Danila Rukhovich

Hi @zhouzaida , done. I haven't tried `torch.cuda.Event` before, hope my script is right. Also don't think that the decrease of speed is important here.

Hi, @Tai-Wang. I think yes, it is the similar problem. The thing is that the intersection of 2 rotated boxes is a convex polygon with from 1 to 8 vertices....

Hi @Angericky , According to the author of the original rotated iou [implementation](https://github.com/lilanxiao/Rotated_IoU) the result may be inaccurate in some corner cases [1](https://github.com/lilanxiao/Rotated_IoU/issues/39#issuecomment-1056978008), [2](https://github.com/lilanxiao/Rotated_IoU/issues/8). Actually it is a bug. However...

Do you have plans to release the code for your FCOS3D on NuScenes in near future?

Hi @dihuangdh , Were you able to reproduce `73.4` on ScanNet with voxel size of 2cm? Btw looks like even the author of `MinkowskiEngine` can not reproduce it with the...

Hi @Steven-m2ai , The overfitting issues are strange from my point of view, 2000 image should be enough. Can you share your config, train/val metrics, some info about dataset (indoor/outdoor,...

> If you do not mind, could I email you the extra details about the dataset? I think yes, if there is something more to share. > The projection matrices...

> Yes, I have set n_classes to 1 But in your config it is 10. However it is not important. I saw your images. It must be much better on...

Hard to help you here :( Does reducing the model size help?

Hi Garrick, Thanks for your interest in our research. I will try to answer some of your questions. First, I've never tried to run this code on images in the...