ZhuLifa

Results 45 comments of ZhuLifa

Hi @wojtat , Only two results are saved in`args.saved_path/submit` and `args.saved_path/results.pkl` in this evaluation script. If both of them are not what you need, you may update the code to...

> Hi yewzijian: > > I am trying to train the model on my own datasets, but the model output 'nan' when training several epoch. I find the 'nan' are...

Hi vinits5, Glad to hear from your. And i have sent the trained model by the email you provided above. I observed some partial-to-complete registration results may not good due...

It's still not working in version 1.8.1

您好 @xiaobaitu123344, 配对点是近似的,如何得到可以看一下[3DMatch论文](https://openaccess.thecvf.com/content_cvpr_2017/papers/Zeng_3DMatch_Learning_Local_CVPR_2017_paper.pdf) Figure 2.

Hi, @fb059 , could you help to provide your config for `voxel_size` and `point_cloud_range` ? And then `print(xi.size())` in https://github.com/zhulf0804/PointPillars/blob/57af3f50fd3442e6e5c22467e16d28033c4cc51a/model/pointpillars.py#L179

> voxel_size is [0.25, 0.25, 8] > > and point_cloud_range is [-50, -50, -5, 50, 50, 3]. > > And when I print(xi.size()) in pointpillars.py, the output is torch.Size([6, 128,...

Hi @fb059, it seems there are no elements in tensor `features`. Please help check features.size() in https://github.com/zhulf0804/PointPillars/blob/57af3f50fd3442e6e5c22467e16d28033c4cc51a/model/pointpillars.py#L76 and https://github.com/zhulf0804/PointPillars/blob/57af3f50fd3442e6e5c22467e16d28033c4cc51a/model/pointpillars.py#L91