Dataset Versions
v3
2024-06-17 6:08pm
Generated on Jun 17, 2024
1908 Total Images
View All Images
Dataset Split
Train Set 90%
1713Images
Valid Set 7%
131Images
Test Set 3%
64Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (black edges) in 1024x1024
Augmentations
Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±8° Horizontal, ±8° Vertical
Hue: Between -15° and +15°
Saturation: Between -30% and +30%
Exposure: Between -15% and +15%
Blur: Up to 1px
Noise: Up to 0.65% of pixels