Dataset Versions

v4

2024-12-06 3:40pm

Generated on Dec 6, 2024

Dataset Split

Train Set 97%
2220Images
Valid Set 2%
36Images
Test Set 1%
28Images

Preprocessing

Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -30% and +30%
Noise: Up to 1.29% of pixels