Frederick Hong
Frederick Hong
I am pretty sure this guy is a japanese who does not have a "QQ", so to speak...
> Have any other reproduce the result successfully? I got the best valid acc 88% in seaching process with the random seed setted as 2(without cutout data precessing). May I...
> > Joules or Voltus. > > Both of them are commercial tools. > > hi, 请问你有做过rocketcore / BOOM 的功耗面积仿真吗？ Hi, @meton-robean 请问你找到了相关的工具吗，另外可以分享一下这篇paper的名字吗？谢谢。
Hi, @suyunzzz @zhijian-liu , sorry to bother you. I am looking for the torchsparse counterpart for `MinkowskiInterpolation()`. Any update on this issue? Or any possible suggestions for me to investigate...
Hi, did you try the **phase 1** as mentioned in the readme? How will it affect the training performance?
Thank you for your kind reply. Just wondering, did you run into errors below for phase 1? ``` | WARNING | models.neucon_network:compute_loss:242 - target: no valid voxel when computing loss...
> I was training with batch_size=1 and changing it to batch_size=2 Correct me if I am wrong, but I guess this problem is caused by the insufficient fragments amount during...
I don't think so.
> Hi, > > Yes, the simdat package is my private lib. I do have plan to replace it to make it easier to run the demo script, but unfortunately,...
3090 with cuda11.4 good to go. For 11.2 should be with no problem.