Dataset Versions

v9

2023-04-20 6:57pm

Generated on Apr 20, 2023

Dataset Split

Train Set 82%
2673Images
Valid Set 9%
300Images
Test Set 9%
291Images

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 -15° and +15°
Brightness: Between -25% and +25%
Exposure: Between -20% and +20%
Blur: Up to 2.75px