Dataset Versions

v18

2024-05-25 7:38pm

Generated on May 25, 2024

Dataset Split

Train Set 87%
3726Images
Valid Set 4%
177Images
Test Set 8%
357Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 0 remapped, 1 dropped

Augmentations

Outputs per training example: 3
Rotation: Between -5° and +5°
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -12% and +12%
Exposure: Between -15% and +15%
Noise: Up to 0.22% of pixels