Dataset Versions

v1

2024-09-25 4:32am

Generated on Sep 25, 2024

Dataset Split

Train Set 88%
4422Images
Valid Set 8%
427Images
Test Set 4%
203Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -6° and +6°
Shear: ±7° Horizontal, ±7° Vertical
Blur: Up to 1.1px
Noise: Up to 0.7% of pixels