Dataset Versions

v1

2023-03-03 12:38pm

Generated on Mar 3, 2023

Dataset Split

Train Set 86%
552Images
Valid Set 7%
44Images
Test Set 7%
48Images

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°
Shear: ±15° Horizontal, ±15° Vertical
Noise: Up to 5% of pixels