pthread -B /home/jin/anaconda3/envs/point1/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include -I/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/TH -I/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/jin/anaconda3/envs/point1/include/python3.8 -c pointpillars/ops/voxelization/voxelization_cpu.cpp -o build/temp.linux-x86_64-3.8/pointpillars/ops/voxelization/voxelization_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -DTORCH_EXTENSION_NAME=voxel_op -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14 cc1plus: warning: command-line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/ATen/Parallel.h:140, from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3, from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5, from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3, from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:13, from /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/torch/extension.h:4, from pointpillars/ops/voxelization/voxelization_cpu.cpp:2: /home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/include/ATen/ParallelOpenMP.h:83: warning: ignoring ‘#pragma omp parallel’ [-Wunknown-pragmas] 83 | #pragma omp parallel for if ((end - begin) >= grain_size) | Traceback (most recent call last): File "setup.py", line 4, in <module> setup( File "/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/setuptools/__init__.py", line 153, in setup return distutils.core.setup(**attrs) File "/home/jin/anaconda3/envs/point1/lib/python3.8/distutils/core.py", line 148, in setup dist.run_commands() File "/home/jin/anaconda3/envs/point1/lib/python3.8/distutils/dist.py", line 966, in run_commands self.run_command(cmd) File "/home/jin/anaconda3/envs/point1/lib/python3.8/distutils/dist.py", line 985, in run_command cmd_obj.run() File "/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/setuptools/command/build_ext.py", line 79, in run _build_ext.run(self) File "/home/jin/anaconda3/envs/point1/lib/python3.8/distutils/command/build_ext.py", line 340, in run self.build_extensions() File "/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 708, in build_extensions build_ext.build_extensions(self) File "/home/jin/anaconda3/envs/point1/lib/python3.8/distutils/command/build_ext.py", line 449, in build_extensions self._build_extensions_serial() File "/home/jin/anaconda3/envs/point1/lib/python3.8/distutils/command/build_ext.py", line 474, in _build_extensions_serial self.build_extension(ext) File "/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/setuptools/command/build_ext.py", line 202, in build_extension _build_ext.build_extension(self, ext) File "/home/jin/anaconda3/envs/point1/lib/python3.8/distutils/command/build_ext.py", line 528, in build_extension objects = self.compiler.compile(sources, File "/home/jin/anaconda3/envs/point1/lib/python3.8/distutils/ccompiler.py", line 574, in compile self._compile(obj, src, ext, cc_args, extra_postargs, pp_opts) File "/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 456, in unix_wrap_single_compile cflags = unix_cuda_flags(cflags) File "/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 423, in unix_cuda_flags cflags + _get_cuda_arch_flags(cflags)) File "/home/jin/anaconda3/envs/point1/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1561, in _get_cuda_arch_flags arch_list[-1] += '+PTX' IndexError: list index out of range
11-22
ninja是一个构建工具，某些包（如PyTorch扩展）需要它来编译。 解决方案: - 安装ninja: ```bash # Ubuntu/Debian sudo apt-get install ninja-build # CentOS sudo yum install ninja-build # 或者使用...
ubuntu安ubuntu@VM-0-10-ubuntu:~/cuda$ nvcc -V nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2019 NVIDIA Corporation Built on Sun_Jul_28_19:07:16_PDT_2019 Cuda compilation tools, release 10.1, V10.1.243 ubuntu@VM-0-10-ubuntu:~/cuda$ sudo cp cuda/include/cudnn.h /usr/local/cuda-10.1/include/ cp: cannot stat 'cuda/include/cudnn.h': No such file or directory ubuntu@VM-0-10-ubuntu:~/cuda$ sudo cp cuda/lib64/libcudnn* /usr/local/cuda-10.1/lib64/ cp: cannot stat 'cuda/lib64/libcudnn*': No such file or directory ubuntu@VM-0-10-ubuntu:~/cuda$ sudo chmod a+r /usr/local/cuda-10.1/include/cudnn.h /usr/local/cuda-10.1/lib64/libcudnn* chmod: cannot access '/usr/local/cuda-10.1/include/cudnn.h': No such file or directory chmod: cannot access '/usr/local/cuda-10.1/lib64/libcudnn*': No such file or directory装libtorch对应版本
03-22
嗯，用户正在尝试在Ubuntu系统上安装与CUDA 10.1对应的LibTorch版本，但在复制cuDNN文件时遇到了问题。首先，我需要理清楚用户的操作步骤和错误原因。用户执行了nvcc -V，显示CUDA 10.1已安装。然后尝试复制cuDNN的...
ust/detail/config.h:22, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/complex.h:24, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/util/complex.h:9, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/core/ScalarType.h:4, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/core/Scalar.h:10, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:8, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Context.h:4, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9, from pointpillars/ops/voxelization/voxelization_cuda.cu:1: /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cuda/std/__internal/cpp_dialect.h:40:6: error: #error libcu++ requires at least C++ 17. Define CCCL_IGNORE_DEPRECATED_CPP_DIALECT to suppress this message. 40 | # error libcu++ requires at least C++ 17. Define CCCL_IGNORE_DEPRECATED_CPP_DIALECT to suppress this message. | ^~~~~ In file included from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cub/util_arch.cuh:46, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cub/config.cuh:46, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cub/util_debug.cuh:39, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/system/cuda/config.h:49, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/system/cuda/detail/execution_policy.h:40, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/iterator/detail/device_system_tag.h:31, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/iterator/iterator_traits.h:42, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/type_traits/is_trivially_relocatable.h:37, from /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/thrust/complex.h:35, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/util/complex.h:9, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/core/ScalarType.h:4, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/c10/core/Scalar.h:10, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:8, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/Context.h:4, from /home/jin/anaconda3/envs/point/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9, from pointpillars/ops/voxelization/voxelization_cuda.cu:1: /usr/local/cuda-13.0/targets/x86_64-linux/include/cccl/cub/util_cpp_dialect.cuh:88:8: error: #error CUB requires at least C++17. Define CCCL_IGNORE_DEPRECATED_CPP_DIALECT to suppress this message. 88 | # error CUB requires at least C++17. Define CCCL_IGNORE_DEPRECATED_CPP_DIALECT to suppress this message. | ^~~~~ error: command '/usr/local/cuda/bin/nvcc' failed with exit status 1 如何解决
最新发布
11-25
- 但是，nvcc在编译主机代码（host code）时，默认可能不会使用C++17，所以我们需要同时确保主机编译器（如g++或cl.exe）支持C++17，并在编译命令中传递正确的标志。 3. 如果使用CMake构建项目，可以在CMakeLists...
FAILED: /home/ros1/GraspNet_ros/knn/build/temp.linux-x86_64-cpython-38/home/ros1/GraspNet_ros/knn/src/vision.o c++ -MMD -MF /home/ros1/GraspNet_ros/knn/build/temp.linux-x86_64-cpython-38/home/ros1/GraspNet_ros/knn/src/vision.o.d -pthread -B /home/ros1/anaconda3/envs/yolo/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/ros1/GraspNet_ros/knn/src -I/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/include -I/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/include/TH -I/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda-11.4/include -I/home/ros1/anaconda3/envs/yolo/include/python3.8 -c -c /home/ros1/GraspNet_ros/knn/src/vision.cpp -o /home/ros1/GraspNet_ros/knn/build/temp.linux-x86_64-cpython-38/home/ros1/GraspNet_ros/knn/src/vision.o -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=knn_pytorch -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/include/ATen/Parallel.h:140, from /home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3, from /home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5, from /home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3, from /home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:13, from /home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/include/torch/extension.h:4, from /home/ros1/GraspNet_ros/knn/src/cpu/vision.h:2, from /home/ros1/GraspNet_ros/knn/src/knn.h:2, from /home/ros1/GraspNet_ros/knn/src/vision.cpp:1: /home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/include/ATen/ParallelOpenMP.h:83: warning: ignoring #pragma omp parallel [-Wunknown-pragmas] 83 | #pragma omp parallel for if ((end - begin) >= grain_size) | In file included from /home/ros1/GraspNet_ros/knn/src/vision.cpp:1: /home/ros1/GraspNet_ros/knn/src/knn.h: In function ‘int knn(at::Tensor&, at::Tensor&, at::Tensor&)’: /home/ros1/GraspNet_ros/knn/src/knn.h:36:42: error: ‘c10::cuda::CUDACachingAllocator’ has not been declared 36 | float *dist_dev = (float*)c10::cuda::CUDACachingAllocator::raw_alloc(ref_nb * query_nb * sizeof(float)); | ^~~~~~~~~~~~~~~~~~~~ /home/ros1/GraspNet_ros/knn/src/knn.h:45:16: error: ‘c10::cuda::CUDACachingAllocator’ has not been declared 45 | c10::cuda::CUDACachingAllocator::raw_delete(dist_dev); | ^~~~~~~~~~~~~~~~~~~~ ninja: build stopped: subcommand failed. Traceback (most recent call last): File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1667, in _run_ninja_build subprocess.run( File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/subprocess.py", line 516, 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 "setup.py", line 62, in <module> setup( File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/__init__.py", line 117, in setup return distutils.core.setup(**attrs) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/core.py", line 183, in setup return run_commands(dist) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/core.py", line 199, in run_commands dist.run_commands() File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/dist.py", line 954, in run_commands self.run_command(cmd) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/dist.py", line 950, in run_command super().run_command(command) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/dist.py", line 973, in run_command cmd_obj.run() File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/command/install.py", line 97, in run self.do_egg_install() File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/command/install.py", line 149, in do_egg_install self.run_command('bdist_egg') File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/cmd.py", line 316, in run_command self.distribution.run_command(command) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/dist.py", line 950, in run_command super().run_command(command) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/dist.py", line 973, in run_command cmd_obj.run() File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/command/bdist_egg.py", line 168, in run cmd = self.call_command('install_lib', warn_dir=False) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/command/bdist_egg.py", line 154, in call_command self.run_command(cmdname) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/cmd.py", line 316, in run_command self.distribution.run_command(command) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/dist.py", line 950, in run_command super().run_command(command) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/dist.py", line 973, in run_command cmd_obj.run() File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/command/install_lib.py", line 19, in run self.build() File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/command/install_lib.py", line 110, in build self.run_command('build_ext') File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/cmd.py", line 316, in run_command self.distribution.run_command(command) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/dist.py", line 950, in run_command super().run_command(command) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/dist.py", line 973, in run_command cmd_obj.run() File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/command/build_ext.py", line 98, in run _build_ext.run(self) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/command/build_ext.py", line 359, in run self.build_extensions() File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 708, in build_extensions build_ext.build_extensions(self) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/command/build_ext.py", line 476, in build_extensions self._build_extensions_serial() File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/command/build_ext.py", line 502, in _build_extensions_serial self.build_extension(ext) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/command/build_ext.py", line 263, in build_extension _build_ext.build_extension(self, ext) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/Cython/Distutils/build_ext.py", line 136, in build_extension super().build_extension(ext) File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/setuptools/_distutils/command/build_ext.py", line 557, in build_extension objects = self.compiler.compile( File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 529, in unix_wrap_ninja_compile _write_ninja_file_and_compile_objects( File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1354, in _write_ninja_file_and_compile_objects _run_ninja_build( File "/home/ros1/anaconda3/envs/yolo/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1683, in _run_ninja_build raise RuntimeError(message) from e RuntimeError: Error compiling objects for extension
06-07
3.在编译PyTorch扩展时，还有哪些常见的错误以及如何解决？</think> ### 解决 PyTorch CUDA knn 扩展编译错误：`'c10::cuda::CUDACachingAllocator' not declared` #### 错误原因分析 该错误通常发生在以下情况： 1...
fatal error: torch/extension.h: No such file or directory
kaggle expert，全球排名前1000，清华计算机研究生，兴趣算法工程
04-22 3493
其实就是你现在环境的torch版本和你编译文件时用的不是一个版本，很大可能是你用了不同的conda环境导致的。更改为你编译代码用的torch版本即可。
cocos2d-x 3.4 VS2013无法打开包含文件extensions/ExtensionExport.h
DAo_1990的博客
07-24 1658
cocos2d-x 3.4 VS2013 无法打开包含文件extensions/ExtensionExport.h1、在你自己的头文件中加入#include ”cocos-ext.h” 2、使用命名空间USING_NS_CC_EXT; 3、选中工程右键“属性”->”配置属性“->”c/c++”->”常规”->”附加包含目录”中添加“”$(EngineRoot)
安装DCNv2时fatal error: torch/extension.h: No such file or directory 2 | #include ＜torch/extension
m0_45208018的博客
06-10 180
fatal error: torch/extension.h: No such file or directory 2 | #include <torch/extension.h>oh, i meet this problem, my torch version is 0,4,1, so i need git checkout pytorch_0.4 before make.sh
cetnos7下使用g++方式实现c++调用pytorch模型
guazhi8853的博客
11-24 916
#include <torch/script.h> // One-stop header. #include <iostream> #include <memory> int main(int argc, const char *argv[]) { if (argc != 2) { std::cerr << "usage: example-app <path-to-exported-script-module>\
python粘性拓展_PyTorch中的C++扩展实现
weixin_39717367的博客
11-25 300
今天要聊聊用 PyTorch 进行 C++ 扩展。在正式开始前，我们需要了解 PyTorch 如何自定义module。这其中，最常见的就是在 python 中继承torch.nn.Module，用 PyTorch 中已有的 operator 来组装成自己的模块。这种方式实现简单，但是，计算效率却未必最佳，另外，如果我们想实现的功能过于复杂，可能 PyTorch 中那些已有的函数也没法满足我们的要求...
Pytorch自定义C++/CUDA扩展
weixin_44966641的博客
07-04 3370
Pytorch自定义C++/CUDA扩展
PyTorch 添加 C++ 拓展
weixin_43254181的博客
01-22 1543
记录复现一篇博客的过程
PyTorch中构建和调用C++/CUDA扩展
wolaiyeptx的博客
11-30 4755
翻译至PyTorch官方教程 C++ 扩展有两种形式：它们可以使用 setuptools“提前”构建，或者通过 torch.utils.cpp_extension.load()“及时”构建。 我们将从第一种方法开始，稍后讨论后者。 使用setuptools构建 对于“提前”风格，我们通过编写 setup.py 脚本来构建我们的 C++ 扩展，该脚本使用 setuptools 编译我们的 C++ 代码。 对于 LLTM，它看起来很简单： from setuptools import setup, Extens
pytorch forward_pytorch的C++ extension写法
weixin_39827850的博客
11-21 286
2019年的最后一天了，终于填了一个早就想了解的坑。就是关于pytorch如何自定义一个扩展，这里主要是说C++扩展。首先为什么需要扩展？python调用C++的库也是可行的啊。刚开始我也在思考这个问题，觉得没有必要。但是后来深入了解了以后发现还是有必要的。举个栗子，调用始终是使用的是别人的东西，但是扩展则是通过他人的帮助来完成一个属于自己的东西。pytorch的C++ extension和pyt...
评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
红包 添加红包
表情包 插入表情
表情包 代码片
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值