Dataset Versions

v5

2024-06-06 8:37am

Generated on Jun 6, 2024

Dataset Split

Train Set 85%
2127Images
Valid Set 7%
175Images
Test Set 8%
200Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -45° and +45°
Shear: ±14° Horizontal, ±14° Vertical
Saturation: Between -18% and +18%
Exposure: Between -8% and +8%