Dataset Versions

v1

Test 0 Version

Generated on Dec 9, 2023

Dataset Split

Train Set 88%
96Images
Valid Set 8%
9Images
Test Set 4%
4Images

Preprocessing

Auto-Orient: Applied

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 22% Minimum Zoom, 42% Maximum Zoom
Rotation: Between -20° and +20°
Brightness: Between -30% and +30%
Exposure: Between -40% and +40%
Blur: Up to 2.5px
Noise: Up to 6% of pixels
Cutout: 3 boxes with 10% size each