Dataset Versions
v3
V1_civil_damage
Generated on Jan 31, 2024
3799 Total Images
View All Images
Dataset Split
Train Set 87%
3324Images
Valid Set 8%
317Images
Test Set 4%
158Images
Preprocessing
Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 224x224
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Saturation: Between -25% and +25%
Exposure: Between -10% and +10%
Blur: Up to 1.7px
Noise: Up to 0.1% of pixels