Dataset Versions

v1

2023-04-18 8:24am

Generated on Apr 18, 2023

Dataset Split

Train Set 88%
828Images
Valid Set 8%
76Images
Test Set 4%
39Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 28% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -33% and +33%
Blur: Up to 1.75px
Noise: Up to 6% of pixels
Cutout: 3 boxes with 20% size each