Dataset Versions

v1

2024-07-25 3:08pm

Generated on Jul 25, 2024

Dataset Split

Train Set 91%
630Images
Valid Set 5%
37Images
Test Set 3%
23Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 2048x2048
Auto-Adjust Contrast: Using Contrast Stretching

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Hue: Between -19° and +19°
Saturation: Between -25% and +25%
Brightness: Between -19% and +19%
Exposure: Between -12% and +12%
Blur: Up to 2.7px
Noise: Up to 1.65% of pixels