AiuniAI / Unique3D

[NeurIPS 2024] Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
https://wukailu.github.io/Unique3D/
MIT License
3.11k stars 246 forks source link

ERROR: Failed building wheel for pytorch3d #20

Closed Limbicnation closed 5 months ago

Limbicnation commented 5 months ago

Hi! I am currently testing this repository on Windows Subsystem for Linux (WSL). After running the pip install -r requirements.txt command, I encountered the following error:

WSL_Miniconda_Environments/unique3d/lib/python3.8/site-packages/torch/include -I/mnt/i/WSL_Miniconda_Environments/unique3d/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/mnt/i/WSL_Miniconda_Environments/unique3d/lib/python3.8/site-packages/torch/include/TH -I/mnt/i/WSL_Miniconda_Environments/unique3d/lib/python3.8/site-packages/torch/include/THC -I/mnt/i/WSL_Miniconda_Environments/unique3d/include/python3.8 -c /tmp/pip-req-build-3zhc0h0k/pytorch3d/csrc/ball_query/ball_query.cu -o build/temp.linux-x86_64-cpython-38/tmp/pip-req-build-3zhc0h0k/pytorch3d/csrc/ball_query/ball_query.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' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -std=c++17 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89
      nvcc fatal   : Unsupported gpu architecture 'compute_89'
      error: command '/usr/bin/nvcc' failed with exit code 1
      [end of output]

  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for pytorch3d
  Running setup.py clean for pytorch3d
Successfully built nvdiffrast
Failed to build pytorch3d
ERROR: Could not build wheels for pytorch3d, which is required to install pyproject.toml-based projects
Limbicnation commented 5 months ago
nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Sep_21_10:33:58_PDT_2022
Cuda compilation tools, release 11.8, V11.8.89
Build cuda_11.8.r11.8/compiler.31833905_0
LucioC commented 5 months ago

I was able to install everything on WSL2, just by following the instructions, and had to update OpenGL version for ubuntu, but is not possible to run it because it WSL2 doesn't have Opengl-cuda interop support https://docs.nvidia.com/cuda/wsl-user-guide/index.html#features-not-yet-supported

So I guess you need to install on windows or linux directly.

Limbicnation commented 5 months ago

I was able to install everything on WSL2, just by following the instructions, and had to update OpenGL version for ubuntu, but is not possible to run it because it WSL2 doesn't have Opengl-cuda interop support https://docs.nvidia.com/cuda/wsl-user-guide/index.html#features-not-yet-supported

So I guess you need to install on windows or linux directly.

Thanks for the info! I'll try installing using the Windows instructions instead. I've tested it on Ubuntu 22.04 LTS, and it works well. Having it working on Windows would be great too!