garyli1019 / pointnet-keras

Keras implementation for Pointnet

MIT License

122 stars 42 forks source link

classification deep-learning keras point-cloud pointnet segmentation

readme

pointnet-keras

Original tensorflow implementation: https://github.com/charlesq34/pointnet

Package requirement: Python3.6, keras, tensorflow, numpy, matplotlib, h5py

Results

Segmentation Sample

seg_sample

How to Run code:

Classification:

Download the aligned dataset from Link
Put all traning .h5 files under Prepdata folder, all testing .h5 files under Prepdata_test folder
Run train_cls.py. Accuracy rate will be 82.5%, which is slightly lower than the original implementation.

Segmentation:

Download and unzip the shapenet dataset from Link.
Run Seg_dataprep.py then train_seg.py.

Point Architecture

Input Transformation Net: Input: Nx3 point cloud sample, Output: 3x3 transformation net
Feature Transformation Net:
Global Feature: Input: Nx3 point cloud sample multiply input T_net. Output: 1*1024 global feature
Classification Net: Input: Nx3 point cloud sample multiply input T_net. Output: 1x40 softmax prediction