ST3D on different classes about st3d HOT 9 CLOSED

It is hard to provide a general solution for all datasets. However, as I know, some researchers achieve amazing results on some custom datasets with multiple categories (approach fully supervised results) with a few adjustments to ST3D. Hence I believe that ST3D should work for other datasets with multiple categories, but need some tuning of hyper-parameters.

from st3d.

I fixed the bugs on multi-category and got good performance on multi-category. Thank you very much! Could you please tell when will you release the code for ST3D++?

from st3d.

Happy to heard that! We don't have a clear plan to release the code since the paper is still in submission. BTW, the techinical modification of ST3D++ is not significant, may be I can support DSNorm and SASD in this repo later. I believe that it should be easy to reproduce our results.

from st3d.

Thank you very much! I would like to see DSNorm and SASD as soon as possible!

from st3d.

For further research, I want to learn from the DSNorm and SASD. Could you please send me the code contains the DSNorm and SASD by email? Thank you very much!

from st3d.

Hello !
I am very interested in your solution for multi-category ST3D as I am working on a similar problem, is there any way you could send it to me by email please ?
Thanks a lot !

from st3d.

Hello ! I am very interested in your solution for multi-category ST3D as I am working on a similar problem, is there any way you could send it to me by email please ? Thanks a lot !

You need to change the pred_labels for ignore in

from st3d.

Excuse me, may i ask ask how to modify the code specifically, applied to multi-class pre-training and multi-class ST3D training

from st3d.

Hello ! I am very interested in your solution for multi-category ST3D as I am working on a similar problem, is there any way you could send it to me by email please ? Thanks a lot !

You need to change the pred_labels for ignore in

ST3D/pcdet/utils/self_training_utils.py

Line 191 in 68a9d3e

pred_labels[ignore_mask] = -1

and others. And change the code for loading pseudo labels of multi-categories in

ST3D/pcdet/datasets/dataset.py

Line 152 in 68a9d3e

gt_names = np.array([self.class_names[0] for n in gt_boxes])

and others.

Excuse me, may i ask how to modify the code specifically, applied to multi-class pre-training and multi-class ST3D training. Or just need to change the top two lines pred_labels[ignore_mask] = -1 gt_names = np.array([self.class_names[0] for n in gt_boxes])

from st3d.