Point cloud data set

[16619884724]

Hello, your work is excellent, I have some questions to be solved:

1. What you input is not the most original coordinate data of the point cloud. How do these modelnet40 npy files get? I want to find the relevant code to process my original point cloud data.
2. In addition, the data fed by the cloud branch, the original dimension is the format of Bx3xN? I am confused about the dimensional transformation problem. Usually, the input point cloud dimension should be BXNXdim, why not see the dimension transformation in your code, but in the defined functions like [gather_neighbor] and [get_neighbor_feature], There is batch_size = x.size()[0] ;num_dim = x.size()[1] ; num_point = x.size()[2], so the input is BXdimXN in your .npy data ? I am very confused.I am looking forward to your answer.