https://github.com/yanx27/GACNet

Pytorch implementation of 'Graph Attention Convolution for Point Cloud Segmentation'
https://github.com/yanx27/GACNet

gacnet point-cloud s3dis segmentation

Last synced: about 2 months ago
JSON representation

Pytorch implementation of 'Graph Attention Convolution for Point Cloud Segmentation'

• Host: GitHub
• URL: https://github.com/yanx27/GACNet
• Owner: yanx27
• Created: 2019-04-03T05:10:38.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-04-03T13:12:53.000Z (over 5 years ago)
• Last Synced: 2024-07-22T03:37:05.269Z (about 2 months ago)
• Topics: gacnet, point-cloud, s3dis, segmentation
• Language: Python
• Size: 171 KB
• Stars: 162
• Watchers: 4
• Forks: 31
• Open Issues: 13
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Graph Attention Convolution for Point Cloud Segmentation

This is personal pytorch implmentation of GACNet on S3DIS dataset, but **not official version**.

![](pic.png)

## Download Data

Run `download_data.sh` and save dataset in `./indoor3d_sem_seg_hdf5_data/`

## Train Model

Run `python train_semseg.py`

## Announcement

It is only a **personal implmentation**, and the experimental results **do not represent the model in paper**. There are still many hyper parameters that need to be adjusted when the author publishes the source code.

## Environments

Ubuntu 16.04 


Python 3.6.5 


Pytorch 0.4.1