Dataset Versions
v3
2024-02-15 3:13pm
Generated on Feb 15, 2024
419 Total Images
View All Images
Dataset Split
Train Set 72%
300Images
Valid Set 14%
59Images
Test Set 14%
60Images
Preprocessing
Auto-Orient: Applied
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images
Hue: Between -16° and +16°
Brightness: Between -22% and +22%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels