Dataset Versions

v3

2024-11-01-0300

Generated on Nov 1, 2024

Dataset Split

Train Set 93%
420Images
Valid Set 7%
34Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (black edges) in 2048x2048

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -5° and +5°
Shear: ±5° Horizontal, ±5° Vertical
Brightness: Between -4% and +4%
Exposure: Between -4% and +4%
Noise: Up to 0.1% of pixels