Pointnet_Pointnet2_pytorch
Pointnet_Pointnet2_pytorch copied to clipboard
yanx27
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
not a issue, just a simple question that I feel confused when I read the code in S3DISDataLoader.py, can anyone tell me why were only x-axis and y-axis normalized but...
Hi all, We faced an issue with this implementation during the evaluation stage. We got inconsistent test loss results each time we evaluate the same data. We traced the code...
你好，想问下如果我的两类物体的数据标签有重叠（分类分割的是同一类型物体，但部分部件不一样），不像代码中是分隔开的，我应该怎么修改？
Can it work for different number of classes? My class number = 2 Where I change in train_semseg.py? What is label_weights, the value of the similar to class number? Anyone...
Can you explain the meaning of "Best Instance Accuracy" in "train_classification.py" and the distinction with "class accuracy"?
Hi, can you please explain this: https://github.com/yanx27/Pointnet_Pointnet2_pytorch/blob/e365b9f7b9c3d7d6444278d92e298e3f078794e1/data_utils/S3DISDataLoader.py#L70 why you followed this arrangement for the data and why you did not move the centre from the normalized points? ~Thanks
When I use S3DIS dataset, it is working, but when I am using my own dataset, it is stuck at classifier.train()! What is the reason? is it normalization issue? I...