j_linlian的博客

os.walk()

pytorch多卡训练

Mitsuba渲染3D点云（颜色角度设置）初始设置

screen 后台命令

显卡是3090，算力不够#删除原来的Torchpip uninstall torchpip install torch==1.7.0+cu110 torchvision==0.8.1+cu110 torchaudio===0.7.0 -f https://download.pytorch.org/whl/torch_stable.html

conda config --remove-key channels conda config --add channels http://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/conda config --add channels http://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/conda config --add channels http://mirrors.tuna.ts.

导入 language_tool_python，tool = language_tool_python.LanguageTool('en-US') 报错注意：我的程序是在服务器上跑的，查了APIUsing language_tool_python locally：import language_tool_pythontool = language_tool_python.LanguageTool('en-US')Using language_tool_python with the p

import open3d as o3dimport numpy as nppcd_load = o3d.io.read_point_cloud("chair.ply")# convert Open3D.o3d.geometry.PointCloud to numpy arrayxyz_load = np.asarray(pcd_load.points)print(xyz_load)

将x.split() 改成 str(x).split()