Dataset Versions

v2

2024-11-07 2:58am

Generated on Nov 7, 2024

Dataset Split

Train Set 84%
27Images
Valid Set 9%
3Images
Test Set 6%
2Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (reflect edges) in 1280x1280
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Rotation: Between -5° and +5°
Brightness: Between -15% and +15%
Blur: Up to 0.5px