Height Detection Dataset

v9

buildings3

Generated on Jul 5, 2024

Dataset Split

Train Set 96%
621Images
Valid Set 3%
17Images
Test Set 1%
8Images

Preprocessing

Auto-Orient: Applied
Static Crop: 4-100% Horizontal Region, 16-79% Vertical Region
Resize: Stretch to 1280x1280

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Saturation: Between -25% and +25%
Brightness: Between -22% and +22%
Noise: Up to 0.83% of pixels