Dataset Versions

v1

2024-01-03 9:32pm

Generated on Jan 3, 2024

Dataset Split

Train Set 88%
762Images
Valid Set 8%
72Images
Test Set 4%
36Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -15° and +15°
Noise: Up to 0.42% of pixels
Cutout: 10 boxes with 12% size each