Dataset Versions

v2

meregeaug_classification

Generated on Nov 7, 2023

Dataset Split

Train Set 88%
2514Images
Valid Set 8%
238Images
Test Set 4%
116Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -25% and +25%
Noise: Up to 5% of pixels