Dataset Versions

v2

2023-11-15 11:32am

Generated on Nov 15, 2023

Dataset Split

Train Set 88%
42Images
Valid Set 8%
4Images
Test Set 4%
2Images

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: ±15° Horizontal, ±15° Vertical
Blur: Up to 2.5px
Cutout: 3 boxes with 10% size each