samiepapa / deca Goto Github PK

$ python demos/demo_reconstruct.py -i TestSamples/examples/ --saveDepth True --saveObj True
/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/cuda/__init__.py:125: UserWarning:
NVIDIA GeForce RTX 3090 with CUDA capability sm_86 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_70 sm_75.
If you want to use the NVIDIA GeForce RTX 3090 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/

  warnings.warn(incompatible_device_warn.format(device_name, capability, " ".join(arch_list), device_name))
creating the FLAME Decoder
trained model found. load /home/yongilcho/reposit/DECA/data/deca_model.tar
/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/setuptools/distutils_patch.py:25: UserWarning: Distutils was imported before Setuptools. This usage is discouraged and may exhibit undesirable behaviors or errors. Please use Setuptools' objects directly or at least import Setuptools first.
  warnings.warn(
Traceback (most recent call last):
  File "demos/demo_reconstruct.py", line 130, in <module>
    main(parser.parse_args())
  File "demos/demo_reconstruct.py", line 49, in main
    deca = DECA(config = deca_cfg, device=device)
  File "/home/yongilcho/reposit/DECA/decalib/deca.py", line 50, in __init__
    self._setup_renderer(self.cfg.model)
  File "/home/yongilcho/reposit/DECA/decalib/deca.py", line 53, in _setup_renderer
    set_rasterizer(self.cfg.rasterizer_type)
  File "/home/yongilcho/reposit/DECA/decalib/utils/renderer.py", line 39, in set_rasterizer
    load(name='standard_rasterize_cuda',
  File "/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 963, in load
    return _jit_compile(
  File "/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1170, in _jit_compile
    _write_ninja_file_and_build_library(
  File "/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1264, in _write_ninja_file_and_build_library
    _write_ninja_file_to_build_library(
  File "/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1593, in _write_ninja_file_to_build_library
    cuda_flags = common_cflags + COMMON_NVCC_FLAGS + _get_cuda_arch_flags()
  File "/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1414, in _get_cuda_arch_flags
    raise ValueError("Unknown CUDA arch ({}) or GPU not supported".format(arch))
ValueError: Unknown CUDA arch (8.6) or GPU not supported

$ python demos/demo_reconstruct.py -i TestSamples/examples/ --saveDepth True --saveObj True
Downloading: "https://www.adrianbulat.com/downloads/python-fan/2DFAN4-cd938726ad.zip" to /home/yongilcho/.cache/torch/hub/checkpoints/2DFAN4-cd938726ad.zip
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 91.9M/91.9M [00:52<00:00, 1.83MB/s]
creating the FLAME Decoder
trained model found. load /home/yongilcho/reposit/DECA/data/deca_model.tar
/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/setuptools/distutils_patch.py:25: UserWarning: Distutils was imported before Setuptools. This usage is discouraged and may exhibit undesirable behaviors or errors. Please use Setuptools' objects directly or at least import Setuptools first.
  warnings.warn(
Traceback (most recent call last):
  File "/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1717, in _run_ninja_build
    subprocess.run(
  File "/home/yongilcho/anaconda3/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 "demos/demo_reconstruct.py", line 130, in <module>
    main(parser.parse_args())
  File "demos/demo_reconstruct.py", line 49, in main
    deca = DECA(config = deca_cfg, device=device)
  File "/home/yongilcho/reposit/DECA/decalib/deca.py", line 50, in __init__
    self._setup_renderer(self.cfg.model)
  File "/home/yongilcho/reposit/DECA/decalib/deca.py", line 53, in _setup_renderer
    set_rasterizer(self.cfg.rasterizer_type)
  File "/home/yongilcho/reposit/DECA/decalib/utils/renderer.py", line 39, in set_rasterizer
    load(name='standard_rasterize_cuda',
  File "/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1124, in load
    return _jit_compile(
  File "/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1337, in _jit_compile
    _write_ninja_file_and_build_library(
  File "/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1449, in _write_ninja_file_and_build_library
    _run_ninja_build(
  File "/home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1733, in _run_ninja_build
    raise RuntimeError(message) from e
RuntimeError: Error building extension 'standard_rasterize_cuda': [1/3] /usr/local/cuda/bin/nvcc  -DTORCH_EXTENSION_NAME=standard_rasterize_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include/TH -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/yongilcho/anaconda3/include/python3.8 -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 --compiler-options '-fPIC' -std=c++14 -ccbin=$(which gcc-7) -c /home/yongilcho/reposit/DECA/decalib/utils/rasterizer/standard_rasterize_cuda_kernel.cu -o standard_rasterize_cuda_kernel.cuda.o
FAILED: standard_rasterize_cuda_kernel.cuda.o
/usr/local/cuda/bin/nvcc  -DTORCH_EXTENSION_NAME=standard_rasterize_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include/TH -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/yongilcho/anaconda3/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 --compiler-options '-fPIC' -std=c++14 -ccbin=$(which gcc-7) -c /home/yongilcho/reposit/DECA/decalib/utils/rasterizer/standard_rasterize_cuda_kernel.cu -o standard_rasterize_cuda_kernel.cuda.o
-c: No such file or directory
nvcc fatal   : Failed to preprocess host compiler properties.
[2/3] c++ -MMD -MF standard_rasterize_cuda.o.d -DTORCH_EXTENSION_NAME=standard_rasterize_cuda -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include/TH -isystem /home/yongilcho/.virtualenvs/DECA/lib/python3.8/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /home/yongilcho/anaconda3/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -c /home/yongilcho/reposit/DECA/decalib/utils/rasterizer/standard_rasterize_cuda.cpp -o standard_rasterize_cuda.o
ninja: build stopped: subcommand failed.

$ pip list
Package           Version
----------------- ------------------
chumpy            0.70
face-alignment    1.3.5
future            0.18.2
fvcore            0.1.5.post20211023
imageio           2.13.5
iopath            0.1.9
kornia            0.6.3
llvmlite          0.37.0
networkx          2.6.3
ninja             1.10.2.3
numba             0.54.1
numpy             1.20.3
opencv-python     4.5.5.62
packaging         21.3
Pillow            8.4.0
pip               21.3.1
portalocker       2.3.2
pyparsing         3.0.6
pytorch3d         0.6.1
PyWavelets        1.2.0
PyYAML            5.1.1
scikit-image      0.19.1
scipy             1.7.3
setuptools        49.2.1
six               1.16.0
tabulate          0.8.9
termcolor         1.1.0
tifffile          2021.11.2
torch             1.10.2+cu113
torchaudio        0.10.2+cu113
torchvision       0.11.3+cu113
tqdm              4.62.3
typing_extensions 4.0.1
yacs              0.1.8