Dataset Versions
v9
2024-01-19 1:42am
Generated on Jan 18, 2024
788 Total Images
View All Images
Dataset Split
Train Set 76%
600Images
Valid Set 16%
124Images
Test Set 8%
64Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (reflect edges) in 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Blur: Up to 1.5px