Dataset Versions

v1

2023-04-14 6:11pm

Generated on Apr 14, 2023

Dataset Split

Train Set 87%
720Images
Valid Set 8%
64Images
Test Set 6%
48Images

Preprocessing

Tile: 4 rows x 4 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Saturation: Between -15% and +15%
Brightness: Between -15% and +15%
Exposure: Between -15% and +15%
Mosaic: Applied