Cat

Can I just use class MultiBoxLoss(nn.Module) in this file to replace my original detection loss and everything is done? https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/loss/multibox_loss.py

Do you mean I should revise the code provided at https://github.com/ScanNet/ScanNet/tree/master/BenchmarkScripts/ScanNet200 ? By the way, is the predicted mesh provided? I supose it may facilitate further model improvement. One more...

I'm sorry for not getting back to you sooner. We did not test different tensor shapes using the MindSpore code.

> Thanks for the question. Did you also use the backbones pre-trained with WS? Also, make sure every WS-Conv2d is followed by an activation normalization layer; otherwise, use a regular...