v3

2024-10-25 7:52am

Generated on Oct 25, 2024

Dataset Split

Train Set 91%
159Images
Valid Set 8%
14Images
Test Set 1%
2Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 128x128

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -35° and +35°
Shear: ±13° Horizontal, ±33° Vertical
Saturation: Between -60% and +60%
Blur: Up to 4.9px
Noise: Up to 1.96% of pixels