Dataset Versions

v3

2024-05-10 12:16pm

Generated on May 10, 2024

Dataset Split

Train Set 92%
2460Images
Valid Set 4%
119Images
Test Set 3%
92Images

Preprocessing

Auto-Orient: Applied
Static Crop: 0-100% Horizontal Region, 47-84% Vertical Region
Resize: Stretch to 256x256
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Rotation: Between -15° and +15°
Saturation: Between -33% and +33%
Exposure: Between -15% and +15%