Update README.md
This commit is contained in:
Xu Ma
GitHub
parent
5f451a545a
commit
d951ba3b83
112
README.md
112
README.md
|
|
@ -1,86 +1,93 @@
|
|||
# pointMLP-pytorch
|
||||
__Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework__
|
||||
# Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework （ICLR 2022）
|
||||
|
||||
|
||||
|
||||
[](https://paperswithcode.com/sota/3d-point-cloud-classification-on-modelnet40?p=rethinking-network-design-and-local-geometry)
|
||||
|
||||
[](https://paperswithcode.com/sota/3d-point-cloud-classification-on-scanobjectnn?p=rethinking-network-design-and-local-geometry)
|
||||
|
||||
[archived: Feb/3/2022]
|
||||
|
||||
<div align="left">
|
||||
<a><img src="images/smile.png" height="70px" ></a>
|
||||
<a><img src="images/neu.png" height="70px" ></a>
|
||||
<a><img src="images/columbia.png" height="70px" ></a>
|
||||
</div>
|
||||
|
||||
[Project Sites]() | [arXiv]() | Primary contact: [Xu Ma](mailto:ma.xu1@northeastern.edu)
|
||||
|
||||
<div align="center">
|
||||
<img src="overview.png" width="650px" height="300px">
|
||||
<img src="images/overview.png" width="650px" height="300px">
|
||||
</div>
|
||||
|
||||
Overview of one stage in PointMLP. Given an input point cloud, PointMLP progressively extract local features using residual point MLP blocks. In each stage, we first transform local point using a geometric affine module, then local points are are extracted before and after aggregation respectively. By repeating multiple stages, PointMLP progressively enlarge the receptive field and model entire point cloud geometric information.
|
||||
|
||||
## TO DO:
|
||||
- [ ] to be updated by Feb/14 (due to another submission deadline)
|
||||
- [ ] release paper/codes by Feb/7/2022
|
||||
- [ ] update std bug (unstable testing)
|
||||
|
||||
## BibTeX
|
||||
|
||||
@inproceedings{
|
||||
ma2022rethinking,
|
||||
title={Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual {MLP} Framework},
|
||||
author={Xu Ma and Can Qin and Haoxuan You and Haoxi Ran and Yun Fu},
|
||||
booktitle={International Conference on Learning Representations},
|
||||
year={2022},
|
||||
url={https://openreview.net/forum?id=3Pbra-_u76D}
|
||||
}
|
||||
|
||||
|
||||
|
||||
## News & Updates:
|
||||
- [ ] updated pretrained models
|
||||
- [ ] project page
|
||||
- [ ] update std bug (unstable testing in previous version)
|
||||
- [ ] paper/codes release
|
||||
|
||||
## Updates Jan/31/2022:
|
||||
|
||||
We will release an official code here: [http://github.com/13952522076/pointMLP-pytorch](http://github.com/13952522076/pointMLP-pytorch)
|
||||
|
||||
This anonymous link will expire on: **4/2/2022**
|
||||
|
||||
**Note:** this anonymous link is synchronized with [http://github.com/13952522076/pointMLP-pytorch/tree/d2b8dbaa06eb6176b222dcf2ad248f8438582026
|
||||
](http://github.com/13952522076/pointMLP-pytorch/tree/d2b8dbaa06eb6176b222dcf2ad248f8438582026).
|
||||
:point_right::point_right::point_right:**NOTE:** The codes/models/logs for submission version (without bug fixed) can be found here [commit:d2b8dbaa](http://github.com/13952522076/pointMLP-pytorch/tree/d2b8dbaa06eb6176b222dcf2ad248f8438582026).
|
||||
|
||||
|
||||
## For rebuttal
|
||||
|
||||
|
||||
The link to CurveNet on ScanObjectNN : [[link]](https://drive.google.com/drive/folders/1u02_2aK6hfT3Ds81vtd4wv3n3tFGQ3bX?usp=sharing)
|
||||
|
||||
The link to Residual PointNet++ on MOdelNet40: [[link]](https://drive.google.com/drive/folders/1klIpv2QLTVhDWusfQCAMXq-DkYawr-yA?usp=sharing)
|
||||
|
||||
The link to intergrating our Affine to other models: [[DGCNN]](https://drive.google.com/drive/folders/1qDkCKVtF-QXrDceBKAvcoZ4mv9vTaYnR?usp=sharing) [[PointNet++]](https://drive.google.com/drive/folders/1jPfB_8xJjkCQfdRAsL1u6FfABpfFKEC9?usp=sharing)
|
||||
|
||||
To link to more pre-MLP blocks withou pos-MLP blocks: [[link]](https://drive.google.com/drive/folders/1KORIIUZmEJ3FHKPeKj-p8u9m7o5DKnmQ?usp=sharing)
|
||||
|
||||
|
||||
## Pre-trained models
|
||||
|
||||
Please download the pre-trained models and log files here: [[anonymous google drive]](https://drive.google.com/drive/folders/1Jn9HNpPsrq-1XqSmOUtw4cwPMjsIiIpz?usp=sharing)
|
||||
|
||||
|
||||
## Install
|
||||
Please ensure that python3.7+ is installed. We suggest user use conda to create a new environment.
|
||||
|
||||
Install dependencies
|
||||
```bash
|
||||
# 1. clone this repo
|
||||
git clone https://github.com/ma-xu/pointMLP-pytorch.git
|
||||
cd pointMLP-pytorch
|
||||
|
||||
# 2. create a conda virtual environment and activate it
|
||||
conda create -n pointmlp python=3.7 -y
|
||||
conda activate pointmlp
|
||||
|
||||
# 3. install required libs, pytorch 1.8.1, torchvision 0.9.1, etc.
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
Install CUDA kernels
|
||||
```bash
|
||||
# 4. install CUDA kernels
|
||||
pip install pointnet2_ops_lib/.
|
||||
```
|
||||
|
||||
## Classification ModelNet40
|
||||
The dataset will be automatically downloaded, run following command to train
|
||||
|
||||
## Useage
|
||||
|
||||
### Classification ModelNet40
|
||||
**Train**: The dataset will be automatically downloaded, run following command to train.
|
||||
|
||||
By default, it will create a fold named "checkpoints/{modelName}-{msg}-{randomseed}", which includes args.txt, best_checkpoint.pth, last_checkpoint.pth, log.txt, out.txt.
|
||||
```bash
|
||||
cd pointMLP-pytorch/classification_ModelNet40
|
||||
# train pointMLP
|
||||
python main.py --model pointMLP
|
||||
# train pointMLP-elite
|
||||
python main.py --model pointMLPElite
|
||||
# please add other paramemters as you wish.
|
||||
```
|
||||
By default, it will create a fold named "checkpoints/{modelName}-{msg}-{randomseed}", which includes args.txt, best_checkpoint.pth, last_checkpoint.pth, log.txt, out.txt.
|
||||
|
||||
To conduct voting experiments, run
|
||||
|
||||
To conduct voting testing, run
|
||||
```bash
|
||||
# please modify the msg accrodingly
|
||||
python voting.py --model pointMLP --msg demo
|
||||
```
|
||||
|
||||
|
||||
## Classification ScanObjectNN
|
||||
### Classification ScanObjectNN
|
||||
|
||||
- Make data folder and download the dataset
|
||||
```bash
|
||||
|
|
@ -102,7 +109,7 @@ python main.py --model pointMLPElite
|
|||
By default, it will create a fold named "checkpoints/{modelName}-{msg}-{randomseed}", which includes args.txt, best_checkpoint.pth, last_checkpoint.pth, log.txt, out.txt.
|
||||
|
||||
|
||||
## Part segmentation
|
||||
### Part segmentation
|
||||
|
||||
- Make data folder and download the dataset
|
||||
```bash
|
||||
|
|
@ -120,3 +127,22 @@ python main.py --model pointMLP
|
|||
# please add other paramemters as you wish.
|
||||
```
|
||||
|
||||
|
||||
## Acknowledgment
|
||||
|
||||
Our implementation is mainly based on the following codebases. We gratefully thank the authors for their wonderful works.
|
||||
|
||||
[CurveNet](https://github.com/tiangexiang/CurveNet),
|
||||
[PAConv](https://github.com/CVMI-Lab/PAConv),
|
||||
[GDANet](https://github.com/mutianxu/GDANet),
|
||||
[Pointnet2_PyTorch](https://github.com/erikwijmans/Pointnet2_PyTorch)
|
||||
|
||||
## LICENSE
|
||||
PointMLP is under the Apache-2.0 license.
|
||||
Please contact the authors for commercial use.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue