How to save the repaired point cloud？

[dfg112d]

Using the trained model, how to specify to repair a broken point cloud and save the repaired point cloud?

[hzxie]

Please describe your problem more specifically.

[dfg112d]

训练好的模型如何对它的修复效果进行测试，能不能想二维图像识别一样，输入一个待识别的图像，输出识别后的图像，输入一个残缺的点云，输出修复后的点云

…

------------------ 原始邮件 ------------------ 发件人: "hzxie/GRNet" ***@***.***>; 发送时间: 2022年5月18日(星期三) 下午3:17 ***@***.***>; ***@***.******@***.***>; 主题: Re: [hzxie/GRNet] How to save the repaired point cloud？ (Issue #38) Please describe your problem more specifically. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>

[hzxie]

We didn't provide the code single file inference.
Instead, you can use the --inference option for runner.py to generate completed point clouds given a data loader.