Dataset Versions

v1

2024-05-20 4:21pm

Generated on May 20, 2024

Dataset Split

Train Set 90%
1656Images
Valid Set 6%
109Images
Test Set 4%
70Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±12° Horizontal, ±12° Vertical
Saturation: Between -25% and +25%
Brightness: Between -13% and +13%
Blur: Up to 0.9px
Noise: Up to 1.25% of pixels