Dataset Versions
v2
2024-07-19 9:43pm
Generated on Jul 19, 2024
203 Total Images
View All Images
Dataset Split
Train Set 86%
174Images
Valid Set 9%
19Images
Test Set 5%
10Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 960x960
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Grayscale: Apply to 15% of images
Hue: Between -20° and +20°
Saturation: Between -25% and +25%
Exposure: Between -10% and +10%
Blur: Up to 1.8px