Dataset Versions

v1

2023-12-15 10:32am

Generated on Dec 15, 2023

Dataset Split

Train Set 88%
189Images
Valid Set 8%
18Images
Test Set 4%
9Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-69% Horizontal Region, 0-56% Vertical Region
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -35° and +35°
Shear: ±16° Horizontal, ±21° Vertical
Blur: Up to 1.75px
Noise: Up to 3% of pixels