Dataset Versions

v1

2024-04-23 8:31pm

Generated on Apr 24, 2024

Dataset Split

Train Set 87%
642Images
Valid Set 8%
61Images
Test Set 4%
31Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -15% and +15%
Blur: Up to 2.5px