RandLA-Net

RandLA-Net copied to clipboard

Error when tesing main_SemanticKITTI.py

5

xkhnhms

Format of the .ply files RandLA script generated are not read by open3d's read_point_cloud function

1

Hey @QingyongHu , can you help me understand the right way to import the .ply files because open3d's read_point_cloud function can't import them. I get the error: Read PLY failed:...

samhithaaaa

the difference between the number of classes

8

Hi ; I tried to apply the model on my dataset, I prepared this data as Semantic3D dataset but I have 6 classes instead of 8 classes and I set...

ayoubOUSSM2021

@QingyongHu thanks for you work, I'm asking about the areas used in training the pretrained model you uploaded, thanks alot.

youssef962

can I run on ubuntu20.04 using gpu?

1

youssef962

cannot build nearest_neighbors

3

when building nearest_neighbors from setup.py file it shows the following error: ` running install running build running build_ext skipping 'knn.cpp' Cython extension (up-to-date) building 'nearest_neighbors' extension error: Unable to find...

youssef962

the pnumpy=1.16.1 in the helper_requirements.txt cannot be find

fenfenglitech

Performance on ScanNet

4

Hello @QingyongHu, Thank you for sharing your work! You mentioned in a previous issue that you'll release details on ScanNet and other datasets such NPM3D. Can you please give some...

HaniItani

关于训练Semantic3D的GPU选项

3

你好，我在训练的时候按照python main_Semantic3D.py 中的说明运行代码时cfg设置成了--mode train --gpu 1，但在训练过程中并未占用显存，请问这是否已经在调用GPU训练了

lin1061991611

Needs Training datasets and Epoch running during Test stage on Semantic3D

2

您好，感谢您的开源！ 在对预训练模型的测试过程中，由于服务器磁盘我只解压了reduces-8的测试集部分，不过通过阅读报错和项目代码，发现Test还需要使用到标注为1的一个训练集（我使用的就是数据集下载的.sh的链接前两个场景数据），并且在正式跑test前还需要跑2趟Epoch用于后面的Reproject probs，按理说常规的深度学习的test都是可以直接跑的，请问为什么这里还需要【1、训练集数据，2、用GPU跑非常耗时耗费显存的两个epoch？】 之后才可以输出test结果 谢谢！ Greetings, thanks for the open-source. During the test stage, I only extraced the reduces-8 dataset partially due to the limit of my server's disk size,...

kxdkxd