hang up while loading deca_model

[puckikk1202]

My terminal hanged up while loading the given deca_model. deca.py line 88. I think it is not processing anything task. trained model found. load D:\gitdoc\DECA\data\deca_model.tar Have anyone happened to this? Please let me know if you have any solutions.

[bxiong97]

I am having the same issue. I'm using Windows 10, Visual Studio Code, Powershell to run the code. I already installed all those requirements successfully. I can also load deca_model.tar However, I got an error message regarding the compiler version... I wonder why? Could anyone help with that? Many thanks!

creating the FLAME Decoder
trained model found. load D:\Research\Face Reconstruction\DECA\DECA\data\deca_model.tar
C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py:270: UserWarning: Error checking compiler version for cl: [WinError 2] The system cannot find the file specified
  warnings.warn('Error checking compiler version for {}: {}'.format(compiler, error))
INFO: Could not find files for the given pattern(s).
Traceback (most recent call last):
  File "demos/demo_reconstruct.py", line 127, in <module>
    main(parser.parse_args())
  File "demos/demo_reconstruct.py", line 46, in main
    deca = DECA(config = deca_cfg, device=device)
  File "D:\Research\Face Reconstruction\DECA\DECA\decalib\deca.py", line 50, in __init__
    self._setup_renderer(self.cfg.model)
  File "D:\Research\Face Reconstruction\DECA\DECA\decalib\deca.py", line 53, in _setup_renderer
    set_rasterizer(self.cfg.rasterizer_type)
  File "D:\Research\Face Reconstruction\DECA\DECA\decalib\utils\renderer.py", line 41, in set_rasterizer
    extra_cuda_cflags = ['-std=c++14', '-ccbin=$$(which gcc-7)']) # cuda10.2 is not compatible with gcc9. Specify gcc 7
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 974, in load
    keep_intermediates=keep_intermediates)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1179, in _jit_compile 
    with_cuda=with_cuda)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1272, in _write_ninja_file_and_build_library
    with_cuda=with_cuda)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1645, in _write_ninja_file_to_build_library
    with_cuda=with_cuda)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1747, in _write_ninja_file
    'cl']).decode().split('\r\n')
  File "C:\Users\Beibei\.conda\envs\py36\lib\subprocess.py", line 356, in check_output
    **kwargs).stdout
  File "C:\Users\Beibei\.conda\envs\py36\lib\subprocess.py", line 438, in run
    output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['where', 'cl']' returned non-zero exit status 1.

[MollyHoo]

I am having the same issue. I'm using Windows 10, Visual Studio Code, Powershell to run the code. I already installed all those requirements successfully. I can also load deca_model.tar However, I got an error message regarding the compiler version... I wonder why? Could anyone help with that? Many thanks!

creating the FLAME Decoder
trained model found. load D:\Research\Face Reconstruction\DECA\DECA\data\deca_model.tar
C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py:270: UserWarning: Error checking compiler version for cl: [WinError 2] The system cannot find the file specified
  warnings.warn('Error checking compiler version for {}: {}'.format(compiler, error))
INFO: Could not find files for the given pattern(s).
Traceback (most recent call last):
  File "demos/demo_reconstruct.py", line 127, in <module>
    main(parser.parse_args())
  File "demos/demo_reconstruct.py", line 46, in main
    deca = DECA(config = deca_cfg, device=device)
  File "D:\Research\Face Reconstruction\DECA\DECA\decalib\deca.py", line 50, in __init__
    self._setup_renderer(self.cfg.model)
  File "D:\Research\Face Reconstruction\DECA\DECA\decalib\deca.py", line 53, in _setup_renderer
    set_rasterizer(self.cfg.rasterizer_type)
  File "D:\Research\Face Reconstruction\DECA\DECA\decalib\utils\renderer.py", line 41, in set_rasterizer
    extra_cuda_cflags = ['-std=c++14', '-ccbin=$$(which gcc-7)']) # cuda10.2 is not compatible with gcc9. Specify gcc 7
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 974, in load
    keep_intermediates=keep_intermediates)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1179, in _jit_compile 
    with_cuda=with_cuda)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1272, in _write_ninja_file_and_build_library
    with_cuda=with_cuda)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1645, in _write_ninja_file_to_build_library
    with_cuda=with_cuda)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1747, in _write_ninja_file
    'cl']).decode().split('\r\n')
  File "C:\Users\Beibei\.conda\envs\py36\lib\subprocess.py", line 356, in check_output
    **kwargs).stdout
  File "C:\Users\Beibei\.conda\envs\py36\lib\subprocess.py", line 438, in run
    output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['where', 'cl']' returned non-zero exit status 1.

same question. do you solve it?

[num-doc]

same question. do you solve it? creating the FLAME Decoder trained model found. load E:\objectPy\DECA-master\data\deca_model.tar

[HDYYZDN]

我的终端在加载给定deca_model时挂起。deca.py 行 88。我认为它没有处理任何任务。 有没有人发生过这种情况？如果您有任何解决方案，请告诉我。trained model found. load D:\gitdoc\DECA\data\deca_model.tar

你找到standard_rasterize_cuda文件夹，然后删除lock文件，是锁住了，就可以解决了

[HDYYZDN]

我遇到了同样的问题。我正在使用 Windows 10、可视化工作室代码、强力外壳来运行代码。我已经成功安装了所有这些要求。我也可以加载deca_model.tar但是，我收到了有关编译器版本的错误消息...我想知道为什么？任何人都可以帮忙吗？非常感谢！

creating the FLAME Decoder
trained model found. load D:\Research\Face Reconstruction\DECA\DECA\data\deca_model.tar
C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py:270: UserWarning: Error checking compiler version for cl: [WinError 2] The system cannot find the file specified
  warnings.warn('Error checking compiler version for {}: {}'.format(compiler, error))
INFO: Could not find files for the given pattern(s).
Traceback (most recent call last):
  File "demos/demo_reconstruct.py", line 127, in <module>
    main(parser.parse_args())
  File "demos/demo_reconstruct.py", line 46, in main
    deca = DECA(config = deca_cfg, device=device)
  File "D:\Research\Face Reconstruction\DECA\DECA\decalib\deca.py", line 50, in __init__
    self._setup_renderer(self.cfg.model)
  File "D:\Research\Face Reconstruction\DECA\DECA\decalib\deca.py", line 53, in _setup_renderer
    set_rasterizer(self.cfg.rasterizer_type)
  File "D:\Research\Face Reconstruction\DECA\DECA\decalib\utils\renderer.py", line 41, in set_rasterizer
    extra_cuda_cflags = ['-std=c++14', '-ccbin=$$(which gcc-7)']) # cuda10.2 is not compatible with gcc9. Specify gcc 7
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 974, in load
    keep_intermediates=keep_intermediates)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1179, in _jit_compile 
    with_cuda=with_cuda)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1272, in _write_ninja_file_and_build_library
    with_cuda=with_cuda)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1645, in _write_ninja_file_to_build_library
    with_cuda=with_cuda)
  File "C:\Users\Beibei\.conda\envs\py36\lib\site-packages\torch\utils\cpp_extension.py", line 1747, in _write_ninja_file
    'cl']).decode().split('\r\n')
  File "C:\Users\Beibei\.conda\envs\py36\lib\subprocess.py", line 356, in check_output
    **kwargs).stdout
  File "C:\Users\Beibei\.conda\envs\py36\lib\subprocess.py", line 438, in run
    output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['where', 'cl']' returned non-zero exit status 1.

同样的问题。你解决了吗？

你找到standard_rasterize_cuda文件夹，然后删除lock文件，是锁住了，就可以解决了

[Daksitha]

were you able to find a solution? I am also running on Windows 10.