search

charlesq34 / pointnet

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Other
4.71k stars 1.44k forks source link

Questions about sem_seg of our own outdoor scene dataset! #126

Open Jaiy opened 6 years ago

Jaiy commented 6 years ago

Hi, I,m interested in the great work, now I want to use the network to handle my own dataset. The dataset I have is different from the dataset mentioned in the project. The input data only has the XYZ ,intensity but doesn't have RGB. If I want to use the dataset to do semantic segmentation, how do I handle the dataset? Do I only write the XYZ value to the .txt files or add the intensity value ？And how can I modify the scripts of making HDF5 if only have the XYZ value? Anybody could provide some suggestions? Thanks a lot!

L-YeZhu commented 5 years ago

It's up to you whether to add the intensity value or not. For the generation of HDF5 files, take a look into the /utils/data_prep_util.py/def save_h5 which is also used in gen_indoor3d_h5.py, shouldn't be difficult to modify the scripts, all you need to do is to change the parameter of data_dim in gen_indoor3d_h5.py.