 | Acta Crystallographica Section A Acta Crystallographica Section A FOUNDATIONS AND ADVANCES |
journal menu
![[Figure 1]](lu5027fig1mag.jpg)
|
|
Figure 1
Data collection and processing workflow. (a) Data collection from randomly selected scan areas. (b) The resulting 1600 diffraction patterns and images from each scan area were gain-corrected, and the integrated image (made from 1600 frame scans in image mode) was used to assign classes to the individual diffraction frames. (c) 2D diffraction patterns were used for the convolutional neural network (CNN) and the radial intensity averages for the support vector machine (SVM) and fully connected neural network (FCNN) training. |
![[Figure 1]](lu5027fig1.jpg)
| FOUNDATIONS ADVANCES |
ISSN: 2053-2733
access
