疯狂世界

> Hello @Aflexiblebox, thank you for your questions. > > It looks like: > > 1. SMARTS somehow did not install correctly. > > > * The command `which scl`...

It worked well, I reduce the version number to pytorch-1.5.1

> Yes, it seems there is a typo here, and the corresponding function should be uvd2xyz_nvidia() , thanks for your correction! > > During our experiments, we didn't notice significant...

> Hi @NOTGOOOOD, thank you for your interest in our work. I'm sorry for not getting back to you sooner. > > About the consistency between frames: There could be...

Replaced `value.type()` with `value.scalar_type()` in `ms_deform_attn_cuda.cu` can solve this issue. My env torch=2.9.0 & torchvision=0.24.0 & cuda 13.0

> Thanks for your open source code I am trying to train the model on KITTI. So I want to ask, how DEPTH_SCALE value is decided? currently, for tartan, it's...

Hi, dear developer, how is going on ? I also need to use the ONNX model to predict.