https://github.com/Zehaos/mx-pointnet

A MXNet implementation for PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
https://github.com/Zehaos/mx-pointnet

Last synced: about 2 months ago
JSON representation

A MXNet implementation for PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

• Host: GitHub
• URL: https://github.com/Zehaos/mx-pointnet
• Owner: Zehaos
• License: mit
• Created: 2018-01-12T12:23:09.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2018-01-16T05:06:54.000Z (over 6 years ago)
• Last Synced: 2024-06-12T04:25:27.936Z (3 months ago)
• Language: Python
• Homepage:
• Size: 15.6 KB
• Stars: 15
• Watchers: 5
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-MXNet - mx-pointnet

README

        
# mx-pointnet(in progress)

This repository contains a [MXNet](https://github.com/apache/incubator-mxnet) implementation for the [Pointnet](https://arxiv.org/abs/1612.00593).

The official implementation is avaliable [here](https://github.com/charlesq34/pointnet).

**Note:** Only support point cloud classification Currently.

## Requirements and Dependencies

- Install MXNet(https://github.com/apache/incubator-mxnet) on a machine with CUDA GPU

- Install CUDNN v5 or v6

- Install h5py for python

## Train and Test

- Modify ```config/cfg.py``` by your setting

- ```python train.py```

- ```python test.py```

## Performance

### Classification

| Modelnet40 | Top1-Acc|

|:---:|:---:|

| Ours| 88.0 |

| Reference[1]| 89.2 |

## Reference

[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