PointMLP/README.md

40 lines
983 B
Markdown
Raw Normal View History

2021-10-04 07:01:38 +00:00
# pointMLP-pytorch
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
2021-10-04 07:26:41 +00:00
## Install
2021-10-04 07:48:33 +00:00
Please ensure that python3.7+ is installed. We suggest user use conda to create a new environment.
Install dependencies
```bash
pip install -r requirement.txt
```
Install CUDA kernels
```bash
pip install pointnet2_ops_lib/.
```
2021-10-04 07:26:41 +00:00
## Classification ModelNet40
2021-10-04 16:15:43 +00:00
The dataset will be automatically downloaded, run following command to train
2021-10-04 16:11:38 +00:00
```bash
# train pointMLP
python main.py --model pointMLP
# train pointMLP-elite
python main.py --model pointMLPElite
# please add other paramemters as you wish.
```
2021-10-04 16:15:43 +00:00
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
```bash
# please modify the msg accrodingly
python voting.py --model pointMLP --msg demo
```
2021-10-04 16:11:38 +00:00
2021-10-04 07:26:41 +00:00
## Classification ScanObjectNN
## Part segmentation