AlexBob

> Hi @zoomkinseok , As far as I know, it doesn't consider your questions. I'm curious why you want GT sampled objects not to appear behind non-annotated objects, I think...

Hi @thangvubk @mcmingchang , According to https://github.com/thangvubk/SoftGroup/blob/11dcbfd74b7660a2b82ac6473af107849c7d545f/docs/config_explanation.md, we can see that `instance_voxel_cfg -> spatial_shape` means the dimension of instance in terms of voxels, i.e., H, W, D of instance will...

For Ubuntu 20.04, please just change the python version into 3.8.10, which can solve this problem well.

> @Rolandxx7 thanks for letting me know this. I think it is mostly because of the initial radius. Please reply to me with the following: > > 1. Are you...

> okay. First, are you able to reproduce the original PointRCNN with PointNet++? This is the first thing you have to make sure. If you can reproduce PointRCNN, then, my...

> hi Roland, 3D dataset is super sensitive to the radius. It defines the receptive fields. An important reason for Overfitting is an improper radius. > > PointRCNN has played...

@guochengqian Hi, I have used Pointnext-s and tried the scheme of changing the radius you told me, and the accuracy is indeed improved. However, it still does not exceed the...

> @Rolandxx7 our code also support the multi-grouping version of pointnet++. but you might tune the code just a little bit to make the multi-grouping pointnext work. @guochengqian Thank you...