Dataset Versions

v8

2024-12-07 10:44pm

Generated on Dec 7, 2024

Dataset Split

Train Set 91%
180Images
Valid Set 8%
16Images
Test Set 1%
1Images

Preprocessing

Auto-Orient: Applied
Static Crop: 18-87% Horizontal Region, 13-84% Vertical Region
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 26% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±4° Horizontal, ±4° Vertical
Blur: Up to 0.8px
Noise: Up to 0.02% of pixels