Cylinder3D
Cylinder3D copied to clipboard
xinge008
Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)
Hey, thank you for the great paper and code! Does there exist code to visualize the predictions? I couldn't find it. Thanks in advance!
 Got a lot of labels, I want to know is it possible to visualize these results? using SemanticKITTI
Really thanks for sharing this awesome code ! I'm really looking forward to do some experiments with this great model, but now I'm struggling with the run time. In my...
Table 1: Results of our proposed method and state-of-the-art  Segmentation methods on SemanticKITTI test set. Note that all results are obtained from the literature, where post-processing, flip & rotation...
I read the code ，it do not have the point-wise refine moduls，Can you share？？
I find it has 'semantic-kitti-multiscan.yaml' in your repository, do you have a multi-scan pretrained model? If I want to train multi-scan data, what should I do? Thanks.
Thanks for your impressive works! These codes may help with the error of the spconv.
does the pretrain model MIOU is best?? I test it on semantic kitti val dataset ,MIOU is low ,about 45. It's the same with nuscenes. Is there is wrong ??
你好，很抱歉打扰您！ 1.请问我如何使用自己标注的数据集进行训练？ 2.我的数据集格式需要像semantic-kitti一样分成train/val/test的sequence吗？（如果要，各需要多少个sequence呢？） 非常感谢您的建议！
Hi, while trying the below command: > python demo_folder.py --demo-folder demo_folder --save-folder demo_save I had the following error: > terminate called after throwing an instance of 'std::bad_alloc' > what(): std::bad_alloc...
