Dataset Versions
v3
Third Version
Generated on May 7, 2024
703 Total Images
View All Images
Dataset Split
Train Set 89%
624Images
Valid Set 6%
45Images
Test Set 5%
34Images
Preprocessing
Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 0-75% Vertical Region
Resize: Fit (white edges) in 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Saturation: Between -25% and +25%
Blur: Up to 2.1px