Dataset Versions

v6

2024-09-05 2:48pm

Generated on Sep 5, 2024

Dataset Split

Train Set 82%
324Images
Valid Set 9%
36Images
Test Set 9%
36Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (black edges) in 640x640
Tile: 6 rows x 6 columns
Modify Classes: 0 remapped, 3 dropped

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -15° and +15°
Brightness: Between -15% and +15%
Blur: Up to 0.9px