view article
Figure 3
Demonstration of a mini-batch of patches (11 × 11 pixels) with data augmentation for model training. (a) The peak maxima is in the center of the patch. (b) The peak maxima is intentionally offset by up to ±2 pixels in the horizontal and vertical directions for the same peaks.

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