/NIPS2017

Code for Boomsma W, Frellsen J (2017) Spherical convolutions and their application in molecular modelling. Advances in Neural Information Processing Systems 30 (NIPS 2017).

Primary LanguagePython

Deepfold

Library for supporting spherical convolution in tensorflow, including sperical and cubed-sphere representation for conducting convolutions on the sphere. The latter is described in detail here:

W. Boomsma, J. Frellsen, Spherical Convolutions and their application in molecular modelling, Conference on Neural Information Processing Systems (NIPS) 30, 2017.