Dataset Versions
v3
2023-10-12 10:33pm
Generated on Oct 12, 2023
325 Total Images
View All Images
Dataset Split
Train Set 88%
285Images
Valid Set 8%
26Images
Test Set 4%
14Images
Preprocessing
Auto-Orient: Applied
Static Crop: 15-85% Horizontal Region, 15-85% Vertical Region
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Shear: ±17° Horizontal, ±17° Vertical
Hue: Between -40° and +40°
Saturation: Between -45% and +45%
Noise: Up to 4% of pixels
Cutout: 3 boxes with 9% size each
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise
Bounding Box: Rotation: Between -20° and +20°
Bounding Box: Exposure: Between -20% and +20%
