Hugues THOMAS

You could try to use an older version of python? Or search for how to solve `numpy.distutils._msvccompiler` issues on google. I cannot help much with windows build, as I am...

It could be normal, as the validation during training is performed on a small subset of the whole validation cloud. Depending on which part get picked, the score can be...

Hi @aoligei178, Thanks, they are appearing under my name (hugues.thomas) on the official test set on codalab.

You are right, the exception surely comes from the dataloader. If the bug occurs at a random epoch, it is possible that it is caused by an aberrant input (for...

Actually, the coarser trees were in the TF implementation too. The idea is that potentials are here to ensure regular picking of input spheres across the dataset. Because spheres are...

> Can you link to the TF code where coarser trees are used (for S3DIS), I am not able to find it. Actually, you are right, I cannot find them,...

Well actually, it depends, I noticed performance drops on some datasets too, but on S3DIS, I noticed a performance increase... SO I don't know what to think of TF vs...

Hi @BingHan0458, > what is the meaning of these inputs -- "q_pts, s_pts, neighb_inds, x"? I can't find the relevant description. q_pts (Tensor): query points (M, 3). s_pts (Tensor): support...

Hi @ghasemadi, I need more than that to be able to help you with your problem. What version of python are you using? What version of Numpy? You might need...

First a question. Is it a frame dataset like SemanticKitti or an area like S3DIS. Can you post a picture of the data? Here are some suggestions: - You can...