Dataset Versions

v8

2024-02-29 10:56pm

Generated on Feb 29, 2024

Dataset Split

Train Set 88%
276Images
Valid Set 8%
25Images
Test Set 4%
13Images

Preprocessing

Auto-Orient: Applied
Static Crop: 55-70% Horizontal Region, 6-98% Vertical Region
Resize: Fit within 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -5° and +5°
Shear: ±5° Horizontal, ±5° Vertical
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%