Dataset Versions
v7
2024-11-18 10:57pm
Generated on Nov 18, 2024
1725 Total Images
View All Images
Dataset Split
Train Set 92%
1581Images
Valid Set 4%
73Images
Test Set 4%
71Images
Preprocessing
Auto-Orient: Applied
Static Crop: 20-82% Horizontal Region, 20-82% Vertical Region
Resize: Fill (with center crop) in 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -20° and +20°
Shear: ±16° Horizontal, ±10° Vertical
Bounding Box: Flip: Horizontal
Bounding Box: Rotation: Between -21° and +21°