WhiteFireFox / PAPC

PAPC is a deep learning for point clouds platform based on pure PaddlePaddle

English | 简体中文

PAPC

Welcome to PAPC(Paddle PointCloud) which is a deep learning for point clouds platform based on pure PaddlePaddle.

Show

Model Zoo

Clas

• VoxNet
• Kd-Networks
• PointNet-Basic
• PointNet
• PointNet++SSG
• PointNet++MSG

Seg

• Kd-Unet
• PointNet-Basic
• PointNet
• PointNet++SSG
• PointNet++MSG

Detect

• PointRCNN
• Pointpillars-building

Dataset

Based on ShapeNet dataset(.h5 format). Support custom dataset(data format refered to ShapeNet dataset).

Installation

Step 1. Install PaddlePaddle

System Requirements:

• PaddlePaddle >= 2.0.0rc
• Python >= 3.6+

Highly recommend you install the GPU version of PaddlePaddle, due to large overhead of pointcloud models, otherwise it could be out of memory while running the models. For more detailed installation tutorials, please refer to the official website of PaddlePaddle。

Step 2. Download PAPC repo

git clone https://github.com/AgentMaker/PAPC.git

Training

Help For Training

python train.py --help

Quick Training

python train.py

Better Experience

This project is mounted on Baidu AIStudio which provides a free GPU environment like Google Colab. You can run this project on it for free.

Url1: Origin PAPC Project
Url2: PAPC Project

Contact us

Email : [e-mail]