Dataset Versions

v1

v1

Generated on Jun 2, 2023

Dataset Split

Train Set 83%
15Images
Valid Set 11%
2Images
Test Set 6%
1Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 22% Maximum Zoom
Rotation: Between -10° and +10°
Shear: ±12° Horizontal, ±9° Vertical
Brightness: Between -16% and +16%
Blur: Up to 2.5px