Dataset Versions

v1

2024-12-05 9:31pm

Generated on Dec 5, 2024

Dataset Split

Train Set 88%
549Images
Valid Set 8%
52Images
Test Set 4%
26Images

Preprocessing

Auto-Orient: Applied
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Hue: Between -16° and +16°
Exposure: Between -15% and +15%
Blur: Up to 1px