Dataset Versions

v3

2024-12-17 8:09pm

Generated on Dec 17, 2024

Dataset Split

Train Set 87%
591Images
Valid Set 8%
57Images
Test Set 4%
28Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -10° and +10°
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -15% and +15%
Noise: Up to 1.8% of pixels