我的环境：Ubuntu18.04和22.04，torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1  python3.7和3.8都跑过

第一种方法：

一行代码就行，剩下的就是漫长的等待

pip install git+https://github.com/facebookresearch/pytorch3d.git@v0.7.3

# 注意如果需要其他版本，后面的0.7.3可以修改 

https://github.com/facebookresearch/pytorch3d

网址里面可以选择自己需要的版本

第二种方法：

这是FFHQ项目中提到的安装pytorch3d和nvdiffrast的方法：

mkdir thirdparty
cd thirdparty
git clone https://github.com/facebookresearch/iopath
git clone https://github.com/facebookresearch/fvcore
git clone https://github.com/facebookresearch/pytorch3d
git clone https://github.com/NVlabs/nvdiffrast
conda install -c bottler nvidiacub
pip install -e iopath
pip install -e fvcore
pip install -e pytorch3d
pip install -e nvdiffrast

第三种方法：

运行以下代码：

import sys
import torch
import subprocess

pyt_version_str=torch.__version__.split("+")[0].replace(".", "")
version_str="".join([
    f"py3{sys.version_info.minor}_cu",
    torch.version.cuda.replace(".",""),
    f"_pyt{pyt_version_str}"
])
subprocess.run(["pip", "install", "fvcore", "iopath"])
subprocess.run(["pip", "install", f"--no-index", f"--no-cache-dir", f"pytorch3d", f"-f", f"https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html"])