刘彦超

删掉CodecCommander.kext就没问题，layout-id还是30，亲测可用 

normals是用来存储每个点的法向信息，isforks是用来存储是否分叉部分的语义标签，codebook是相似度矩阵标签，这些标注信息需要你进行标注后放进hdf5文件中。

The source code you asked is not open yet. You may refer to the [L1 skeleton](http://vcc.szu.edu.cn/research/2013/L1skeleton.html) and implement it.

I added the link for baiduyun in README. Please check. BTW, it's all ok for me to access the OneDrive files.

Well, the GT skeletons are obtained from the labeled mesh dataset that is not shared yet. We use the axis of each cylinder to get the GT skeleton. The code...

OK, I'll find time to pack those files. BTW, is there any free net disk? My Google Drive and OneDrive are full.

Thanks! I just uploaded the skeletons to my OneDrive. You can access by this [link](https://1drv.ms/u/s!Am5H_4z5WHyYdj2bBsp9-9tw_NI?e=AoMWBX). This package contains all GT skeletons for our test data. You can check the filenames...

Sorry, we didn't generate the associated radius for every skeleton edge. You may estimate the radius by yourself. > Hi @marktube , > > Is it possible that you could...

Sorry, we didn't generate for the training data. > Hi @marktube > > Do you have GT skeletons for the training data too? > > Cheers, Harry

You may need to install nvcc corresponding to your runtime pytorch version.