huyanbi

大佬可以用你的预训练模型跑2048个点的吗

@AllenXiangX ，Hello, I have also encountered this issue. I can confirm that I am using the cuda version of the torch. I encountered it while training on point cloud completion.`(spd)...

@AllenXiangX ,I compiled again and the situation is as follows`(spd) root@I1230eab0b100201c25:/hy-tmp/SnowflakeNet/models/pointnet2_ops_lib# python setup.py install running install /usr/local/miniconda3/envs/spd/lib/python3.7/site-packages/setuptools/command/install.py:37: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools....

@AllenXiangX Okay, I'll try

@AllenXiangX .hellow,After trying, I found that it didn't solve the problem.

@yuxumin ，Thank you for your answer, but I still don't quite understand. Could you please help me explain how to operate it specifically

Okay, can I do this? First add the class for fps, then add on line 101 gt = farthest_point_sample(gt, 2048).`def farthest_point_sample(point, npoint): N, D = point.shape xyz = point[:,:3] centroids...

@yuxumin .Boss, it seems that it's not possible. I made a mistake here.`Traceback (most recent call last): File "main.py", line 68, in main() File "main.py", line 62, in main test_net(args,...

What should I do?thank you

or`fps_idx = farthest_point_sample(16384, 2048, points[:, :3]) new_points = points[fps_idx]`