Dataset Versions

v19

2024-04-02 4:17am

Generated on Apr 2, 2024

Dataset Split

Train Set 100%
5292Images
Valid Set 0%
3Images
Test Set 0%
3Images

Preprocessing

Auto-Orient: Applied
Dynamic Crop: Class: not
Resize: Fit within 156x145
Auto-Adjust Contrast: Using Adaptive Equalization

Augmentations

Outputs per training example: 49
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Saturation: Between -25% and +25%
Brightness: Between 0% and +25%
Exposure: Between -15% and +15%