pytorch implementation for PointNet

Last update: Dec 30, 2022

Related tags

Overview

PointNet.pytorch

This repo is implementation for PointNet(https://arxiv.org/abs/1612.00593) in pytorch. The model is in pointnet/model.py.

It is tested with pytorch-1.0.

Download data and running

git clone https://github.com/fxia22/pointnet.pytorch
cd pointnet.pytorch
pip install -e .

Download and build visualization tool

cd script
bash build.sh #build C++ code for visualization
bash download.sh #download dataset

Training

cd utils
python train_classification.py --dataset 
   
     --nepoch=
    
      --dataset_type 
     
      
python train_segmentation.py --dataset 
      
        --nepoch=

Use --feature_transform to use feature transform.

Performance

Classification performance

On ModelNet40:

	Overall Acc
Original implementation	89.2
this implementation(w/o feature transform)	86.4
this implementation(w/ feature transform)	87.0

On A subset of shapenet

	Overall Acc
Original implementation	N/A
this implementation(w/o feature transform)	98.1
this implementation(w/ feature transform)	97.7

Segmentation performance

Segmentation on A subset of shapenet.

Class(mIOU)	Airplane	Bag	Cap	Car	Chair	Earphone	Guitar	Knife	Lamp	Laptop	Motorbike	Mug	Pistol	Rocket	Skateboard	Table
Original implementation	83.4	78.7	82.5	74.9	89.6	73.0	91.5	85.9	80.8	95.3	65.2	93.0	81.2	57.9	72.8	80.6
this implementation(w/o feature transform)	73.5	71.3	64.3	61.1	87.2	69.5	86.1	81.6	77.4	92.7	41.3	86.5	78.2	41.2	61.0	81.1
this implementation(w/ feature transform)					87.6											81.0

Note that this implementation trains each class separately, so classes with fewer data will have slightly lower performance than reference implementation.

Sample segmentation result:

pytorch implementation for PointNet

Related tags

Overview

PointNet.pytorch

Download data and running

Performance

Classification performance

Segmentation performance

Links

Owner

Fei Xia

A super lightweight Lagrangian model for calculating millions of trajectories using ERA5 data

The code for our paper Semi-Supervised Learning with Multi-Head Co-Training

code for our paper "Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer"

Waymo motion prediction challenge 2021: 3rd place solution

SCAAML is a deep learning framwork dedicated to side-channel attacks run on top of TensorFlow 2.x.

A tensorflow=1.13 implementation of Deconvolutional Networks on Graph Data (NeurIPS 2021)

Control-Raspberry-Pi-Robot-using-Hand-Gestures - A 4WD Robot car based on Raspberry Pi that controlled by hand gestures(using openCV and mediapipe)

CLUES: Few-Shot Learning Evaluation in Natural Language Understanding

This is an open solution to the Home Credit Default Risk challenge 🏡

3D cascade RCNN for object detection on point cloud

This is code of book "Learn Deep Learning with PyTorch"

Stock-Prediction - prediction of stock market movements using sentiment analysis and deep learning.

[CVPR2021] UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles

[NeurIPS 2021] Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

PyTorch Implementation of NCSOFT's FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis

A PyTorch Implementation of Gated Graph Sequence Neural Networks (GGNN)

On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification

Wind Speed Prediction using LSTMs in PyTorch

This is the formal code implementation of the CVPR 2022 paper 'Federated Class Incremental Learning'.

Differential Privacy for Heterogeneous Federated Learning : Utility & Privacy tradeoffs