Implementation of PointNet-1 on Point Cloud segmentation problem by Keras(based Tensorflow).
This repo is implementation for PointNet(https://arxiv.org/abs/1612.00593) in Keras. The model is in pointnet.py.
Original tensorflow implementation: https://github.com/charlesq34/pointnet
Pytorch implementation: https://github.com/fxia22/pointnet.pytorch
This code was built and developed based on this repo: https://github.com/garyli1019/pointnet-keras
Windows & OS X & Linux:
conda env create -f environment.yml
Below is guide to download data, train network then test prediction on Shapenet dataset
- Download and unzip the Shapenet dataset to
./pointnet1_keras/DATA
directory - Run training, type on terminal:
python train_segmentation.py
- Run testing, type on terminal:
python test_segmentation.py
NGUYEN CONG MINH – @Facebook – minhnc.edu.tw@gmail.com
Distributed under the MIT license. See LICENSE
for more information.
https://github.com/minhncedutw/pointnet1_keras
- Fork it (https://github.com/yourname/yourproject/fork)
- Create your feature branch (
git checkout -b feature/fooBar
) - Commit your changes (
git commit -am 'Add some fooBar'
) - Push to the branch (
git push origin feature/fooBar
) - Create a new Pull Request