Dataset Versions

v9

2024-03-25 8:11pm

Generated on Mar 25, 2024

Dataset Split

Train Set 94%
13083Images
Valid Set 5%
738Images
Test Set 1%
120Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%
Blur: Up to 1.3px
Noise: Up to 1.56% of pixels