Dataset Versions

v14

2024-10-26 2:24am

Generated on Oct 26, 2024

Dataset Split

Train Set 90%
2208Images
Valid Set 8%
200Images
Test Set 2%
54Images

Preprocessing

Auto-Orient: Applied
Resize: Fit within 640x640
Grayscale: Applied
Modify Classes: 6 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 10% Maximum Zoom
Rotation: Between -5° and +5°
Shear: ±5° Horizontal, ±5° Vertical
Brightness: Between -5% and +5%
Exposure: Between -5% and +5%
Blur: Up to 1px