Dataset Versions

v1

Final Dataset

Generated on Jan 13, 2024

Dataset Split

Train Set 92%
46404Images
Valid Set 4%
1932Images
Test Set 4%
1932Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Tile: 3 rows x 2 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -15% and +15%
Brightness: Between -10% and +10%