Original tensorflow implementation: https://github.com/charlesq34/pointnet
Package requirement: Python3.6, keras, tensorflow, numpy, matplotlib, h5py
Download the aligned dataset from https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip Put all traning h5 files under Prepdata folder, all testing h5 files under Prepdata_test folder, then run train_cls.py. Accuracy rate will be 82.5%, which is slightly lower than the original implementation.
Download and unzip the shapenet dataset from https://shapenet.cs.stanford.edu/ericyi/shapenetcore_partanno_v0.zip. Run Seg_dataprep.py then train_seg.py.