Disaster Classification Computer Vision Model
720 Total Images
View All Images
Dataset Split
Train Set 88%
630Images
Valid Set 8%
60Images
Test Set 4%
30Images
Preprocessing
Auto-Orient: Applied
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Blur: Up to 4px
Noise: Up to 0.5% of pixels