This repository contains a MXNet implementation for the Pointnet. The official implementation is avaliable here.
Note: Only support point cloud classification Currently.
- Install MXNet(https://github.com/apache/incubator-mxnet) on a machine with CUDA GPU
- Install CUDNN v5 or v6
- Install h5py for python
- Modify
config/cfg.py
by your setting python train.py
python test.py
Modelnet40 | Top1-Acc |
---|---|
Ours | 88.0 |
Reference[1] | 89.2 |
[1] Charles R. Qi, et al. "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation" https://arxiv.org/abs/1612.00593 (2016).
[2] Chen, Tianqi, et al. "Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems." arXiv:1512.01274 (2015).
[3] MXNet training code is based largely on Tusimple's resnet implementation, https://github.com/TuSimple/resnet.mxnet