hyangwinter

No, the data distributions of these two datasets are very different. If you do this, the result will get a big performance loss. You should retrain this model on KITTI.

Well, I have not tested this model on the KITTI dataset. If you are interested, you can refer to the official implementation to replace FlyingThings3D dataloader with KITTI dataloader.

Hi, My CUDA version is 10.0. The problem looks like the extension is not compiled properly. I found several pages for you that might cause this error: https://stackoverflow.com/questions/28451859/cuda-invalid-device-function-how-to-know-architecture-code https://stackoverflow.com/questions/17599189/what-is-the-purpose-of-using-multiple-arch-flags-in-nvidias-nvcc-compiler But...

[This page](https://en.wikipedia.org/wiki/CUDA) shows the relationship between GPUs and their compute capability. For example, my RTX 2080 Ti compute capability is 7.5, so the parameter of `arch` and `code` is `compute_75`...

It seems that mismatched NVCC vs CUDA Runtime version is the root cause. Please refer to this issue for more information: https://github.com/facebookresearch/detectron2/issues/62#issuecomment-542447753