https://github.com/chinakook/PointCNN.MX

A MXNet implemetation of PointCNN
https://github.com/chinakook/PointCNN.MX

Last synced: about 2 months ago
JSON representation

A MXNet implemetation of PointCNN

• Host: GitHub
• URL: https://github.com/chinakook/PointCNN.MX
• Owner: chinakook
• License: mit
• Created: 2018-03-16T02:00:38.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2018-08-22T03:35:27.000Z (over 6 years ago)
• Last Synced: 2024-08-01T22:41:34.735Z (5 months ago)
• Language: Python
• Size: 47.9 KB
• Stars: 17
• Watchers: 5
• Forks: 6
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-MXNet - PointCNN.MX

README

        
# PointCNN.MX

This is a MXNet implementation of [PointCNN](https://github.com/yangyanli/PointCNN). It is as efficent as the origin Tensorflow implemetation and achieves same accuracy on both classification and segmentaion jobs. See the following references for more information:

```

"PointCNN"

Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen

arXiv preprint arXiv:1801.07791, 2018.

```

[https://arxiv.org/abs/1801.07791](https://arxiv.org/abs/1801.07791)

# Usage

We've tested code on MNIST only.

```python

python ./download_datasets.py -d mnist -f ./

python ./prepare_mnist_data.py -f ./mnist/zips

python ./pointcnn_cls.py

```

# License

Our code is released under MIT License (see LICENSE file for details).