Flip Augmentation: Difference between revisions

From Civitai Wiki
Jump to navigation Jump to search
(Created page with "Artificially double the number of training images by performing a horizontal flip. If your data is not left-right symmetrical (which will be the case when training humans, subjects), this option should be avoided. Category:Training")
 
(No difference)

Latest revision as of 07:23, 11 October 2023

Artificially double the number of training images by performing a horizontal flip. If your data is not left-right symmetrical (which will be the case when training humans, subjects), this option should be avoided.