Deep residual networks for crystallography trained on synthetic data

Mendez, D.; Holton, J.M.; Lyubimov, A.Y.; Hollatz, S.; Mathews, I.I.; Cichosz, A.; Martirosyan, V.; Zeng, T.; Stofer, R.; Liu, R.; Song, J.; McPhillips, S.; Soltis, M.; Cohen, A.E.

doi:10.1107/S2059798323010586

Acta Crystallographica Section D
Acta Crystallographica
Section D STRUCTURAL BIOLOGY

IUCr IT WDC

home archive editors for authors for readers submit subscribe open access

view article

Figure 4
Downsampling scheme. A region of a PILATUS 6M image with a Bragg reflection is shown (with numbers indicating pixel values). Raw data (left) are divided into blocks of pixels (indicated by red dashed lines). This occurs for both simulated and experimental data. The `conditioned' pixel value (right) is the square root of the maximum pixel value within each block, cast to an integer (floor operation). Block size varies according to the detector model; either 2 × 2 blocks (PILATUS 6M) or 4 × 4 blocks (EIGER 16M, JUNGFRAU 16M and Rayonix 340) were used.

STRUCTURAL
BIOLOGY

ISSN: 2059-7983

Volume 80| Part 1| January 2024| Pages 26-43

https://doi.org/10.1107/S2059798323010586

Open

access

Follow Acta Cryst. D

Search IUCr Journals		doi		Advanced search
Author		volume	page