Dataset Versions

v1

2024-01-24 10:44pm

Generated on Jan 24, 2024

Dataset Split

Train Set 84%
48Images
Valid Set 9%
5Images
Test Set 7%
4Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Hue: Between -14° and +14°
Saturation: Between -25% and +25%
Brightness: Between -3% and +3%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels