haiyang-w/rbgnet

[CVPR2022] This is the official code of "RBGNet: Ray-based Grouping for 3D Object Detection".

rbgnet's Issues

How do I run this network with my own data?

Dear all, thank you for publishing this work.
I am curious how to use this network on my own data. For example, say I have a PCD for chairs, I do not have the ground truth for this. I just want to run inference script to give me a list of detected objects.
How would be the best way to progress using your network? Any help on this would be very much appreciated.
Thank you for the contribution !!

AttributeError: module ‘torch’ has no attribute ‘searchsorted’

Hello！Congratulations first on your newly accepted CVPR manuscript in 2022. And I am also working on this field. While I am running the project，I meet a problem called module ‘torch’ has no attribute ‘searchsorted’ when running train.py. And I may assume this is due to the different versions of pytorch. Therefore, may I know the substitution of function ‘searchsorted’ in pytorch 1.1
The environment is as follows:
Python=3.6
Pytorch=1.1
CUDA=10.0
spconv=1.0
File “..pcdet/models/dense_heads/rbg_head.py”，line 1140，in _get_fine_points
inds = torch.searchsorted(cdf, u, right=True)

About the usage of spconv

Thanks for your great work. According to the config file and paper, the installation of spconv is only for the compatibility with full mmdet3d/pcdet's compilation. Am I understanding it right?

How to get prediction files on ScanNet and SUNRGBD?

Hi, thanks for your great work! Do you know how to get prediction files on ScanNet and SUNRGBD? Can I just set 'save_to_file' as True when evaluating just like other datasets in OpenPCDet?