【已解决】ValueError: Unknown CUDA arch (8.9) or GPU not supported

这个问题在配置Obbdetection环境的过程中卡了很久，主要是出现在运行了如下代码之后

pip install -v -e .

出现了这样的报错

Traceback (most recent call last):
      File "<string>", line 2, in <module>
      File "<pip-setuptools-caller>", line 34, in <module>
      File "I:\Obbdetection-master\setup.py", line 195, in <module>
        setup(
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\__init__.py", line 117, in setup
        return distutils.core.setup(**attrs)
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\_distutils\core.py", line 183, in setup
        return run_commands(dist)
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\_distutils\core.py", line 199, in run_commands
        dist.run_commands()
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\_distutils\dist.py", line 954, in run_commands
        self.run_command(cmd)
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\dist.py", line 950, in run_command
        super().run_command(command)
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\_distutils\dist.py", line 973, in run_command
        cmd_obj.run()
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\command\develop.py", line 35, in run
        self.install_for_development()
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\command\develop.py", line 112, in install_for_development
        self.run_command('build_ext')
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\_distutils\cmd.py", line 316, in run_command
        self.distribution.run_command(command)
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\dist.py", line 950, in run_command
        super().run_command(command)
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\_distutils\dist.py", line 973, in run_command
        cmd_obj.run()
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\command\build_ext.py", line 98, in run
        _build_ext.run(self)
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\_distutils\command\build_ext.py", line 359, in run
        self.build_extensions()
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\torch\utils\cpp_extension.py", line 670, in build_extensions
        build_ext.build_extensions(self)
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\_distutils\command\build_ext.py", line 476, in build_extensions
        self._build_extensions_serial()
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\_distutils\command\build_ext.py", line 502, in _build_extensions_serial
        self.build_extension(ext)
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\command\build_ext.py", line 263, in build_extension
        _build_ext.build_extension(self, ext)
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\setuptools\_distutils\command\build_ext.py", line 557, in build_extension
        objects = self.compiler.compile(
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\torch\utils\cpp_extension.py", line 635, in win_wrap_ninja_compile
        cuda_post_cflags = win_cuda_flags(cuda_post_cflags)
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\torch\utils\cpp_extension.py", line 507, in win_cuda_flags
        cflags + _get_cuda_arch_flags(cflags))
      File "C:\Users\admin\.conda\envs\pytorch_obbcp38\lib\site-packages\torch\utils\cpp_extension.py", line 1438, in _get_cuda_arch_flags
        raise ValueError("Unknown CUDA arch ({}) or GPU not supported".format(arch))
    ValueError: Unknown CUDA arch (8.9) or GPU not supported
    error: subprocess-exited-with-error

    × python setup.py develop did not run successfully.
    │ exit code: 1
    ╰─> See above for output.

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

本人配置是4060ti，使用的torch版本是1.7.1-cp37+cu110（torchvision-0.8.2-cp37+cu110,torchaudio-0.7.2-cp37），以下是解决方案：

首先是根据ValueError前的路径找到虚拟环境中的cpp_extension.py，可以直接用记事本打开该文件，找到如下代码：

supported_arches = ['3.5', '3.7', '5.0', '5.2', '5.3', '6.0', '6.1', '6.2',
                        '7.0', '7.2', '7.5', '8.0', '8.6']

在最后补上对应gpu的算力即可（我的4060ti的算力是8.9，于是有修改如下）

supported_arches = ['3.5', '3.7', '5.0', '5.2', '5.3', '6.0', '6.1', '6.2',
                        '7.0', '7.2', '7.5', '8.0', '8.6','8.9']