Fictionarry / ER-NeRF

[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
https://fictionarry.github.io/ER-NeRF/
MIT License
906 stars 125 forks source link

have a problem installing pytorch3d #68

Closed zhuyang2356 closed 8 months ago

zhuyang2356 commented 8 months ago

My cuda version is 11.4 I use the following commands:

conda create -n ernerf python=3.10 conda activate ernerf conda install pytorch==1.12.1 torchvision==0.13.1 cudatoolkit=11.3 -c pytorch

cd pathToProject git clone https://github.com/Fictionarry/ER-NeRF.git cd ER-NeRF-main

install pyaudio having a problem, using the following commands to achieve success.

apt-get update apt-get install portaudio19-dev apt-get install python3-all-dev pip install pyaudio -i https://pypi.tuna.tsinghua.edu.cn/simple pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

while using this command to install pytorch3d, pip install "git+https://github.com/facebookresearch/pytorch3d.git" have these errors:

copying pytorch3d/datasets/r2n2/r2n2_synset_dict.json -> build/lib.linux-x86_64-cpython-310/pytorch3d/datasets/r2n2 running build_ext error: [Errno 2] No such file or directory: '/usr/local/cuda/bin/bin/nvcc' [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 Failed to build pytorch3d ERROR: Could not build wheels for pytorch3d, which is required to install pyproject.toml-based projects

I thought the problem may be because the pytorch3d version has changed, can author give details of the pytorch3d? Or author can have a solution?

zhuyang2356 commented 8 months ago

i changed my enviroment variable cuda_home from /usr/local/cuda/bin to /usr/local/cuda, and it works. I will follow and see if things have any futher problems.

nicongger commented 6 months ago

conda install -c fvcore -c iopath -c conda-forge fvcore iopath conda install pytorch3d -c pytorch3d -c pytorch -c conda-forge