Dataset Versions

v2

test_ver

Generated on Sep 16, 2024

Dataset Split

Train Set 87%
426Images
Valid Set 8%
41Images
Test Set 4%
20Images

Preprocessing

Auto-Orient: Applied
Static Crop: 0-100% Horizontal Region, 0-100% Vertical Region
Resize: Fit within 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 10% Maximum Zoom
Rotation: Between -9° and +9°
Shear: ±3° Horizontal, ±3° Vertical
Brightness: Between -20% and +20%