Dataset Versions
v1
2024-12-18 3:13pm
Generated on Dec 18, 2024
3249 Total Images
View All Images
Dataset Split
Train Set 86%
2808Images
Valid Set 9%
288Images
Test Set 5%
153Images
Preprocessing
Auto-Orient: Applied
Auto-Adjust Contrast: Using Histogram Equalization
Tile: 3 rows x 3 columns
Augmentations
Outputs per training example: 2
90° Rotate: Clockwise
Rotation: Between -15° and +15°
Shear: ±11° Horizontal, ±11° Vertical
Hue: Between -45° and +45°
Saturation: Between -30% and +30%
Blur: Up to 5.6px
Noise: Up to 1.68% of pixels