Dataset Versions

v3

2023-09-14 11:51pm

Generated on Sep 14, 2023

Dataset Split

Train Set 85%
633Images
Valid Set 9%
64Images
Test Set 6%
47Images

Preprocessing

Auto-Orient: Applied
Static Crop: 38-63% Horizontal Region, 31-75% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Saturation: Between -20% and +20%
Brightness: Between -25% and +25%
Blur: Up to 2px
Noise: Up to 5% of pixels