application hindsight

Open KuangSongyang1113 opened this issue 3 years ago • 3 comments

If I want to apply hindsight to my project, do I need to prepare my dataset just like lyft dataset?

Dec 06 '22 00:12 KuangSongyang1113

Hi KuangSongyang1113! Thanks for your interest! Yes, you can prepare your dataset as described in the repo.

Dec 06 '22 23:12 YurongYou

By installing spconv with python setup.py bdist_wheel，I got "Caffe2: CUDA detected:10.1. But actually I got cuda version 11.8 with nvidia-smi command in terminal. How did spconv check the cuda version?

Dec 08 '22 11:12 KuangSongyang1113

I am not exactly sure, but it might be also related to the cudatoolkit you installed via conda. Did it throw an error? If not it should be fine, since cuda should be backward compatible.

Dec 08 '22 23:12 YurongYou