HexagDLy - Processing hexagonally sampled data with CNNs in PyTorch

HexagDLy is a Python-library extending the PyTorch deep learning framework with convolution and pooling operations on hexagonal grids. It aims to ease the access to convolutional neural networks for applications that rely on hexagonally sampled data as, for example, commonly found in ground-based astroparticle physics experiments.

[1]  Colin P.D. Birch,et al.  Rectangular and hexagonal grids used for observation, experiment and simulation in ecology , 2007 .

[2]  Kevin Sahr,et al.  HEXAGONAL DISCRETE GLOBAL GRID SYSTEMS FOR GEOSPATIAL COMPUTING , 2011 .

[3]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[4]  Neil Storey,et al.  A Comparison Between Square and Hexagonal Sampling Methods for Pipeline Image Processing , 1990, Other Conferences.

[5]  Thomas Lohse,et al.  Probing Convolutional Neural Networks for Event Reconstruction in \gamma-Ray Astronomy with Cherenkov Telescopes , 2017 .

[6]  Richard C. Staunton,et al.  The design of hexagonal sampling structures for image digitization and their use with local operators , 1989, Image Vis. Comput..

[7]  M. Huennefeld.  Deep Learning in Physics exemplified by the Reconstruction of Muon-Neutrino Events in IceCube , 2017 .

[8]  P. O. Hulth,et al.  Search for dark matter annihilation in the Galactic Center with IceCube-79 , 2015, 1505.07259.

[9]  Heidelberg,et al.  Gamma-Hadron Separation in Very-High-Energy gamma-ray astronomy using a multivariate analysis method , 2009, 0904.1136.

[10]  Takemasa Miyoshi,et al.  The Non-hydrostatic Icosahedral Atmospheric Model: description and development , 2014, Progress in Earth and Planetary Science.

[11]  Qi Feng,et al.  The analysis of VERITAS muon images using convolutional neural networks , 2016, Proceedings of the International Astronomical Union.

[12]  M. Erdmann,et al.  A deep learning-based reconstruction of cosmic ray-induced air showers , 2017, 1708.00647.

[13]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[14]  T. Lohse,et al.  Application of deep learning methods to analysis of imaging atmospheric Cherenkov telescopes data , 2018, Astroparticle Physics.

[15]  Max Welling,et al.  Spherical CNNs , 2018, ICLR.

[16]  Nathanael Perraudin,et al.  DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications , 2018, Astron. Comput..

[17]  Pierre Vandergheynst,et al.  ShapeNet: Convolutional Neural Networks on Non-Euclidean Manifolds , 2015, ArXiv.

[18]  Juan José Rodríguez-Vázquez,et al.  Artificial Neural Networks in Pattern Recognition , 2018, Lecture Notes in Computer Science.

[19]  G. Piano,et al.  Science with the Cherenkov Telescope Array , 2015 .

[20]  R.M. Mersereau,et al.  The processing of hexagonally sampled two-dimensional signals , 1979, Proceedings of the IEEE.