Dataset Versions

v3

2023-12-26 3:45pm

Generated on Dec 26, 2023

Dataset Split

Train Set 89%
3006Images
Valid Set 9%
312Images
Test Set 2%
59Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Vertical
Crop: 0% Minimum Zoom, 12% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -25% and +25%
Blur: Up to 0.5px
Noise: Up to 3% of pixels