view article
Figure 8
Peaks located by BraggNN when peaks deviate from the geometric center. The error is the Euclidean distance ( l2) between truth (solid-line cross) and BraggNN prediction (dotted-line cross). Upper row: using BraggNN trained without data augmentation. Bottom row: using BraggNN trained with data augmentation for the same peaks as the upper row.

IUCrJ
Volume 9| Part 1| January 2022| Pages 104-113
ISSN: 2052-2525
https://doi.org/10.1107/S2052252521011258