Dataset Versions

v1

2022-12-01 9:57am

Generated on Dec 1, 2022

Dataset Split

Train Set 92%
426Images
Valid Set 8%
36Images
Test Set %
0Images

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 -21° and +21°
Shear: ±15° Horizontal, ±15° Vertical
Blur: Up to 2.5px
Noise: Up to 5% of pixels
Cutout: 3 boxes with 12% size each