Dataset Versions

v7

2024-02-24 12:24am

Generated on Feb 23, 2024

Dataset Split

Train Set 88%
216Images
Valid Set 8%
20Images
Test Set 4%
10Images

Preprocessing

Auto-Orient: Applied
Static Crop: 45-68% 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%