HexagDLy-Processing hexagonally sampled data with CNNs in PyTorch
HexagDLy-Processing hexagonally sampled data with CNNs in PyTorch
复制标题
DOI：
10.1016/j.softx.2019.02.010
复制
发表时间：
2019-01-01
期刊：
影响因子：
3.4
通讯作者：
Holch, Tim L.
中科院分区：
文献类型：
--
作者：
Steppa, Constantin;Holch, Tim L.
hexdly是一个python库，扩展了PyTorch深度学习框架，在六边形网格上进行卷积和池化操作。它的目标是简化卷积神经网络应用程序的访问，这些应用程序依赖于六边形采样数据，例如，通常在地面天体粒子物理实验中发现。(C) 2019作者。Elsevier B.V.出版
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. (C) 2019 The Authors. Published by Elsevier B.V.