cracks segmentation Computer Vision Model
1500 Total Images
View All Images
Dataset Split
Train Set 96%
1431Images
Valid Set 2%
34Images
Test Set 2%
35Images
Preprocessing
Auto-Orient: Applied
Augmentations
Outputs per training example: 3
Rotation: Between -17° and +17°
Brightness: Between -23% and +23%
Noise: Up to 6% of pixels