Skip to content
/ aptbps Public

Density-adaptive distance encoding for machine learning on point clouds

License

Notifications You must be signed in to change notification settings

rdimaio/aptbps

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

APTBPS

Installation

Requirements

  • Python 3.x
  • scikit-learn
  • numpy
  • tqdm
  • KDEpy
  • scipy

pip installation

$ pip3 install git+https://github.com/rdimaio/aptbps

From source

Or, if you prefer, you can install it from source:

# Clone the repository
$ git clone https://github.com/rdimaio/aptbps

# Go into the aptbps folder
$ cd aptbps

# Install aptbps
$ python setup.py install

Usage

import aptbps
from bps import bps

# x is a batch of point clouds in the shape [n_clouds, n_points, n_dims]

# Original bps implementation
x_bps = aptbps.encode(x, bps_cel) 

# 2-partition triangle-gkde aptbps encoding
x_aptbps = aptbps.adaptive_encode(x, n_parts=2, bps_cell_type='dists')

# 8-partition comp-fftkde aptbps encoding
x_aptbps_fftkde = aptbps.adaptive_encode(x, n_parts=8, kde='fft', partitioning='comp', bps_cell_type='dists')

Resources

Contributing

Pull requests are welcome! If you would like to include/remove/change a major feature, please open an issue first.

Acknowledgement

BPS repository

License

This project is licensed under the MIT License - see the LICENSE file for details.

About

Density-adaptive distance encoding for machine learning on point clouds

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages