Dataset Versions

v7

Test2

Generated on Nov 23, 2024

Dataset Split

Train Set 80%
2745Images
Valid Set 14%
486Images
Test Set 6%
194Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -11° and +11°
Grayscale: Apply to 15% of images
Brightness: Between -23% and +23%
Exposure: Between -10% and +10%
Noise: Up to 1.72% of pixels