RandLA-Net issues

Test point cloud with pretrained model

1

Hello, I want to use the point cloud I collected to test the pre-trained model on semanticKITTI. I just convert the ply file to .npy and put it in velodyne,...

jmwang0117

How to do inference on unlabelled data

1

I have trained the model on custom dataset using same S3DIS classes and prepared data also in same way, i could see the output for validation data, now how can...

Mythili-kannan

The old codalab is no longer valid.

2

According to this link: https://groups.google.com/g/codalab-competitions/c/xJlHTZAgztM The old codalab is offline now, and I cant submit any new trained result to the evaluation server. Could u please move the old challenge...

AlberTgarY

s3dis area1 验证miou不到20%

3

使用s3dis area1作为验证集，在linux和windows上训练100次后miou不到20%，重复训练很多次了都提不上去，为什么？环境:linux/windows,tensorflow-gpu=2.6,nvidia 1065-ti 4g内存，batchsize=1 ![image](https://user-images.githubusercontent.com/38464816/259427090-bdb38f22-ef13-424e-b234-40883990a394.jpeg)

gxushine

Coordinate System for S3DIS

Hi, I would like to inquire details about the coordinate system used in S3DIS dataset. Thank you.

hsekki

Multi frame visualization of SemanticKitti

1

Hi qingyong, I want to know how to realize the multi frame visualization of semantic Kitti. Is it through open3d? Thanks. Best

sunqi405873120

Inquiry Regarding Inference on Unlabeled Data Using RandLA-Net

I've been working with RandLA-Net, specifically mimicking the setup used for the S3DIS dataset, for semantic segmentation of point cloud data, focusing on building facades. While achieving promising results on...

ome-13