Dataset Versions
v3
Wallcrack_v1
Generated on Dec 20, 2024
7834 Total Images
View All Images
Dataset Split
Train Set 73%
5706Images
Valid Set 14%
1065Images
Test Set 14%
1063Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 200x200
Grayscale: Applied
Auto-Adjust Contrast: Using Adaptive Equalization
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 2
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -45° and +45°
Brightness: Between -15% and +15%
Noise: Up to 0.1% of pixels