Coder Social home page Coder Social logo

pointnet-in-pytorch's Introduction

(Probably) the simplest PointNet implementation in Pytorch

  • Neural network uses only 10 lines of code (model.py)
  • Operates shape classification task on ShapeNet

Usage

cd pointnet.pytorch
./download.sh
cd ..
python3 classify.py

Requirements

  • Pytorch
  • CUDA (You can workaround by commenting out something.cuda() calls)

Classification performance

On A subset of shapenet, epoch=250, batchsize=32, number of points in the pointcloud data = 2500.

Overall Acc
Original implementation N/A
pointnet-pytorch 82.9%
pointnet.pytorch(w/o feature transform) 98.1
pointnet.pytorch(w/ feature transform) 97.7
This Implementation 99.8

pointnet-in-pytorch's People

Contributors

yamaguchi1024 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.