a problem from sample

[peng666]

Hello, I found that there seems to be something wrong with using sample to get GT with '02691156/5e44d38e88458ab1e1873a3963e0d14' . What's wrong？ Thanks a lot.

[qinglew]

Could you please give a more detailed description of the error？Screenshots are better.

获取 Outlook for iOShttps://aka.ms/o0ukef

---

发件人: peng666 @.> 发送时间: Friday, March 19, 2021 11:55:46 AM 收件人: qinglew/PCN-PyTorch @.> 抄送: Subscribed @.***> 主题: [qinglew/PCN-PyTorch] a problem from sample (#1)

Hello, I found that there seems to be something wrong with using sample to get GT with '02691156/5e44d38e88458ab1e1873a3963e0d14' . What's wrong？ Thanks a lot.

― You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/qinglew/PCN-PyTorch/issues/1, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AMQMMOH2TYUGRKSXKERRGBTTELDMFANCNFSM4ZOABFDQ.

[peng666]

Thank you for your reply. This is 02691156 / 5e44d38e88458ab1e1873a3963e0d14 in shapenet.v1

This is the result of resampling from the model, gt.pcd

I found that I had more than one model error. Have you ever encountered such a situation？My code comes from PCN's sample.

[qinglew]

I try again with the model you said. I got a good point cloud from the .obj file.

Here is the content of the file generated:

I think you should compile the code in your machine again, and the version of the PCL and VTK should be the same as the information in https://github.com/qinglew/PCN-PyTorch/tree/master/sample. I did this in Ubuntu 18.04 LTS. It seems that you are using Windows OS. I think you should check the generated .pcd file whether there is some right content. You also can write code to visualize the .pcd file generated to check.

[peng666]

Thank you very much. I'll check my environment.