Dataset Versions

v2

2024-03-14 6:31pm

Generated on Mar 14, 2024

Dataset Split

Train Set 87%
381Images
Valid Set 8%
37Images
Test Set 4%
18Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -10° and +10°
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -20% and +20%
Brightness: Between -24% and +24%
Exposure: Between -11% and +11%
Blur: Up to 3.4px
Noise: Up to 1.56% of pixels