激光雷达位置识别CrossLoc3D配置全流程

引言

许久未更新，最近配这个环境配了两天，最后决定写个文来记录一下。代码连接

环境创建

代码中要求python37的环境，务必遵守，因为后续安装的pptk库仅在37下有效。但是我们可以先创建好环境后再安装numpy库等，不然太慢了conda install

conda create -n Crossloc python=3.7
conda activate Crossloc

注意在这一步，我们选择使用pip安装pytorch，博主使用conda install装了两个小时还没好要死了。注意先安装pytorch再装

conda install pytorch==1.9.1 torchvision==0.10.1 torchaudio==0.9.1 cudatoolkit=11.3 -c pytorch

后续再安装一点其他库即可

pip install pandas tensorboard numpy -i https://pypi.tuna.tsinghua.edu.cn/simple

conda install openblas-devel -c anaconda
sudo apt-get install openexr libopenexr-dev
conda install -c conda-forge openexr

pip install laspy pytest addict pytorch-metric-learning==0.9.97 yapf==0.40.1 bitarray==1.6.0 h5py transforms3d open3d -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install tqdm setuptools==59.5.0 einops -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install bagpy utm pptk -i https://pypi.tuna.tsinghua.edu.cn/simple
conda install -c conda-forge openexr-python
pip install pyexr pyntcloud -i https://pypi.tuna.tsinghua.edu.cn/simple

最后

git clone https://github.com/rayguan97/crossloc3d.git
cd crossloc3d/MinkowskiEngine
python setup.py install --blas_include_dirs=${CONDA_PREFIX}/include --blas=openblas