Crackwatch Computer Vision Dataset
5210 Total Images
View All Images
Dataset Split
Train Set 92%
4809Images
Valid Set 5%
259Images
Test Set 3%
142Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 720x720
Augmentations
Outputs per training example: 3
Rotation: Between -15° and +15°
Saturation: Between -34% and +34%
Brightness: Between -25% and +25%
Noise: Up to 1.88% of pixels