Dataset Versions

v3

2023-01-27 2:59pm

Generated on Jan 27, 2023

Dataset Split

Train Set 83%
15Images
Valid Set 11%
2Images
Test Set 6%
1Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -45° and +45°
Hue: Between -22° and +22°
Brightness: Between -33% and +33%
Exposure: Between -12% and +12%
Blur: Up to 0.75px