Dataset Versions

v9

2023-01-17 6:43pm

Generated on Jan 17, 2023

Dataset Split

Train Set 90%
36Images
Valid Set 8%
3Images
Test Set 3%
1Images

Preprocessing

Auto-Orient: Applied

Augmentations

Outputs per training example: 3
Cutout: 3 boxes with 16% size each
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Bounding Box: Rotation: Between -11° and +11°
Bounding Box: Shear: ±15° Horizontal, ±15° Vertical
Bounding Box: Blur: Up to 3.25px
Bounding Box: Noise: Up to 5% of pixels