Dataset Versions

v2

2024-11-20 10:39pm

Generated on Nov 20, 2024

Dataset Split

Train Set 96%
186Images
Valid Set 2%
4Images
Test Set 2%
3Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -7° and +7°
Shear: ±4° Horizontal, ±5° Vertical
Saturation: Between -9% and +9%
Exposure: Between -16% and +16%
Noise: Up to 0.06% of pixels