https://github.com/Gaozhongpai/PaiConvPoint

Official repository for the paper "PAI-Conv: Permutable Anisotropic Convolutional Networks for Learning on Point Clouds" [Classification for uniformly sampled data]
https://github.com/Gaozhongpai/PaiConvPoint

Last synced: about 2 months ago
JSON representation

Official repository for the paper "PAI-Conv: Permutable Anisotropic Convolutional Networks for Learning on Point Clouds" [Classification for uniformly sampled data]

• Host: GitHub
• URL: https://github.com/Gaozhongpai/PaiConvPoint
• Owner: Gaozhongpai
• Created: 2020-05-18T06:46:37.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2021-03-15T02:27:34.000Z (over 3 years ago)
• Last Synced: 2024-07-21T21:43:38.025Z (2 months ago)
• Language: Python
• Homepage:
• Size: 676 KB
• Stars: 5
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        

# PAI-Conv: Permutable Anisotropic Convolutional Networks for Learning on Point Clouds [Classification]

![Pai-Conv](data/images/pai-conv.png "Pai-Conv operation")

## Point Cloud Classification

* Run the training script:

``` 1024 points

python main.py --exp_name=paigcnn_1024 --model=paigcnn --num_points=1024 --k=20 --use_sgd=True

```

``` 2048 points

python main.py --exp_name=paigcnn_2048 --model=paigcnn --num_points=2048 --k=40 --use_sgd=True

```

* Run the evaluation script after training finished:

``` 1024 points

python main.py --exp_name=paigcnn_1024_eval --model=paigcnn --num_points=1024 --k=20 --use_sgd=True --eval=True --model_path=checkpoints/paigcnn_1024/models/model.t7

```

``` 2048 points

python main.py --exp_name=paigcnn_2048_eval --model=paigcnn --num_points=2048 --k=40 --use_sgd=True --eval=True --model_path=checkpoints/paigcnn_2048/models/model.t7

```

* Run the evaluation script with pretrained models:

``` 1024 points

python main.py --exp_name=paigcnn_1024_eval --model=paigcnn --num_points=1024 --k=20 --use_sgd=True --eval=True --model_path=pretrained/model.1024.t7

```

``` 2048 points

python main.py --exp_name=paigcnn_2048_eval --model=paigcnn --num_points=2048 --k=40 --use_sgd=True --eval=True --model_path=pretrained/model.2048.t7

```

# Data Organization

The following is the organization of the dataset for 8192 points expected by the code:

    * dataset/

        * train/ (created by data_generation.py)

        * test/ (created by data_generation.py)

#### Acknowlegements:

The structure of this codebase is borrowed from [DGCNN](https://github.com/WangYueFt/dgcnn).