Dataset Versions
v4
orient_tile_flip_rotate_bright
Generated on Sep 14, 2023
444 Total Images
View All Images
Dataset Split
Train Set 85%
378Images
Valid Set 10%
45Images
Test Set 5%
21Images
Preprocessing
Auto-Orient: Applied
Tile: 2 rows x 2 columns
Modify Classes: 1 remapped, 0 dropped
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Brightness: Between -25% and +25%