Dataset Versions

v3

2024-09-19 11:56pm

Generated on Sep 19, 2024

Dataset Split

Train Set 77%
339Images
Valid Set 11%
50Images
Test Set 11%
50Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -30% and +30%
Blur: Up to 1.2px
Noise: Up to 3.15% of pixels
Cutout: 6 boxes with 10% size each